Move mcp-run-python

Author: samuelcolvin

.github/workflows/ci.yml

@@ -29,10 +29,6 @@ jobs:
       - name: Install dependencies
         run: uv sync --all-extras --all-packages --group lint
 
-      - uses: denoland/setup-deno@v2
-        with:
-          deno-version: v2.x
-
       - uses: pre-commit/[email protected]
         with:
           extra_args: --all-files --verbose
@@ -272,29 +268,6 @@ jobs:
           path: htmlcov
           include-hidden-files: true
 
-  test-mcp-run-python:
-    runs-on: ubuntu-latest
-    timeout-minutes: 5
-    env:
-      UV_PYTHON: "3.12"
-    steps:
-      - uses: actions/checkout@v4
-
-      - uses: astral-sh/setup-uv@v5
-        with:
-          enable-cache: true
-
-      - uses: denoland/setup-deno@v2
-        with:
-          deno-version: v2.x
-
-      - run: make lint-js
-
-      - run: uv run --package mcp-run-python pytest mcp-run-python -v --durations=100
-
-      - run: deno task dev warmup
-        working-directory: mcp-run-python
-
   # https://github.com/marketplace/actions/alls-green#why used for branch protection checks
   check:
     if: always()
@@ -307,7 +280,6 @@ jobs:
       - test-lowest-versions
       - test-examples
       - coverage
-      - test-mcp-run-python
     runs-on: ubuntu-latest
 
     steps:

.pre-commit-config.yaml

@@ -44,14 +44,6 @@ repos:
         types: [python]
         language: system
         pass_filenames: false
-      - id: lint-js
-        name: Lint JS
-        entry: make
-        args: [lint-js]
-        language: system
-        types_or: [javascript, ts, json]
-        files: "^mcp-run-python/"
-        pass_filenames: false
       - id: clai-help
         name: clai help output
         entry: uv

Makefile

@@ -8,12 +8,8 @@
 .pre-commit: ## Check that pre-commit is installed
 	@pre-commit -V || echo 'Please install pre-commit: https://pre-commit.com/'
 
-.PHONY: .deno
-.deno: ## Check that deno is installed
-	@deno --version > /dev/null 2>&1 || (printf "\033[0;31m✖ Error: deno is not installed, but is needed for mcp-run-python\033[0m\n    Please install deno: https://docs.deno.com/runtime/getting_started/installation/\n" && exit 1)
-
 .PHONY: install
-install: .uv .pre-commit .deno ## Install the package, dependencies, and pre-commit for local development
+install: .uv .pre-commit ## Install the package, dependencies, and pre-commit for local development
 	uv sync --frozen --all-extras --all-packages --group lint --group docs
 	pre-commit install --install-hooks
 
@@ -38,10 +34,6 @@ lint: ## Lint the code
 	uv run ruff format --check
 	uv run ruff check
 
-.PHONY: lint-js
-lint-js: ## Lint JS and TS code
-	cd mcp-run-python && deno task lint-format
-
 .PHONY: typecheck-pyright
 typecheck-pyright:
 	@# PYRIGHT_PYTHON_IGNORE_WARNINGS avoids the overhead of making a request to github on every invocation
@@ -77,11 +69,6 @@ testcov: test ## Run tests and generate an HTML coverage report
 	@echo "building coverage html"
 	@uv run coverage html
 
-.PHONY: test-mrp
-test-mrp: ## Build and tests of mcp-run-python
-	cd mcp-run-python && deno task build
-	uv run --package mcp-run-python pytest mcp-run-python -v
-
 .PHONY: update-examples
 update-examples: ## Update documentation examples
 	uv run -m pytest --update-examples tests/test_examples.py

docs/mcp/client.md

@@ -19,7 +19,7 @@ Pydantic AI comes with two ways to connect to MCP servers:
 - [`MCPServerSSE`][pydantic_ai.mcp.MCPServerSSE] which connects to an MCP server using the [HTTP SSE](https://spec.modelcontextprotocol.io/specification/2024-11-05/basic/transports/#http-with-sse) transport
 - [`MCPServerStdio`][pydantic_ai.mcp.MCPServerStdio] which runs the server as a subprocess and connects to it using the [stdio](https://spec.modelcontextprotocol.io/specification/2024-11-05/basic/transports/#stdio) transport
 
-Examples of all three are shown below; [mcp-run-python](run-python.md) is used as the MCP server in all examples.
+Examples of all three are shown below.
 
 Each MCP server instance is a [toolset](../toolsets.md) and can be registered with an [`Agent`][pydantic_ai.Agent] using the `toolsets` argument.
 
@@ -59,9 +59,9 @@ agent = Agent('openai:gpt-4o', toolsets=[server])  # (2)!
 
 async def main():
     async with agent:  # (3)!
-        result = await agent.run('How many days between 2000-01-01 and 2025-03-18?')
+        result = await agent.run('What is 7 plus 5')
     print(result.output)
-    #> There are 9,208 days between January 1, 2000, and March 18, 2025.
+    #> The answer is 12.
 ```
 
 1. Define the MCP server with the URL used to connect.
@@ -97,19 +97,26 @@ Will display as follows:
 [`MCPServerSSE`][pydantic_ai.mcp.MCPServerSSE] connects over HTTP using the [HTTP + Server Sent Events transport](https://spec.modelcontextprotocol.io/specification/2024-11-05/basic/transports/#http-with-sse) to a server.
 
 !!! note
-    [`MCPServerSSE`][pydantic_ai.mcp.MCPServerSSE] requires an MCP server to be running and accepting HTTP connections before running the agent. Running the server is not managed by Pydantic AI.
+    The SSE transport in MCP is deprecated, you should use Streamable HTTP instead.
+
+Before creating the SSE client, we need to run a server that supports the SSE transport.
+
 
-The name "HTTP" is used since this implementation will be adapted in future to use the new
-[Streamable HTTP](https://github.com/modelcontextprotocol/specification/pull/206) currently in development.
+```python {title="sse_server.py" dunder_name="not_main"}
+from mcp.server.fastmcp import FastMCP
+
+app = FastMCP()
 
-Before creating the SSE client, we need to run the server (docs [here](run-python.md)):
+@app.tool()
+def add(a: int, b: int) -> int:
+    return a + b
 
-```bash {title="terminal (run sse server)"}
-deno run \
-  -N -R=node_modules -W=node_modules --node-modules-dir=auto \
-  jsr:@pydantic/mcp-run-python sse
+if __name__ == '__main__':
+    app.run(transport='sse')
 ```
 
+Then we can create the client:
+
 ```python {title="mcp_sse_client.py"}
 from pydantic_ai import Agent
 from pydantic_ai.mcp import MCPServerSSE
@@ -120,9 +127,9 @@ agent = Agent('openai:gpt-4o', toolsets=[server])  # (2)!
 
 async def main():
     async with agent:  # (3)!
-        result = await agent.run('How many days between 2000-01-01 and 2025-03-18?')
+        result = await agent.run('What is 7 plus 5')
     print(result.output)
-    #> There are 9,208 days between January 1, 2000, and March 18, 2025.
+    #> The answer is 12.
 ```
 
 1. Define the MCP server with the URL used to connect.
@@ -133,23 +140,16 @@ _(This example is complete, it can be run "as is" — you'll need to add `asynci
 
 ### MCP "stdio" Server
 
-The other transport offered by MCP is the [stdio transport](https://spec.modelcontextprotocol.io/specification/2024-11-05/basic/transports/#stdio) where the server is run as a subprocess and communicates with the client over `stdin` and `stdout`. In this case, you'd use the [`MCPServerStdio`][pydantic_ai.mcp.MCPServerStdio] class.
+MCP also offers [stdio transport](https://spec.modelcontextprotocol.io/specification/2024-11-05/basic/transports/#stdio) where the server is run as a subprocess and communicates with the client over `stdin` and `stdout`. In this case, you'd use the [`MCPServerStdio`][pydantic_ai.mcp.MCPServerStdio] class.
+
+In this example [mcp-run-python](https://github.com/pydantic/mcp-run-python) is used as the MCP server.
 
 ```python {title="mcp_stdio_client.py"}
 from pydantic_ai import Agent
 from pydantic_ai.mcp import MCPServerStdio
 
 server = MCPServerStdio(  # (1)!
-    'deno',
-    args=[
-        'run',
-        '-N',
-        '-R=node_modules',
-        '-W=node_modules',
-        '--node-modules-dir=auto',
-        'jsr:@pydantic/mcp-run-python',
-        'stdio',
-    ]
+    'uvx', args=['mcp-run-python', 'stdio'],
 )
 agent = Agent('openai:gpt-4o', toolsets=[server])
 
@@ -161,7 +161,7 @@ async def main():
     #> There are 9,208 days between January 1, 2000, and March 18, 2025.
 ```
 
-1. See [MCP Run Python](run-python.md) for more information.
+1. See [MCP Run Python](https://github.com/pydantic/mcp-run-python) for more information.
 
 ## Tool call customisation
 

docs/mcp/overview.md

@@ -19,11 +19,3 @@ Some examples of what this means:
 - Pydantic AI could use a web search service implemented as an MCP server to implement a deep research agent
 - Cursor could connect to the [Pydantic Logfire](https://github.com/pydantic/logfire-mcp) MCP server to search logs, traces and metrics to gain context while fixing a bug
 - Pydantic AI, or any other MCP client could connect to our [Run Python](run-python.md) MCP server to run arbitrary Python code in a sandboxed environment
-
-## MCP Servers
-
-To add functionality to Pydantic AI while making it as widely usable as possible, we're implementing some functionality as MCP servers.
-
-So far, we've only implemented one MCP server as part of Pydantic AI:
-
-- [Run Python](run-python.md): A sandboxed Python interpreter that can run arbitrary code, with a focus on security and safety.