gabrielekarra/mcp-anything

Describe what you want. Get a production-ready MCP server.
MCP-Anything turns any data source into a fully implemented MCP server — from a plain-language brief describing what agents should be able to do. It also works directly from codebases, OpenAPI specs, gRPC protos, and GraphQL schemas. Two modes, one tool.
## Try it inside Claude Code
No install step — the skill installs the CLI for you on first use.
/plugin marketplace add gabrielekarra/mcp-anything
/plugin install mcp-anything@mcp-anything
Then just ask: "turn this OpenAPI spec into an MCP server" or "wrap my Flask app as MCP tools". The skill figures out the right mode (generate vs. brief-driven build), runs it, and hands you back a working server plus the client config to add it.
## Quick start
1. Install
bash
pip install mcp-anything
export ANTHROPICAPIKEY=sk-...
2. Write a brief — describe your domain and point at your data source
yaml
# my-api.yaml
servername: payments-mcp
domaindescription: >
A payment API for managing customers, invoices, and subscriptions.
usecases:
"Create a customer with email and name"
"Issue an invoice and send it to the customer"
"Create and cancel subscriptions"
"Issue refunds"
datasourcepath: ./openapi.json # local file or URL
datasourcekind: openapi # openapi | graphql | grpc
authmethod: bearertoken
backendtarget: fastmcp
3. Build
bash
mcp-anything build --brief my-api.yaml -o ./my-mcp-server
4. Run
bash
cd my-mcp-server
pip install -e .
python -m mcppaymentsmcp.server
That's it. You now have a running MCP server. Add it to your agent:
json
"mcpServers": {
"payments": { "command": "python", "args": ["-m", "mcppaymentsmcp.server"] }
## Two modes
### build — brief-driven (recommended)
The LLM reads your brief, groups related operations into ergonomic tools, writes agent-optimised descriptions, and generates the full server package including a SKILL.md agent guide and an eval harness.
### generate — codebase scanner (no brief required)
Point at source code or a spec URL. Static detection, no LLM needed.
bash
# From a local codebase
mcp-anything generate /path/to/your/app
# From a URL (OpenAPI, GraphQL, gRPC)
mcp-anything generate https://api.example.com/openapi.json
## What you get
Both modes produce a complete, pip-installable package:
my-mcp-server/
├── mcp /
│ ├── server.py # FastMCP server (stdio or HTTP)
│ ├── tools/ # One file per tool, HTTP calls via httpx
│ ├── discovery.py # GET /.well-known/mcp
│ └── telemetry.py # Anonymised per-call logging
├── SKILL.md # Agent-readable usage guide (recipes, gotchas, anti-patterns)
├── quickqueries.json # Eval set derived from your use cases
├── evalcases.json # LLM-generated evaluation cases
├── conformancereport.json
├── Dockerfile
└── pyproject.toml
SKILL.md is the key output. It's a structured document written for AI agents — not humans — that lists every tool with its parameters, operation modes, usage recipes, gotchas, and anti-patterns. Agents read it before making any calls, which dramatically reduces hallucinations and misuse.
## How tools get designed
The LLM follows 2026 MCP design rules automatically:
Group CRUD. Three or more operations on the same resource become a single manageX(operation=...) tool. Fewer tools, broader coverage, easier for agents to use.