Skip to main content

A Simple Python MCP Solution

Project description

aiomcp

A Simple Python MCP Solution

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("tool_1", func)
await mcp_server.register_tool("tool_2", impl.method)
await mcp_server.register_tool("tool_3", ToolImpl.class_method)
await mcp_server.host("http://127.0.0.1:8000")

A simple McpClient

mcp_client = McpClient("mcp-client-name")
await mcp_client.initialize("http://127.0.0.1:8000")
# mcp_client = mcp_client.initialize("server.py") for stdio
# mcp_client = mcp_client.initialize(mcp_server) for quick testing without hosting 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(HttpTransport("127.0.0.1", 8000))
mcp_client = McpClient()
await mcp_client.initialize(HttpTransport("127.0.0.1", 8000))

Supported McpTransport implementations:

  • SocksMcpTransport
  • HttpMcpTransport
  • StdioMcpTransport
  • MemoryMcpTransport

Sample: Using MemoryMcpTransport for local debugging.

transport = MemoryMcpTransport()

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

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

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-0.0.1.tar.gz (10.0 kB view details)

Uploaded Source

Built Distribution

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

aiomcp-0.0.1-py3-none-any.whl (11.1 kB view details)

Uploaded Python 3

File details

Details for the file aiomcp-0.0.1.tar.gz.

File metadata

  • Download URL: aiomcp-0.0.1.tar.gz
  • Upload date:
  • Size: 10.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for aiomcp-0.0.1.tar.gz
Algorithm Hash digest
SHA256 141a01a7b3fdba90462ba851375bce37e322a644d8fa2ac2a561bf1e7c009f10
MD5 5f91e3611f40f2835a9c46f6350f9385
BLAKE2b-256 bce85a3b46ce0c36ef1fc44bcd5623a9ddf8b5bddd1969109bb39d1437c666f3

See more details on using hashes here.

Provenance

The following attestation bundles were made for aiomcp-0.0.1.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-0.0.1-py3-none-any.whl.

File metadata

  • Download URL: aiomcp-0.0.1-py3-none-any.whl
  • Upload date:
  • Size: 11.1 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for aiomcp-0.0.1-py3-none-any.whl
Algorithm Hash digest
SHA256 b6ebf24e7eaf45438c9552e88dcc268e3f47253ca15990d6b38577b50a84b1ca
MD5 652a54c4785738fa2ec521d5cb8df2e1
BLAKE2b-256 0d59978bde607a04e746b8dbaba4e7a8ed29aa63d38ef6e6667145686a04fa60

See more details on using hashes here.

Provenance

The following attestation bundles were made for aiomcp-0.0.1-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