Skip to main content

A Simple Python MCP Solution

Project description

aiomcp

A Simple Python MCP Solution

Mission of aiomcp

A smooth start experience.

Tutorial

Expected Behavior for Version 0.1.0

A simple McpServer

def func(a: int, b: int):
    return a + b

impl = ToolImpl()

mcp_server = McpServer("mcp-server-name")
await mcp_server.register_tool(func)
await mcp_server.register_tool(impl.method, alias="tool_alias")
await mcp_server.register_tool(ToolImpl.class_method)
await mcp_server.host("http://127.0.0.1:8000/mcp")

A simple McpClient

mcp_client = McpClient("mcp-client-name")
await mcp_client.initialize("http://127.0.0.1:8000/mcp")
# await mcp_client.initialize(McpHttpTransport("127.0.0.1", 8000, "/mcp"))
# await mcp_client.initialize(McpStdioClientTransport([sys.executable, "server.py"]))
# await mcp_client.initialize(mcp_server) for quick testing without hosting a server
sum_value = await mcp_client.invoke("name", {"a": 1, "b": 2})
# standard MCP functions
# await mcp_client.mcp_tools_list() -> list[McpTool]
# await mcp_client.mcp_tools_call(tool: McpTool, request: McpRequest) -> McpResponse | McpError

Using McpTransports

While McpClient and McpServer handle client/server behavior, they are implemented in a platform-agnostic way by using McpClientTransport/McpServerTransport to handle message streams. Client and server transports usually come in pairs as McpTransport implementations.

mcp_server = McpServer()
await mcp_server.host(McpHttpTransport("127.0.0.1", 8000, "/mcp"))
# await mcp_server.host("http://127.0.0.1:8000/mcp")
mcp_client = McpClient()
await mcp_client.initialize(McpHttpTransport("127.0.0.1", 8000, "/mcp"))
# await mcp_client.initialize("http://127.0.0.1:8000/mcp")

Supported McpTransport implementations:

  • McpDirectTransport: Simple client driven transport that invokes McpServer with minimal MCP protocol overhead.
  • McpMemoryTransport: Single event loop, in-memory transport.
  • McpHttpTransport
  • McpStdioClientTransport / McpStdioServerTransport: stdio based transport

Sample: Using McpMemoryTransport for local debugging.

transport = McpMemoryTransport()

mcp_server = McpServer()
asyncio.create_task(mcp_server.host(transport))

mcp_client = McpClient()
await mcp_client.initialize(transport)

Authorization

Connect to an OAuth 2.1 protected remote MCP server.

from aiomcp import McpClient, McpAuthorizationClient

authorization = await McpAuthorizationClient.discover("http://remote-server/mcp")

# Or use a bearer token
# authorization = McpAuthorizationClient("your-access-token")

client = McpClient("mcp-client-name")
await client.initialize("http://remote-server/mcp", authorization=authorization)

Use GitHub as the OAuth provider to connect to GitHub's MCP server.

from aiomcp import McpClient, McpAuthorizationClient

server_url = "https://api.githubcopilot.com/mcp/"

authorization = await McpAuthorizationClient.discover(
    server_url,
    client_id="{YOUR_CLIENT_ID}",
    client_secret="{YOUR_CLIENT_SECRET}",
)

client = McpClient("mcp-client-name")
await client.initialize(server_url, authorization=authorization)

Protect your MCP server with built-in OAuth 2.1 + Dynamic Client Registration.

from aiomcp import McpServer, McpAuthorizationServer

server = McpServer("mcp-server-name")
await server.register_tool(add, alias="add")

authorization = McpAuthorizationServer()
await server.host("http://127.0.0.1:8000/mcp", authorization=authorization)

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

aiomcp-0.0.7.tar.gz (28.9 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

aiomcp-0.0.7-py3-none-any.whl (28.7 kB view details)

Uploaded Python 3

File details

Details for the file aiomcp-0.0.7.tar.gz.

File metadata

  • Download URL: aiomcp-0.0.7.tar.gz
  • Upload date:
  • Size: 28.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for aiomcp-0.0.7.tar.gz
Algorithm Hash digest
SHA256 0c9b8227b9e9d2b70f3f956ce77bf6e16a06dc83ad1affd4848039e5247e1bdc
MD5 d6a302a4294b9bdf323c1ae9eaff6ee4
BLAKE2b-256 d4cfbc1acf3c8987f6874047fbe71ec3f53af14f4fa3e68eec27e09a370a568a

See more details on using hashes here.

Provenance

The following attestation bundles were made for aiomcp-0.0.7.tar.gz:

Publisher: publish.yml on yangyuan/aiomcp

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file aiomcp-0.0.7-py3-none-any.whl.

File metadata

  • Download URL: aiomcp-0.0.7-py3-none-any.whl
  • Upload date:
  • Size: 28.7 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for aiomcp-0.0.7-py3-none-any.whl
Algorithm Hash digest
SHA256 d146835b3e7aed78d25474b58b9f17bf41c32b1cce5308dced2cc42a5de774a7
MD5 5193fd5876fe4af164d00acbe44dfdf9
BLAKE2b-256 c49c73d1886fa9123cce0ab99229ec939f023576404a049be8fa0ab9af3cf821

See more details on using hashes here.

Provenance

The following attestation bundles were made for aiomcp-0.0.7-py3-none-any.whl:

Publisher: publish.yml on yangyuan/aiomcp

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page