Github to MCP
Point it at any GitHub repository and get a working MCP server back — tools generated from the repo's OpenAPI, GraphQL, gRPC or AsyncAPI definitions and its source code.Read full description
nirholasLABSCO SUMMARY
The .proto path is the part worth noticing.
Most gRPC bridges assume server reflection is switched on, which in a lot of production environments it deliberately is not. Being able to hand it a .proto file plus the server address covers that case without asking anyone to change a deployment. The config file is the whole interface — one list of sources, mixing REST, gRPC and Connect-RPC entries, local and remote.
What it is
A schema-to-tools converter. You list your services in a config file; MCPizer discovers their schemas, converts each operation into a tool, and handles the calls with typed parameters and error handling. Nothing changes in the services themselves.
What you get
- Auto-discovery of OpenAPI and Swagger schemas from a bare service URL — a FastAPI app is found at
/openapi.jsonor/docs, a Spring Boot service at/v3/api-docs— or a direct schema URL when you prefer to be explicit - gRPC services reached through reflection, or through a
.protofile paired with aserveraddress when reflection is not enabled - Connect-RPC services in either gRPC or HTTP/JSON mode, the latter being the easier one to debug
- Schemas fetched from GitHub with
github://URLs, including private repositories, authenticated through theghCLI - Both transports: stdio for clients that launch it as a subprocess, and SSE over HTTP for clients that connect to a running server
Requirements
Go, to install the binary: go install github.com/i2y/mcpizer/cmd/mcpizer@latest, with $GOPATH/bin on your PATH. A config file listing your services under schema_sources, passed with -config or set through MCPIZER_CONFIG_FILE; the default is configs/mcpizer.yaml. Run it as a subprocess with -transport=stdio. Credentials are whatever the target services require; private GitHub schemas use your existing gh CLI authentication rather than a separate token.
Setup effort
One command — go install github.com/i2y/mcpizer/cmd/mcpizer@latest
USE CASES
01
Making an internal microservice callable without new code
Add the service URL to the source list; the OpenAPI document it already publishes becomes the tool definitions.
02
Reaching a gRPC service with reflection disabled
Point at the .proto file and name the server address separately, instead of asking the service owner to enable reflection.
03
Working from schemas that live in a private repo
Reference them with github:// URLs and let the existing gh CLI session authenticate the fetch.
04
Running one bridge across a whole stack
List production, staging and localhost services in the same config so a single server exposes all of them to the assistant.
BEFORE YOU INSTALL
What to know first
Requires
Go, with $GOPATH/bin on your PATH
Where it runs
The documented client runs the server on your machine.
INSTALLATION
Connect your client
Server setup
TERMINAL
go install github.com/i2y/mcpizer/cmd/mcpizer@latestMCP Clients
Claude Desktop
CLAUDE DESKTOP · JSON
{
"mcpServers": {
"mcpizer": {
"command": "mcpizer",
"args": [
"-transport=stdio",
"-config=<YOUR_PATH_TO_CONFIG>"
]
}
}
}
