8e373f0f2e* Add structured output to the Python weather server and client
Both tools declare an output schema - the return type annotation - and return
structured_content alongside the text.
get_alerts answers with a top-level JSON array rather than an array nested in
an object, which protocol revision 2026-07-28 is the first to allow. "No
alerts" is simply []. get_forecast returns an object, for contrast.
The detail worth reading the source for: Alerts is a RootModel[list[Alert]],
not a plain list[Alert]. A list is not a JSON object, so the SDK wraps it as
{"result": [...]} and advertises an object-rooted schema to match, with no
opt-out. A RootModel is a BaseModel, so it is taken as the schema exactly as
written, and a RootModel over a list serializes as the bare list.
Error paths raise: a tool declaring an output schema MUST return conforming
structured content, so a path with no data has to fail.
The client moves to the 2.0 Client API with mode="auto" and prints the
negotiated version on connect. call_tool already revalidates every non-error
result against the declared schema, so the client-side SHOULD needs no code.
Each channel goes to its stated reader: content is forwarded to the model,
structured_content is used as data, reporting how many items came back.
This clears the staleness modelcontextprotocol#3124 flags against this
repository - weather.py imported mcp.server.fastmcp, client.py held the
ClientSession version - and matches that PR's idioms: the short
"from mcp.server import MCPServer" spelling, httpx2 with httpx dropped from
the dependencies since httpx2>=2.5.0 is a hard dependency of mcp,
result.content narrowed to TextContent, and input() on a worker thread.
Requires mcp 2.0.0b2; pyproject.toml sets [tool.uv] prerelease = "allow" so
plain uv run and uv sync work without flags. Model identifier moves to
claude-sonnet-5.
Note that an array-rooted schema only works on a 2026-07-28 connection. This
SDK does not project it down for older clients; it raises server-side instead.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* Update to mcp 2.0.0
The SDK left beta on 2026-07-28, so the pins move off 2.0.0b2 and both
projects drop `[tool.uv] prerelease = allow` — plain `uv run` works now.
Also from review: declare the imports rather than lean on transitive
resolution. weather.py imports httpx2 and client.py imports mcp_types, so
both are listed explicitly. The client README no longer implies every
structured result is counted — only array-rooted ones are.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* Fix get_alerts failing when NWS sends a null field
`dict.get(key, default)` returns the default only when the key is absent. The
NWS API sends these fields as explicit nulls instead of omitting them, so
`props.get(instruction, ...)` passed None straight into a `str` field and
Pydantic rejected the whole result.
One alert in eight for TX is a Special Weather Statement with a null
instruction, which was enough to fail the entire call:
Error executing tool get_alerts: 1 validation error for Alert
instructions
Input should be a valid string [type=string_type, input_value=None]
The smoke test missed it twice over: it calls get_alerts with CA, whose
alerts happen to have no nulls today, and it reports an isError result as a
skip rather than a failure.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* Say "structured content", not "structured output"
The spec never uses the phrase "structured output". It defines two separate
things under Tool Result: "Structured Content" (the `structuredContent` field)
and "Output Schema" (the `outputSchema` field). Collapsing them into
"structured output" conflates the two.
It is also actively confusing here. In LLM tooling "structured output" means
constrained decoding — making the *model* emit conforming JSON. These clients
call a model API, so a reader could reasonably take the phrase to mean the
tool constrains the model's response, which is the opposite of what is going
on: the tool describes the shape of its own result.
Headings and prose now say "structured content". References to real
identifiers are left alone: the Python SDK's own docs page is called
Structured Output and lives at docs/servers/structured-output.md, and its
decorator parameter is `structured_output`.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
52 lines
1.4 KiB
TOML
52 lines
1.4 KiB
TOML
[project]
|
|
name = "weather"
|
|
version = "0.1.0"
|
|
description = "A simple MCP weather server"
|
|
readme = "README.md"
|
|
requires-python = ">=3.10"
|
|
# httpx2, not httpx: `mcp` already depends on httpx2, so adding httpx would
|
|
# install a second HTTP stack alongside it.
|
|
dependencies = [
|
|
"httpx2>=2.5.0",
|
|
"mcp[cli]>=2.0.0",
|
|
# weather.py imports BaseModel, Field, and RootModel directly. RootModel is v2-only.
|
|
"pydantic>=2.0.0",
|
|
]
|
|
|
|
[build-system]
|
|
requires = [ "hatchling",]
|
|
build-backend = "hatchling.build"
|
|
|
|
[dependency-groups]
|
|
dev = [
|
|
"ruff>=0.15.8",
|
|
]
|
|
|
|
[project.scripts]
|
|
weather = "weather:main"
|
|
|
|
[tool.ruff]
|
|
line-length = 120
|
|
target-version = "py310"
|
|
extend-exclude = ["README.md"]
|
|
|
|
[tool.ruff.lint]
|
|
select = [
|
|
"C4", # flake8-comprehensions
|
|
"C90", # mccabe
|
|
"E", # pycodestyle
|
|
"F", # pyflakes
|
|
"I", # isort
|
|
"PERF", # Perflint
|
|
"PL", # Pylint
|
|
"UP", # pyupgrade
|
|
]
|
|
ignore = ["PERF203", "PLC0415", "PLR0402"]
|
|
mccabe.max-complexity = 24 # Default is 10
|
|
|
|
[tool.ruff.lint.pylint]
|
|
allow-magic-value-types = ["bytes", "float", "int", "str"]
|
|
max-args = 23 # Default is 5
|
|
max-branches = 23 # Default is 12
|
|
max-returns = 13 # Default is 6
|
|
max-statements = 102 # Default is 50
|