Skip to content
Merged
Show file tree
Hide file tree
Changes from 1 commit
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 0 additions & 1 deletion docs/get-started/installation.md
Original file line number Diff line number Diff line change
Expand Up @@ -34,7 +34,6 @@ You don't need to know any of this to use the SDK, but if you're wondering what
* `mcp-types`: every protocol type (requests, results, content blocks) as its own package, versioned in lockstep with the SDK. Every `from mcp_types import ...` in these docs is this package.
* [`anyio`](https://anyio.readthedocs.io/): the async runtime. The whole SDK is written against anyio, so it runs on either `asyncio` or `trio`.
* [`pydantic`](https://docs.pydantic.dev/): what every `mcp_types` model is built on, plus all schema generation and validation.
* [`pydantic-settings`](https://docs.pydantic.dev/latest/concepts/pydantic_settings/): server configuration via `MCP_*` environment variables and `.env` files.
* [`httpx2`](https://pypi.org/project/httpx2/): the HTTP client behind the Streamable HTTP and SSE *client* transports, with server-sent events support built in.
* [`starlette`](https://www.starlette.io/), [`uvicorn`](https://www.uvicorn.org/), [`sse-starlette`](https://pypi.org/project/sse-starlette/), and [`python-multipart`](https://pypi.org/project/python-multipart/): the HTTP *server* transports.
* [`jsonschema`](https://pypi.org/project/jsonschema/): validates a tool's structured output against its declared output schema.
Expand Down
16 changes: 16 additions & 0 deletions docs/migration.md
Original file line number Diff line number Diff line change
Expand Up @@ -684,6 +684,22 @@ app = Starlette(routes=[Mount("/", app=mcp.streamable_http_app(json_response=Tru

If you were mutating these via `mcp.settings` after construction (e.g., `mcp.settings.port = 9000`), pass them to `run()` / `sse_app()` / `streamable_http_app()` instead — these fields no longer exist on `Settings`. The `debug` and `log_level` parameters remain on the constructor.

### `MCP_*` environment variables and `.env` files are no longer read

The `Settings` docstring advertised configuration via `MCP_*` environment variables and a `.env` file (e.g. `MCP_DEBUG=true`), but constructor arguments have always taken precedence, so those environment variables never took effect. `Settings` is now a plain Pydantic model rather than a `pydantic-settings` `BaseSettings`, and `pydantic-settings` is no longer a dependency of the SDK.

If you want environment-driven configuration, read the environment yourself and pass the values to the constructor:

```python
import os

from mcp.server.mcpserver import MCPServer

mcp = MCPServer("Demo", debug=os.environ.get("MCP_DEBUG") == "true")
```

If your own code uses `pydantic-settings`, add it to your project's dependencies directly.

### Streamable HTTP request bodies are limited to 4 MiB

V2 applies a 4 MiB default limit to Streamable HTTP POST bodies and returns HTTP 413 before parsing
Expand Down
4 changes: 3 additions & 1 deletion pyproject.toml
Original file line number Diff line number Diff line change
Expand Up @@ -58,6 +58,9 @@
# We add mcp[cli] so `uv sync` considers the extras.
"mcp[cli]",
"mcp-example-stories",
# pydantic-settings is used only by examples (simple-auth, mcpserver/text_me);
# keep it reachable for pyright, which covers examples/servers.
"pydantic-settings>=2.5.2",

Check warning on line 63 in pyproject.toml

View check run for this annotation

Claude / Claude Code Review

text_me.py example breaks outside the repo after pydantic-settings drop

Moving `pydantic-settings` to the dev-only group breaks `examples/mcpserver/text_me.py` for users outside the repo: it does `from pydantic_settings import BaseSettings, SettingsConfigDict` but its PEP 723 block declares `dependencies = []`, so it only ran because `pydantic-settings` was previously a transitive runtime dep of `mcp`. Either declare `pydantic-settings` in the example's inline script dependencies or migrate the example off it, matching the guidance this PR adds to `migration.md`. (T
Comment thread
cubic-dev-ai[bot] marked this conversation as resolved.
Comment thread
claude[bot] marked this conversation as resolved.
"tomli>=2.0; python_version < '3.11'",
"pyright>=1.1.400",
"pytest>=8.4.0",
Expand Down Expand Up @@ -128,7 +131,6 @@
"starlette>=0.27; python_version < '3.14'",
"python-multipart>=0.0.9",
"sse-starlette>=3.0.0",
"pydantic-settings>=2.5.2",
"uvicorn>=0.31.1; sys_platform != 'emscripten'",
"jsonschema>=4.20.0",
"pywin32>=311; sys_platform == 'win32'",
Expand Down
18 changes: 3 additions & 15 deletions src/mcp/server/mcpserver/server.py
Original file line number Diff line number Diff line change
Expand Up @@ -44,8 +44,8 @@
from mcp_types import Resource as MCPResource
from mcp_types import ResourceTemplate as MCPResourceTemplate
from mcp_types import Tool as MCPTool
from pydantic import BaseModel
from pydantic.networks import AnyUrl
from pydantic_settings import BaseSettings, SettingsConfigDict
from starlette.applications import Starlette
from starlette.middleware import Middleware
from starlette.middleware.authentication import AuthenticationMiddleware
Expand Down Expand Up @@ -98,20 +98,8 @@
_CallableT = TypeVar("_CallableT", bound=Callable[..., Any])


class Settings(BaseSettings, Generic[LifespanResultT]):
"""MCPServer settings.

All settings can be configured via environment variables with the prefix MCP_.
For example, MCP_DEBUG=true will set debug=True.
"""

model_config = SettingsConfigDict(
env_prefix="MCP_",
env_file=".env",
env_nested_delimiter="__",
nested_model_default_partial_update=True,
extra="ignore",
)
class Settings(BaseModel, Generic[LifespanResultT]):
"""MCPServer settings, as passed to the `MCPServer` constructor."""

# Server settings
debug: bool
Expand Down
4 changes: 2 additions & 2 deletions uv.lock

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

Loading