测试服务器并观察其运行

阅读约需 103分钟 分钟,8节中含6个示例。

版次 2026.11.14 示例于 2026年11月19日 通过 70个示例中有70个通过 变化内容

AI 翻译。由人工以英文核验。 我们如何制作图书

译自英文版图书,版次 2026.11.14。 阅读原文

读完本章,你将能够:在内存中和通过 HTTP 测试 Model Context Protocol 服务器的工具;在会破坏客户端的模式变更发布之前将其发现;把一次已记录的宿主运行重放为回归测试;用 OpenTelemetry 追踪工具调用;衡量模型选对工具的频率;以及在不破坏现有客户端的前提下停用一个工具。本章中关于协议的结论适用于规范的 2026-07-28 修订版,关于 SDK 的结论适用于 Python SDK,即 mcp 2.3.0。

构建处理工单的宿主一章结尾时,商店支持团队使用的宿主 lib.ticket_host 已针对两台服务器处理了商店的全部 48 张工单。这两台服务器是商店自己的服务器和合作方的包裹追踪服务器,模型的回复取自录制文件 ticket-runs。录制文件是保存在 examples/data/recorded/ 下的模型输出,因此这次运行在每台机器上的重放结果都相同,且无需调用模型。

那次运行留下了两个问题。宿主为 36 of 48 张工单选对了第一个工具,但没有任何信息说明它在哪些工单上选错,也没有说明原因。在退款工单上,模型向客户写的回复仿佛退款已经完成,而在要求退款的工单中,真正调用到 issue_refund 的只有 0 of 7。商店的服务器和宿主在不断变化:描述被改写,字段被改名,工具被替换。其中任何一种变化都可能破坏客户端,而服务器一侧却没有一次调用失败。

Model Context Protocol(MCP)为团队搭建检查提供了几样基础:每个工具的类型化模式,每个请求的 _meta 中的追踪上下文,以及工具列表的变更通知。本章就在这些基础上构建商店的检查。三个新模块承载这套设置。lib.testing 运行一个 pytest 模块,并为每个测试输出一行稳定的结果。lib.contract 比较一个工具模式的两个发布版本。lib.queue_replay 重放第 10 章的队列运行,并对照宿主实际发出的调用,检查每条回复所作的承诺。本章有两个示例重放录制文件 ticket-runs,其余示例不使用模型,本章自身也不调用模型。

这部分尚未翻译,因此以英文显示。

Test tools in memory

最近一次修改见于版次 2026.11.11

A test of a server's tools should run with no port and no subprocess, so that it can run on every change. The Python SDK's Client gives you that: passed a server object instead of a URL or launch parameters, it connects to the server in the same process. The SDK's testing guide calls this the way to test a server, with the line "No subprocess. No port. Nothing on a wire" (testing). In the default mode="auto", the connection is a pair of DirectDispatchers, which hand each request to the server's handler as a Python object, with no streams, no JSON-RPC framing and no initialize handshake (mcp/client/client.py, _connect_inproc; mcp/shared/direct_dispatcher.py).

Two details matter in a test. raise_exceptions=True makes a failure outside a tool's body, such as a bug in a handler, come back with its real message instead of a sanitised "Internal server error". It doesn't change what a tool's own exception does: that is still a result with is_error=True, as it is for any client (testing). The SDK also stamps the server's identity into each result's _meta, so a test that compares whole results has to clear result.meta first (same page). Asserting on the fields a test is about avoids both the stamp and the SDK guide's snapshot library, inline-snapshot, which the book doesn't pin. Async tests need no extra plugin: anyio, which the SDK depends on, ships a pytest plugin that runs any test marked pytest.mark.anyio (AnyIO testing).

What the in-memory path skips matters as much as what it covers. With no HTTP layer, an in-memory test never meets the checks a Streamable HTTP server makes on headers, Origin and Host, never sees a server-sent event, and never carries trace context, as Trace calls with OpenTelemetry shows. The SDK's documentation adds that the in-process path doesn't deliver standalone notifications, such as a change to the tool list (client caching). A suite that is all in memory can pass while every HTTP client fails.

The shop's tests run against chapter 3's server, lib.shop_tools, from Design tools a model can use, with the shop's API on loopback for each test, served by the fixture shop_api_env from lib.testing. Three tests run in memory: an order's status comes back as structured fields, an unknown order comes back as a tool execution error that names find_orders, and an order ID in the wrong form is refused before the tool runs. The fourth serves the same tools over Streamable HTTP on loopback and sends a tools/call whose Mcp-Name header names a different tool from its body: a request the SDK's client never sends, and one an in-memory client can't express. Run as a script, the file runs its own tests with pytest 9.2.0.

test-tools-in-memory.py Python 3.12.15 · cryptography 50.0.2 · httpx2 2.16.2 · jsonschema 4.26.0 · mcp 2.3.0 · mcp-types 2.3.0 · pydantic 2.14.3 · pytest 9.2.0 · starlette 1.10.0 · uvicorn 0.54.0 通过
"""Four pytest tests of the shop's tools: three through the SDK's in-process client, and one over Streamable HTTP onloopback, which reaches a check an in-memory test never makes. The prose's point rests on the unknown-order test'sline and on the last line, which counts the passes."""import pytestfrom mcp import Clientfrom lib import http_mcp, loopback, shop_toolsfrom lib.testing import anyio_backend, run, shop_api_envpytestmark = pytest.mark.anyio                            # runs the async tests on anyio's pytest pluginasync def test_order_status_fields(shop_api_env):        # shop_api_env serves the shop's API on loopback for this test    # raise_exceptions=True: a bug outside a tool's body raises here, with its own message    async with Client(shop_tools.create_server(), raise_exceptions=True) as client:        result = await client.call_tool("get_order_status", {"order_id": "O-1873"})    assert not result.is_error    assert result.structured_content["order_id"] == "O-1873"    assert result.structured_content["status"] == "delivered"async def test_unknown_order_is_a_tool_error(shop_api_env):    async with Client(shop_tools.create_server(), raise_exceptions=True) as client:        result = await client.call_tool("quote_refund", {"order_id": "O-7144"})    assert result.is_error                                    # raise_exceptions doesn't make it raise    assert "find_orders" in result.content[0].text            # the model is told what to do insteadasync def test_malformed_order_id_is_refused(shop_api_env):    async with Client(shop_tools.create_server(), raise_exceptions=True) as client:        result = await client.call_tool("get_order_status", {"order_id": "1873"})    assert result.is_error    text = result.content[0].text                             # only argument validation writes this error:    assert "order_id" in text and "string_pattern_mismatch" in text   # the field and pydantic's pattern checkdef test_http_refuses_a_mismatched_header(shop_api_env):    with loopback.serve(shop_tools.create_server().streamable_http_app()) as base_url:        # the header names check_stock while the body calls get_order_status: the mismatch the server must refuse        reply = http_mcp.post(base_url + "/mcp", "tools/call", {"name": "get_order_status",                              "arguments": {"order_id": "O-1873"}}, headers={"Mcp-Name": "check_stock"})    assert reply.status_code == 400    assert reply.json()["error"]["code"] == -32020        # the JSON-RPC code the server returns for the mismatchif __name__ == "__main__":    run(__file__)
输出python test-tools-in-memory.py
test_order_status_fields: passed
test_unknown_order_is_a_tool_error: passed
test_malformed_order_id_is_refused: passed
test_http_refuses_a_mismatched_header: passed
tests passed: 4 of 4

A failing tool is a result a model can act on. The run reports 4 of 4, and the unknown order's test passed with raise_exceptions=True on: the tool raised ToolError, and the client got an ordinary result with the error flag set and the server's advice in its text, which is what a model needs to correct itself (Report failures as tool results).

The malformed ID never reached the tool. The test asserts that the error names order_id and pydantic's string_pattern_mismatch, which only argument validation writes. The SDK validated the arguments against the tool's parameter model, which its input schema is generated from, before calling the tool (mcp/server/mcpserver/server.py, _handle_call_tool). The HTTP test covers the layer the others skip: the server refused the mismatched header with status 400 and the JSON-RPC error -32020, as Read one HTTP exchange describes, before any tool code ran.

Working rule: Test each tool in memory with Client(server, raise_exceptions=True), and assert on structured_content fields and is_error, not on whole results. Keep at least one test per transport you ship that goes over it on loopback, for the header, origin and streaming checks an in-memory test can't reach, and put the tests of trace propagation and list changes there too.

这部分尚未翻译,因此以英文显示。

Check schemas as a contract

最近一次修改见于版次 2026.11.11

The in-memory tests from the previous section check that a tool does what its own release says. They don't check that the release still fits the clients using the last one. A client depends on a tool through its schemas: it sends arguments that its copy of the inputSchema accepts, and it reads the fields that its copy of the outputSchema promises. When a tool declares an output schema, the server MUST return structured content that conforms to it, and clients SHOULD validate it (tools, "Structured Content").

The Python SDK's client does validate, and it validates against its own copy. It keeps one compiled validator per tool, built from the output schema in the last tools/list it absorbed, and replaces it only when a later listing brings a different schema (mcp/client/session.py, _output_schema_validator and _absorb_tool_listing). A non-error result that doesn't match raises RuntimeError in the caller (mcp/client/session.py, validate_tool_result). So a server that renames an output field breaks every connected client that listed its tools before the release, at the moment each one next calls the tool, and the server sees nothing wrong.

In the shop's case, release 2 of the server renames the per-warehouse on_hand field of check_stock to count. To see the break, a client connects to release 1 in memory and lists the tools. It keeps its connection while the server swaps check_stock for release 2's version, as a rolling deploy would. Then the client calls the tool, lists again and calls once more. Last, a contract test runs the two checks it makes before a release ships: lib.contract.breaking_changes, a diff of the two releases' schemas, and a validation of release 2's real result against release 1's published output schema with jsonschema, the library the client uses.

schema-change-breaks-a-client.py Python 3.12.15 · cryptography 50.0.2 · httpx2 2.16.2 · jsonschema 4.26.0 · mcp 2.3.0 · mcp-types 2.3.0 · pydantic 2.14.3 · pytest 9.2.0 · starlette 1.10.0 · uvicorn 0.54.0 通过
"""What a client connected before a release sees when the release renames check_stock's on_hand to count, and whatthe contract checks report about the same change. The prose's point rests on the client's error line, which namesthe missing field, and on the contract check's line."""import asynciofrom mcp import Clientfrom pydantic import BaseModelfrom lib import confirmations, contract, shop_toolsfrom lib.testing import shop_api_hereclass Warehouse(BaseModel):    warehouse: str    count: int                                            # release 1 called it on_hand    last_counted: strclass StockReport(BaseModel):    sku: str    available: int    warehouses: list[Warehouse]def check_stock(sku: shop_tools.Sku) -> StockReport:    report = confirmations.chapter3_tools()["check_stock"].fn(sku)       # release 1's tool does the reading    return StockReport(sku=sku, available=report.available, warehouses=[Warehouse(        warehouse=w.warehouse, count=w.on_hand, last_counted=str(w.last_counted)) for w in report.warehouses])async def main() -> None:    server = shop_tools.create_server()    with shop_api_here():                                  # the server's tools run in this process        async with Client(server) as client:            listing = await client.list_tools()            print("release 1's tools/list cache hint:", f"ttlMs {listing.ttl_ms}")            server.remove_tool("check_stock")                                  # the release, swapped in while connected            server.add_tool(check_stock, description=shop_tools.DESCRIPTIONS["check_stock"])            try:                await client.call_tool("check_stock", {"sku": "KG-1031"})            except RuntimeError as error:                print("client that listed before the release:", error.args[0].splitlines()[0])  # the message's first line            new = next(tool for tool in (await client.list_tools()).tools if tool.name == "check_stock")  # the release 2 schema            result = await client.call_tool("check_stock", {"sku": "KG-1031"})            print("client after listing again:", "result" if not result.is_error else "tool error")    old = next(tool for tool in listing.tools if tool.name == "check_stock")    print("contract check:", "; ".join(contract.breaking_changes(old, new)) or "no breaking change")    validator = contract.validator(old.output_schema)(old.output_schema)    # by the dialect the schema declares    print("validator for release 1's schema:", type(validator).__name__ + ", as it declares",          old.output_schema.get("$schema", "no $schema"))    # the first error the schema finds in release 2's real result    print("release 2's result against release 1's schema:", next(validator.iter_errors(result.structured_content)).message)asyncio.run(main())
输出python schema-change-breaks-a-client.py
release 1's tools/list cache hint: ttlMs 0
client that listed before the release: Invalid structured content returned by tool check_stock: 'on_hand' is a required property
client after listing again: result
contract check: output warehouses[].on_hand: removed
validator for release 1's schema: Draft202012Validator, as it declares no $schema
release 2's result against release 1's schema: 'on_hand' is a required property

Release 1's tool list carried the SDK's default cache hint, ttlMs 0, so the list was stale the moment it arrived, and the client still validated against it. The call after the release failed inside the client: "Invalid structured content returned by tool check_stock: 'on_hand' is a required property". The server had returned a correct release 2 result. After the client listed the tools again, the same call came back as a result. A zero TTL doesn't protect a connected client, because the validator follows the last listing, not the cache: a client that lists once at startup holds that schema for as long as it runs.

Both contract checks caught the change without a client. The schema diff reported output warehouses[].on_hand: removed, and validating release 2's result against release 1's schema failed with the client's own message: "'on_hand' is a required property". The diff is a reviewer's aid: it compares field paths, types and required inputs, and its docstring lists what it leaves out, such as patterns and enums. The validation is the test to keep, because it checks the server's real output against the exact schema that clients hold.

Breaking changes aren't symmetric. On the output side, removing, renaming or retyping a field breaks clients, and adding an optional field doesn't. On the input side, adding a required argument breaks old callers, and removing one breaks them quietly, because the SDK's server drops arguments it doesn't know without an error, as Treat ticket text as untrusted data shows. The pinned revision allows any JSON Schema 2020-12 keyword in both schemas, and reads a schema with no $schema as 2020-12 (tools). A schema may name another dialect in $schema, and clients and servers MUST validate by the declared dialect, or by 2020-12 when none is declared (base protocol, "JSON Schema Usage"). So choose the validator from the schema, as the SDK's client does with jsonschema's validator_for (mcp/client/session.py, _output_schema_validator). lib.contract.validator does the same for the shop's checks, with 2020-12 as the default. pydantic writes no $schema, so release 1's schema got Draft202012Validator, as it declares no $schema.

Working rule: Keep the last release's tools/list in the repository, and in CI validate every structured result your tests produce against it as well as against the new schema, each by the dialect it declares and by 2020-12 when it declares none. Treat a removed, renamed or retyped output field and a new required input as a breaking change: add the new field beside the old one, or add a new tool, and retire the old shape through a window (Change tools without breaking clients). Don't rely on a short TTL to protect clients that are already connected.

这部分尚未翻译,因此以英文显示。

Replay recorded host runs

最近一次修改见于版次 2026.11.11

Tool tests and contract tests cover the server. The support host from Build a host that works through tickets has logic of its own between the model and the servers: it routes names, asks for consent, sends results back and caps turns, and a change there can make every ticket go wrong without any tool failing. A replay covers that layer. It runs the real host against the real servers, with the model's replies taken from a recording, so a test can assert on what the host did for each ticket.

A replay tests the host and the servers against fixed model outputs. It doesn't test the model: a different model, or the same one with other sampling, needs a new recording. And it holds only while the messages stay as recorded. ReplayModel from lib.host looks each reply up by the SHA-256 of the exact messages, which include every tool definition and every tool result so far, and raises RecordingMismatch when they differ (Run the host loop). So a replay doubles as a tripwire: any change to what the model would see stops it, and a team then decides whether to record again.

The replay also gives the queue's results a second reading. Work through the ticket queue found that the model told customers their refunds were on the way for orders it never refunded. A reply is the model's claim, and the host's call log is the record of what happened, so the host can compare them before a reply reaches a customer. lib.queue_replay holds a small version of that check, built on the phrase check chapter 10 counted with, ticket_host.promises_refund, which looks for phrases such as "will be refunded" or "we'll refund". Reusing it keeps this chapter's counts and chapter 10's the same measurement. Its unbacked_refund is true when a run's last reply makes that promise and no issue_refund call in the run returned a result. The phrase list is a rule of thumb written against this recording's replies, not a classifier, and the module's docstring says what it misses.

queue_replay.replay_queue replays the whole queue, with the support host set up exactly as chapter 10's work-the-ticket-queue sets it up. The run prints one ticket's tool sequence, counts the refunds and the replies that promise one, and replays the first ticket after one sentence has been added to quote_refund's description.

replay-ticket-runs.py Python 3.12.15 · cryptography 50.0.2 · httpx2 2.16.2 · jsonschema 4.26.0 · mcp 2.3.0 · mcp-types 2.3.0 · pydantic 2.14.3 · starlette 1.10.0 · uvicorn 0.54.0 通过
"""Replay chapter 10's queue run, the recording ticket-runs, through the support host, and check each reply's promiseagainst the host's call log. The prose's point rests on the refund lines, which compare refunds issued with repliesthat promise one, and on the last line, which shows what a one-sentence rewording does to the replay."""import asynciofrom lib import queue_replay, shop_tools, ticket_hostfrom lib.host import RecordingMismatchfrom lib.shop_data import load_shopdef reword_quote_refund(host) -> None:              # the server's next release adds a sentence to one description    changed = {**shop_tools.DESCRIPTIONS}    changed["quote_refund"] += " Quotes are in the order's currency."    host.listed["shop"] = shop_tools.with_descriptions(host.listed["shop"], changed)async def main() -> None:    tickets = {ticket.ticket_id: ticket for ticket in load_shop().tickets}    runs = await queue_replay.replay_queue()    print("tickets replayed:", len(runs))    print("T-0009 tools:", " then ".join(turn.tool for turn in runs["T-0009"].calls))   # its calls, in order    print("refunds issued:", sum(queue_replay.refunded(run) for run in runs.values()))    # the phrase check from chapter 10, a rule of thumb: see the module's docstring for what it misses    promised = [ticket_id for ticket_id, run in runs.items() if ticket_host.promises_refund(run.answer)]    # a promise with no refund behind it: no issue_refund call in the run returned a result    unbacked = [ticket_id for ticket_id in promised if queue_replay.unbacked_refund(runs[ticket_id])]    print("replies that promise a refund:", len(promised))    print("of which no call made:", len(unbacked))    for tag in ("issue_refund", "quote_refund"):           # the tickets tagged with each refund tool        group = [t for t in tickets.values() if t.expected_tool == tag]        print(f"{tag} tickets flagged:", f"{sum(t.ticket_id in unbacked for t in group)} of {len(group)}")    print("flagged:", ", ".join(unbacked))    try:        await queue_replay.replay_queue(change=reword_quote_refund, tickets=[tickets["T-0001"]])    except RecordingMismatch:        print("after rewording quote_refund, T-0001 replays:", "no, RecordingMismatch")asyncio.run(main())
输出python replay-ticket-runs.py
tickets replayed: 48
T-0009 tools: shop.quote_refund then shop.find_orders
refunds issued: 0
replies that promise a refund: 11
of which no call made: 11
issue_refund tickets flagged: 6 of 7
quote_refund tickets flagged: 5 of 9
flagged: T-0007, T-0020, T-0029, T-0034, T-0036, T-0037, T-0040, T-0042, T-0045, T-0046, T-0048
after rewording quote_refund, T-0001 replays: no, RecordingMismatch

All 48 tickets replayed, and ticket T-0009 took the path it took in chapter 10: shop.quote_refund then shop.find_orders. An assertion on that sequence is a regression test for the host. If a change to routing or error handling sent the first tool execution error back differently, the model's second turn would no longer match the recording, and the replay would stop.

lib.queue_replay flags the promises that no call backs, and a host should send those replies to a person instead of to the customer. The host issued 0 refunds, yet 11 replies promise one, and 11 of them have no refund behind them.

Of the tickets asking for a refund, 6 of 7 are flagged, and of the tickets asking only what a refund would be, 5 of 9 are, each reply telling the customer the money was on its way. The one refund request not flagged, T-0024, ended with the model asking which product the customer meant, which promises nothing. The flagged tickets are T-0007, T-0020, T-0029, T-0034, T-0036, T-0037, T-0040, T-0042, T-0045, T-0046, T-0048.

The rewording at the end shows the tripwire. After one sentence was added to one description, the first ticket's replay gave no, RecordingMismatch. Every ticket's prompt holds every tool's description, so changing any description changes every prompt. That is the cost of replays, and also their use: a reworded description is the change that can alter what the model chooses, and the replay won't let it through unmeasured.

Working rule: Replay a recorded run of the whole queue in CI, assert on each ticket's tool sequence, and run a check that compares each reply's promises with the calls that returned a result. Keep generated IDs and clocks fixed in the servers a replay runs against, or it stops for reasons that aren't changes. Then treat RecordingMismatch as a signal, not as a flaky test: when you change a description, a prompt or a tool's output, record again with the recording script and compare the new run's scores with the old run's before you ship.

这部分尚未翻译,因此以英文显示。

Trace calls with OpenTelemetry

最近一次修改见于版次 2026.11.11

Tests run before a release; traces show what a server does after it. OpenTelemetry is the common way to get them: an application creates spans, each a named, timed operation with attributes and a parent, and an exporter sends them to a tracing backend. MCP adds one thing of its own. At the pinned revision, the _meta keys traceparent, tracestate and baggage are reserved for trace context, and their values MUST follow the W3C Trace Context and Baggage formats (base protocol). That is how a client's trace and a server's trace join into one, whatever the transport.

The Python SDK traces with no setup in your server's code. Every server installs OpenTelemetryMiddleware, which wraps each inbound message in a SERVER span and does nothing until an OpenTelemetry SDK and exporter are installed (mcp/server/lowlevel/server.py; OpenTelemetry). The source marks the middleware provisional, so its details may change in a 2.x minor release. On the client side, the JSON-RPC paths, which are URLs, stdio and the legacy in-memory mode, open a CLIENT span named MCP send {method} {target} and inject traceparent into the request's _meta, and the server extracts it as the parent of its span (mcp/shared/jsonrpc_dispatcher.py, mcp/shared/_otel.py). The in-process path from Test tools in memory sends no JSON-RPC, so it creates no client span and injects nothing.

The shop wants a trace for each tool call, findable by tool name and showing whether it failed. The script installs OpenTelemetry's SDK, opentelemetry-sdk 1.45.2, with an InMemorySpanExporter, which keeps finished spans in a list that a test can read (opentelemetry/sdk/trace/export/in_memory_span_exporter.py). The script serves chapter 3's tools from Design tools a model can use over Streamable HTTP on loopback in the same process, so the client's and the server's spans land in the same list. It calls find_orders and then quote_refund for an order that doesn't exist. Then it makes the same find_orders call in memory twice, the second time inside a span of the test's own.

trace-a-tool-call.py Python 3.12.15 · cryptography 50.0.2 · httpx2 2.16.2 · jsonschema 4.26.0 · mcp 2.3.0 · mcp-types 2.3.0 · opentelemetry-api 1.45.2 · opentelemetry-sdk 1.45.2 · opentelemetry-semantic-conventions 0.66b2 · pydantic 2.14.3 · pytest 9.2.0 · starlette 1.10.0 · uvicorn 0.54.0 通过
"""The OpenTelemetry spans the SDK emits for the shop's tool calls, over Streamable HTTP on loopback and in memory.The prose's point rests on two printed lines: the HTTP server span, which shows the trace context crossing the wire,and the in-memory server span parents, which show what happens without it."""import asynciofrom mcp import Clientfrom opentelemetry import tracefrom opentelemetry.sdk.trace import TracerProviderfrom opentelemetry.sdk.trace.export import SimpleSpanProcessorfrom opentelemetry.sdk.trace.export.in_memory_span_exporter import InMemorySpanExporterfrom opentelemetry.semconv._incubating.attributes.mcp_attributes import McpMethodNameValuesfrom lib import loopback, shop_toolsfrom lib.testing import shop_api_herespans = InMemorySpanExporter()trace.set_tracer_provider(provider := TracerProvider())provider.add_span_processor(SimpleSpanProcessor(spans))      # each span, as it ends, into memorydef finished(name: str) -> list:                 # every finished span with this name, in the order they ended    return [span for span in spans.get_finished_spans() if span.name == name]def parent(span) -> str:    return next((s.name for s in spans.get_finished_spans() if span.parent and s.context.span_id ==                 span.parent.span_id), "none")      # "none" for a span with no parent, or whose parent never finishedasync def main() -> None:    server = shop_tools.create_server()    with shop_api_here(), loopback.serve(server.streamable_http_app()) as base_url:        async with Client(base_url + "/mcp") as client:            await client.call_tool("find_orders", {"customer_id": "C-0127"})            await client.call_tool("quote_refund", {"order_id": "O-7144"})            # a tool error        print("HTTP spans:", ", ".join(sorted(span.name for span in spans.get_finished_spans())))        # the test makes one call of each, so the first finished span of each name is the call's        call, error = finished("tools/call find_orders")[0], finished("tools/call quote_refund")[0]        print("HTTP server span:", call.name, f"({call.kind.name}), parent: {parent(call)}")        for key in sorted(set(call.attributes) - {"jsonrpc.request.id"}):   # the request ID changes on every run            print(f"attribute {key}:", call.attributes[key])        print("tool error span status:", error.status.status_code.name)        print("tool error span error.type:", error.attributes["error.type"])        spans.clear()        async with Client(server) as client:            await client.call_tool("find_orders", {"customer_id": "C-0127"})            # a span of the test's own, which the in-memory server falls back to as the parent            with trace.get_tracer("shop-tests").start_as_current_span("test find_orders"):                await client.call_tool("find_orders", {"customer_id": "C-0127"})        print("in-memory spans:", ", ".join(sorted(span.name for span in spans.get_finished_spans())))        print("in-memory server span parents:", ", ".join(parent(s) for s in finished("tools/call find_orders")))    # the pinned conventions predate the pinned revision, and this list has no server/discover    assert "server/discover" not in {m.value for m in McpMethodNameValues}asyncio.run(main())
输出python trace-a-tool-call.py
HTTP spans: MCP send server/discover, MCP send tools/call find_orders, MCP send tools/call quote_refund, MCP send tools/list, server/discover, tools/call find_orders, tools/call quote_refund, tools/list
HTTP server span: tools/call find_orders (SERVER), parent: MCP send tools/call find_orders
attribute gen_ai.operation.name: execute_tool
attribute gen_ai.tool.name: find_orders
attribute mcp.method.name: tools/call
attribute mcp.protocol.version: 2026-07-28
tool error span status: ERROR
tool error span error.type: tool_error
in-memory spans: server/discover, test find_orders, tools/call find_orders, tools/call find_orders, tools/list
in-memory server span parents: none, test find_orders

Over HTTP the spans came in pairs, each server span paired with a client span of the same method: MCP send server/discover, MCP send tools/call find_orders, MCP send tools/call quote_refund, MCP send tools/list, server/discover, tools/call find_orders, tools/call quote_refund, tools/list. The client listed the tools before its first call, because it validates the result against the output schema. The trace shows the server's span for the call, tools/call find_orders (SERVER), parent: MCP send tools/call find_orders, so the trace context crossed in _meta.

Its attributes name the method, tools/call, the operation, execute_tool, the tool, find_orders, and the revision (mcp/server/_otel.py).

The failed quote's span has the status ERROR and the error.type tool_error, although the call returned a result and not a JSON-RPC error, so a tracing backend can count tool execution errors without reading result bodies.

A test of trace propagation needs HTTP or stdio, because in memory the server has nothing to extract. In memory there were no client spans, only the server's spans and the test's own test find_orders: server/discover, test find_orders, tools/call find_orders, tools/call find_orders, tools/list. The two server spans' parents were none, test find_orders, in that order. With nothing to extract, the server falls back to whatever span is current, and only the test's own span gave it one (mcp/shared/_otel.py, extract_trace_context).

The names a server emits are the part to treat with care. OpenTelemetry's semantic conventions for MCP have the status Development; they recommend span names of the form {mcp.method.name} {target} and define metrics such as mcp.server.operation.duration (MCP semantic conventions, read 2026-10-31). They have also moved: the page the MCP specification links to shows a notice that the GenAI conventions moved to a repository of their own, which has no tagged release (moved notice). The SDK's server spans follow the recommended naming. Its client span name, MCP send …, doesn't, and the SDK emits no metrics: the source of mcp 2.3.0 never creates a meter. The pinned conventions package, opentelemetry-semantic-conventions 0.66b2, predates the pinned revision. Its list of method names has initialize and logging/setLevel, it still defines mcp.session.id, and it has no server/discover (opentelemetry/semconv/_incubating/attributes/mcp_attributes.py).

For logs, the pinned revision deprecates MCP's own Logging messages, notifications/message, and points servers to standard error on stdio and to OpenTelemetry otherwise (changelog). Replace sampling, roots and logging covers the move.

Working rule: Install an OpenTelemetry SDK and exporter in every server and host you run, and let the SDK's middleware make the server spans. Build dashboards on the attributes the SDK emits, mcp.method.name, gen_ai.tool.name and error.type, and label them as following a Development-status convention at a named version, because the names may change. Don't validate method names against the pinned conventions package. Test propagation over a real transport, and wrap in-memory calls in a span of your own when a test needs a parent.

衡量选对工具的频率

最近一次修改见于版次 2026.11.11

重放已记录的主机运行一节所问的是,主机是否仍然做着它以前做的事。第二个问题是,在商店提供的工具和描述之下,模型选得有多准。通常最先采用的度量是工具选择准确率:模型的第一次调用所用的工具,与正确的智能体会用的工具一致的情形所占的比例,常称为 top-1 准确率。基准测试还会给参数打分。Berkeley Function Calling Leaderboard 就是一个示例:它通过匹配抽象语法树,把每次调用的名称和参数一并与预期值比对(BFCL)。

来自固定记录的数字,衡量的范围很窄:商店的工具名称和描述,针对的是一个模型 Qwen3-4B-Instruct-2507,量化方式为 Q4_K_M,采样温度为 0.7(处理工单队列),使用本书的一条提示词和一个随机种子,覆盖本书编写的 48 张工单。

它只是该设置下的一次抽样,而且各分组都很小:最小的一组只有 8 张工单,因此一张工单就在该组得分中占很大比重。它对一般意义上的模型不说明任何问题。任何一条描述一经改动,就需要重新记录,数字才有意义,重放中的 RecordingMismatch 会强制这一点。每张工单都带有正确的智能体应当最先调用的工具。脚本使用 ticket_host.expected_first_tool 打分,与第 10 章相同:退款请求以 quote_refund 开始才算正确,因为 issue_refund 需要先有报价。

为重放打分时,脚本取每张工单的第一次工具调用,输出总体准确率、按预期工具划分的准确率以及每一种混淆。对于点名了订单的正确调用,脚本还以两种方式给 order_id 参数打分:一种对照工单中所写的订单号,另一种对照客户本意所指的订单。在客户输错了编号的 5 张工单上,两者并不相同。

tool-choice-accuracy.py Python 3.12.15 · cryptography 50.0.2 · httpx2 2.16.2 · jsonschema 4.26.0 · mcp 2.3.0 · mcp-types 2.3.0 · pydantic 2.14.3 · starlette 1.10.0 · uvicorn 0.54.0 通过
"""Score the first tool call of every ticket in chapter 10's queue run against the tool each ticket is tagged with,overall, per tag and by confusion, and check the order IDs of the right calls. The prose's point rests on theaccuracy lines, the per-tag line for refunds, and the two order-ID lines, which differ."""import asynciofrom collections import Counterfrom lib import queue_replay, ticket_hostfrom lib.shop_data import load_shopasync def main() -> None:    tickets = load_shop().tickets    runs = await queue_replay.replay_queue()    scored = []                                            # (ticket, expected tool, first tool called)    for ticket in tickets:        calls = runs[ticket.ticket_id].calls        # the first call, or None when the host made none; a refund ticket expects quote_refund first        scored.append((ticket, ticket_host.expected_first_tool(ticket), calls[0] if calls else None))    right = [(t, call) for t, expected, call in scored if call and call.tool == expected]    print("first tool right:", f"{len(right)} of {len(scored)}")    print("top-1 accuracy:", f"{len(right) / len(scored):.2f}")    for expected, count in sorted(Counter(expected for _, expected, _ in scored).items()):        hits = sum(1 for t, e, call in scored if e == expected and call and call.tool == expected)        print(f"expected {expected}:", f"{hits} of {count}")    confusions = Counter((expected, call.tool if call else "no tool") for _, expected, call in scored                         if not call or call.tool != expected)    for (expected, chosen), count in confusions.most_common():        print(f"expected {expected}, called {chosen}:", count)    with_order = [(t, call) for t, call in right if t.order_id and "order_id" in call.arguments]  # right calls naming an order    as_written = sum(call.arguments["order_id"] == t.cited_order_id for t, call in with_order)   # the ID the ticket gave    meant = sum(call.arguments["order_id"] == t.order_id for t, call in with_order)              # the customer's order    print("right tool, order ID as the ticket wrote it:", f"{as_written} of {len(with_order)}")    print("right tool, order the customer meant:", f"{meant} of {len(with_order)}")    # tickets whose cited ID isn't the order the customer meant    typos = [(t, e, call) for t, e, call in scored if t.cited_order_id and t.cited_order_id != t.order_id]    print("tickets with a mistyped order ID:", len(typos))    print("of which the right tool was called:", sum(1 for _, e, call in typos if call and call.tool == e))    for t, _, call in [(t, e, call) for t, e, call in typos if not call or call.tool != e]:        print(f"mistyped {t.ticket_id}, first tool:", call.tool if call else "no tool")    print("smallest expected-tool group, tickets:", min(Counter(e for _, e, _ in scored).values()))    manifest = queue_replay.manifest()    print("recorded model:", manifest["model"].split("/")[-1])   # the model's name, without its publisher's path    print("recorded quantization:", manifest["quantization"])asyncio.run(main())
输出python tool-choice-accuracy.py
first tool right: 36 of 48
top-1 accuracy: 0.75
expected shop.check_stock: 10 of 10
expected shop.find_orders: 8 of 8
expected shop.get_order_status: 12 of 14
expected shop.quote_refund: 6 of 16
expected shop.quote_refund, called shop.get_order_status: 8
expected shop.get_order_status, called partner.track_parcel: 2
expected shop.quote_refund, called shop.find_orders: 2
right tool, order ID as the ticket wrote it: 18 of 18
right tool, order the customer meant: 14 of 18
tickets with a mistyped order ID: 5
of which the right tool was called: 4
mistyped T-0042, first tool: shop.get_order_status
smallest expected-tool group, tickets: 8
recorded model: Qwen3-4B-Instruct-2507
recorded quantization: Q4_K_M

第一个工具选对的工单有 36 of 48 张,top-1 准确率为 0.75,与第 10 章统计的 36 of 48 相同。

总体数字掩盖了错误所在之处。库存问题的得分为 10 of 10,订单搜索为 8 of 8,而退款工单只有 6 of 16,其中多数未命中的情形,即 8,都转向了 get_order_status,尽管它的描述说退款应使用 quote_refund,而 quote_refund 的描述说应先调用它。这一对描述是下一步要改进的对象,而该队列就是描述改动后需要重新记录的工单集。转向 partner.track_parcel 的两个状态问题,是第 10 章的运单号案例(处理工单队列)。

参数说明了为什么参照对象很重要。在工具正确的前提下,模型有 18 of 18 次调用使用了工单中所写的订单号,有 14 of 18 次调用使用了客户本意所指的订单。

未命中之处来自客户的拼写错误。在输错编号的工单中,有 4 张到达了正确的工具,在这里计分;另一张是 T-0042,它首先转到 shop.get_order_status,因此被算作错误工具。不查询客户的订单,任何模型都无法看穿拼写错误。对照客户本意打分,模型显得粗心;对照所给信息打分,它则是忠实的。这一差距属于主机流程,主机在据订单采取行动之前,应当先核对该订单是否属于工单的客户。

已发表的基准测试指向同样的结论。一篇预印本 RAG-MCP 报告称,在模型选择之前先检索出一份候选工具清单,使其基准任务上的选择准确率从 13.62% 提高到 43.13%,由充当评判者的模型打分(RAG-MCP)。MCP-Bench 覆盖 28 个在线服务器和 250 个工具,报告称在指令未点明工具的任务上,难题依然存在(MCP-Bench)。两者都只是各自任务上的单篇预印本,对商店的数字都没有任何说明。

工作准则: 对每次记录的运行,都按标签给第一个工具打分,而不只给总体打分;并分别给参数打分,一次对照工单交给模型的内容,一次对照事实。先改进最大混淆背后的描述,再重新记录,并在两次记录之间比较各标签的得分。每个得分旁都要写明模型、提示词和工单集,切勿在不同设置之间比较得分。

这部分尚未翻译,因此以英文显示。

Change tools without breaking clients

最近一次修改见于版次 2026.11.11

The contract test in Check schemas as a contract says when a change breaks clients; it doesn't say how to make the change. The specification doesn't either. A tool definition has no deprecation field, and nothing in the pinned revision marks a tool as on its way out (tools). What follows is practice: the book's recommendation, built from parts the specification does define, not a protocol feature.

There are three such parts. A client asks for tool list changes with subscriptions/listen and hears about each one on that stream (subscriptions), as Tell clients when a resource changes shows for resources. A tools/list result carries a cache hint, ttlMs, and a change notification invalidates a cached list that is still fresh; clients MAY re-fetch early when a call fails as if the tool changed, for example with an unknown method or invalid parameters (caching). And a tool execution error is what clients SHOULD give the model so it can correct itself (tools, "Error Handling"). From those parts, the book recommends this procedure: add the new tool beside the old one; mark the old one "Deprecated: use …" in its description; announce the change; shorten the TTL while the change is under way; keep the old tool working through a window; and after the window, answer it with an execution error that names the replacement.

The shop is replacing find_orders with find_orders_v2, which can also filter by SKU. To walk through the three releases, the script serves chapter 3's tools from Design tools a model can use over Streamable HTTP on loopback, with a TTL of one minute on the tool list, and connects two clients: one that listens for list changes, and one that only caches. Release 2 adds find_orders_v2 and rewords find_orders, and the server publishes the change. Release 3 replaces find_orders with a function that raises ToolError. An in-memory client wouldn't do here, because the in-process path doesn't deliver list changes (Test tools in memory).

deprecate-a-tool.py Python 3.12.15 · cryptography 50.0.2 · httpx2 2.16.2 · jsonschema 4.26.0 · mcp 2.3.0 · mcp-types 2.3.0 · pydantic 2.14.3 · pytest 9.2.0 · starlette 1.10.0 · uvicorn 0.54.0 通过
"""Retire find_orders in favour of find_orders_v2 over three releases, watched by a listening client and a cachingclient. The prose's point rests on the caching client's list and on the last line, the error the old name returnsafter the window."""import asynciofrom mcp import Clientfrom mcp.server.caching import CacheHintfrom mcp.server.mcpserver import MCPServerfrom mcp.server.mcpserver.exceptions import ToolErrorfrom mcp.server.subscriptions import InMemorySubscriptionBus, ToolsListChangedfrom lib import confirmations, loopback, shop_toolsfrom lib.testing import shop_api_herebus, tools = InMemorySubscriptionBus(), confirmations.chapter3_tools()server = MCPServer("shop-support", version="0.11.0", tools=list(tools.values()), subscriptions=bus,                   cache_hints={"tools/list": CacheHint(ttl_ms=60_000, scope="public")})   # a minute: short while a change is under wayold = tools["find_orders"]def find_orders_v2(customer_id: shop_tools.CustomerId, sku: shop_tools.Sku | None = None) -> shop_tools.OrderList:    """Search one customer's orders, newest first, optionally only those with one product's SKU."""    found = old.fn(customer_id, limit=50)    return found.model_copy(update={"orders": [o for o in found.orders if sku is None or sku in o.skus]})def retired(customer_id: shop_tools.CustomerId) -> shop_tools.OrderList:    raise ToolError("find_orders was retired. Call find_orders_v2 with the same customer_id.")async def replace_find_orders(fn, description: str) -> None:    server.remove_tool("find_orders")    server.add_tool(fn, name="find_orders", title=old.title, description=description, annotations=old.annotations)    await bus.publish(ToolsListChanged())                     # to every client listening for list changesasync def main() -> None:    with shop_api_here(), loopback.serve(server.streamable_http_app()) as base_url:        async with Client(base_url + "/mcp") as listening, Client(base_url + "/mcp") as cached:            listing, _ = await cached.list_tools(), await listening.list_tools()     # both cache release 1's list            print("release 1:", f"{len(listing.tools)} tools, ttlMs {listing.ttl_ms}")            async with listening.listen(tools_list_changed=True) as changes:   # a stream that carries list-change events                server.add_tool(find_orders_v2)                                       # release 2: the replacement first                await replace_find_orders(old.fn, "Deprecated: use find_orders_v2. " + old.description)                print("event:", type(await anext(changes)).__name__)            print("listening client sees:", ", ".join(t.name for t in (await listening.list_tools()).tools))            print("cached client sees:", ", ".join(t.name for t in (await cached.list_tools()).tools))            during = await cached.call_tool("find_orders", {"customer_id": "C-0127"})            print("find_orders during the window:", "tool error" if during.is_error else "result")            await replace_find_orders(retired, "Retired: use find_orders_v2.")         # release 3: the old name now errors            after = await cached.call_tool("find_orders", {"customer_id": "C-0127"})            print("find_orders after the window:", after.content[0].text)asyncio.run(main())
输出python deprecate-a-tool.py
release 1: 5 tools, ttlMs 60000
event: ToolsListChanged
listening client sees: get_order_status, quote_refund, issue_refund, check_stock, find_orders_v2, find_orders
cached client sees: find_orders, get_order_status, quote_refund, issue_refund, check_stock
find_orders during the window: result
find_orders after the window: Error executing tool find_orders: find_orders was retired. Call find_orders_v2 with the same customer_id.

Release 1 listed 5 tools, ttlMs 60000. When release 2 shipped, the listening client received ToolsListChanged. The SDK drops a cached list before it hands the client such an event (mcp/client/client.py), so the listening client's next listing showed both tools: get_order_status, quote_refund, issue_refund, check_stock, find_orders_v2, find_orders.

The caching client heard nothing and served release 1's list from its cache: find_orders, get_order_status, quote_refund, issue_refund, check_stock. Its call to find_orders during the window still returned a result. A model behind a caching client doesn't learn about find_orders_v2 until the TTL runs out or the client re-fetches, which is why the TTL should be short while a change is under way, and why the old tool has to keep working.

After release 3, the caching client's call to find_orders came back as an execution error the model can act on: "Error executing tool find_orders: find_orders was retired. Call find_orders_v2 with the same customer_id.". A removed tool would have produced the SDK's unknown-tool error instead, which tells the model the name was wrong but not what to call (Report failures as tool results). The SDK returns that error as a tool execution error, although the specification makes an unknown tool a protocol error (mcp/server/mcpserver/tools/tool_manager.py; tools, "Error Handling").

The listening client's list also shows a side effect: find_orders moved to the end. MCPServer lists tools in the order they were added, so the release's live swap, which removes the tool and adds it back, moves it (Cache list results). A changed order changes the start of every prompt that renders the list, which is what a model provider's prompt cache matches on. A server that restarts with the new code lists tools in the order its code registers them, so add new tools at the end and leave the existing ones where they are.

Working rule: Retire a tool in three releases: add the replacement and mark the old tool deprecated in its description, keep both working through a window you announce, then answer the old name with an execution error that names the replacement. Shorten ttlMs on tools/list while the change is under way, publish a list change at each release, and open a subscriptions/listen stream in every host you control. Say in your changelog that the window is your policy, since the protocol defines none.

生产环境中会出什么问题

最近一次修改见于版次 2026.11.11

这里的各项检查只针对一台机器上的一个进程。在生产环境中,同样的信号来自许多副本和客户端,每一种信号都可能以各自的方式误导你。

span 的数量增长到后端无法建立索引。 SDK 以方法和工具来命名服务器端 span,这使不同名称的数量与工具列表一样少。如果在 span 名称中放入订单 ID、资源 URI 或客户 ID,每个取值都会产生一个名称;MCP 约定正是出于这个原因,把资源 URI 放在属性中(MCP 语义约定)。其迹象是追踪费用随流量增长,而不是随功能增加而增长。

追踪携带了商店的数据。 SDK 不会在其 span 中记录工具的参数或结果(mcp/server/_otel.py),而约定也把 gen_ai.tool.call.arguments 标为可选启用(同一来源)。商店的参数中包含客户 ID 和订单 ID,而参数只说明调用方发送了什么。若要记录是谁执行了操作,应取已验证令牌的主体,在支持主机上它就是客服人员,客户则取自服务器核对过的工单记录(避免服务器充当被混淆的代理)。只有在某项设置开启时才把参数加入 span,并且不要让它们进入商店的数据处理政策未涵盖的任何后端。

约定在你的仪表盘之下发生变动。 MCP 约定处于 Development 状态,并且已更换过一次仓库(迁移通知),而 SDK 的中间件被标记为暂定(mcp/server/lowlevel/server.py)。SDK 的某个版本一旦重命名了某个属性,仪表盘就会变空,却不会报任何错误。把属性名称集中放在配置中的一处,并在每次升级 SDK 时检查它们,就像对待任何其他更新触发条件一样。

部署期间各副本不一致。 在滚动部署中,一个副本提供版本 1 的模式,而下一个副本提供版本 2 的模式,从一个副本列出工具、再调用另一个副本的客户端,就会得到把模式当作契约来检查中所述的 RuntimeError。其迹象是客户端验证错误在部署期间上升,部署结束后下降。先发布增量式的变更,只有在每个副本都提供新的形态且过渡期已过之后,才移除旧的形态。

录制会过时。 当生产主机背后的模型发生变化时,回放仍会持续通过,因此录制得到的分数会逐渐偏离客户实际看到的情况。每次更换模型时都要重新录制,正如处理工单队列所建议的那样,并对生产运行的样本执行同样的无依据承诺检查,因为回放无法发现录制时的模型从未出现过的失败。

工作准则: 在依赖某条追踪或某个分数之前,先检查它涵盖了什么:哪种传输方式、哪个模型,以及每个模式的哪个版本。让 span 名称保持有界,默认不把参数放入 span,把仪表盘使用的属性名称固定到某个具名的约定版本,并在每个版本到达副本之前,针对它运行契约测试和回放。

本章做出的决定

  • 工具在内存中测试,使用 Client(server, raise_exceptions=True),对字段进行断言;每种传输方式各有一个回环测试,用来覆盖进程内路径所跳过的部分。
  • pytest 使用 anyio 自带的插件运行,不使用 inline-snapshot,本书不固定其版本。lib.testing 为每个测试输出一行,因此输出保持稳定。
  • **上一个版本的模式就是契约。**CI 使用每个模式所声明方言对应的验证器(默认为 2020-12)来验证新的结果,lib.contract 则对模式做差异比较,以供评审。
  • **第 10 章记录的 ticket-runs 是回放,而不是重新录制。**描述更改后出现 RecordingMismatch,意味着需要重新录制。
  • **宿主对照其调用日志检查回复。**如果回复承诺了退款,而没有任何调用执行过退款,该回复会交给人工处理;lib.queue_replay 中的关键词检查只是一条经验法则。
  • **追踪来自 SDK 的中间件,**其输出的属性被标注为处于 Development 状态的约定,并通过 HTTP 测试传播。
  • **工具选择按标签评分,参数单独评分,**使用 expected_first_tool,与第 10 章的评分方式相同。订单 ID 既对照工单文本评分,也对照客户本来所指的订单评分。
  • **工具分三个版本下线,**每个版本都使用较短的 TTL 并变更一次列表,在过渡期结束后返回指明替代工具的执行错误。该流程是本书的做法,而不是规范的规定。

本章,在本版次中

版次 2026.11.14示例于 2026年11月19日 通过本章 6个示例 个示例中有 6 个通过

译自英文版图书,版次 2026.11.14。

引用本节

格式

每种格式均引用英文原书,本译本以其为准。

每种格式都会注明该版次。其链接会打开当前版次,节标题处会说明该节文本最后一次修改的时间。访问日期和检索日期即为您打开此页的当天。

本页内容

第 11 章,共 12 章: 测试服务器并观察其运行

  1. Test tools in memory
  2. Check schemas as a contract
  3. Replay recorded host runs
  4. Trace calls with OpenTelemetry
  5. 衡量选对工具的频率
  6. Change tools without breaking clients
  7. 生产环境中会出什么问题
  8. 本章做出的决定

返回顶部全部章节