GRPC Transport For
БесплатноНе проверенEnables MCP servers and clients to communicate over gRPC using FastMCP, supporting tool calls, text and image content, and progress reporting.
Описание
Enables MCP servers and clients to communicate over gRPC using FastMCP, supporting tool calls, text and image content, and progress reporting.
README
[!WARNING] Experimental / Proof of Concept
This package is a proof of concept for experimentation purposes. It is not intended for production use. The official Python package is being developed at GoogleCloudPlatform/mcp-grpc-transport-py — please follow/star that repo to stay updated.
A gRPC transport implementation for the Model Context Protocol (MCP) using FastMCP.
Background
- SEP: gRPC as a native MCP transport — the specification enhancement proposal
- Blog: gRPC as a Native Transport for MCP
Features
- Server: expose a FastMCP server over gRPC
- Client: call a gRPC MCP server and get back native
mcp.typesobjects - Tool calls with text and image content, structured output, and progress reporting
- Proto definitions sourced from GoogleCloudPlatform/mcp-grpc-transport-proto
Installation
uv sync
The proto package (mcp-transport-proto) is fetched directly from GitHub via [tool.uv.sources] — no manual proto compilation needed.
Server
import asyncio
from mcp.server.fastmcp import FastMCP
from grpcmcp import serve_grpc
mcp = FastMCP("My Server")
@mcp.tool()
async def my_tool(x: int) -> str:
"""Does something useful."""
return str(x)
if __name__ == "__main__":
asyncio.run(serve_grpc(mcp)) # default: 0.0.0.0:50051
# asyncio.run(serve_grpc(mcp, port=9090))
Client
import asyncio
from grpcmcp import GRPCClient
async def main():
async with GRPCClient("localhost", 50051) as client:
tools = await client.list_tools()
for tool in tools.tools:
print(f"{tool.name}: {tool.description}")
result = await client.call_tool("my_tool", {"x": 42})
for content in result.content:
if content.type == "text":
print(content.text)
asyncio.run(main())
GRPCClient reference
| Parameter | Type | Description |
|---|---|---|
host |
str |
Server hostname |
port |
int |
Server port |
timeout |
float | None |
Default per-call timeout in seconds |
channel_options |
list[tuple] | None |
Raw gRPC channel options |
| Method | Returns |
|---|---|
list_tools() |
types.ListToolsResult |
call_tool(name, arguments) |
types.CallToolResult |
Running the examples
Start the server:
uv run python example/grpc_example_server.py
In another terminal, run the client:
uv run python example/grpc_example_client.py
Requirements
- Python >= 3.10
- grpcio >= 1.78.0
- protobuf >= 4.25.0
- mcp == 1.25.0
Установка GRPC Transport For
У этого сервера нет опубликованного пакета — он собирается из исходников. Открой репозиторий и следуй инструкции в README.
▸ github.com/pawbhard/grpcmcpFAQ
GRPC Transport For MCP бесплатный?
Да, GRPC Transport For MCP бесплатный — установка в пару кликов через Unyly без оплаты.
Нужен ли API-ключ для GRPC Transport For?
Нет, GRPC Transport For работает без API-ключей и переменных окружения.
GRPC Transport For — hosted или self-hosted?
Доступен hosted-вариант: Unyly запускает сервер в облаке, локальная установка не обязательна.
Как установить GRPC Transport For в Claude Desktop, Claude Code или Cursor?
Открой GRPC Transport For на unyly.org, выбери вкладку своего клиента (Claude Desktop, Claude Code, Cursor) и нажми Install — конфиг сгенерируется автоматически, без правки JSON.
Похожие MCP
Omni Video
An MCP server that transforms LLM-enabled IDEs into professional video editors by pre-processing footage into text proxies, generating motion graphics via HTML/
автор: buildwithtazaARA
Generate images, video and audio from any AI agent — one connector.
автор: ARAYouTube
Transcripts, channel stats, search
автор: YouTubeEverArt
AI image generation using various models.
автор: modelcontextprotocolCompare GRPC Transport For with
Не уверен что выбрать?
Найди свой стек за 60 секунд
Автор?
Embed-бейдж для README
Похожее
Все в категории media
