About charm
CHARM is a hosted MCP server for AI agents that need OEM repair information for 1982–2013 vehicles across 80+ makes. Its answers come from factory service manuals and include source attribution, with purchase links when a part number is identified.
Key features
- 01OEM part numbers and service procedures
- 02Torque specs and fluid capacities
- 03Coverage of 1982–2013 vehicles
- 04Manufacturer coverage listing
- 05Purchase links for identified parts
Use cases
- 01Find a vehicle's factory part number
- 02Check torque specs or fluid capacity
- 03Look up a repair procedure by vehicle
- 04Locate where to buy an identified part
MCP support
Exposes OEM repair lookups and a manufacturer list as MCP tools over a hosted Streamable HTTP endpoint. An optional self-hosted instance can run over HTTP or stdio.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://mcp.chatwithcharm.com/mcpclaude mcp add --transport http bitmacrocode-charm https://mcp.chatwithcharm.com/mcp{"mcpServers":{"bitmacrocode-charm":{"type":"http","url":"https://mcp.chatwithcharm.com/mcp"}}}Open in Cursor{"servers":{"bitmacrocode-charm":{"type":"http","url":"https://mcp.chatwithcharm.com/mcp"}}}Open in VS Code{"mcpServers":{"bitmacrocode-charm":{"type":"http","url":"https://mcp.chatwithcharm.com/mcp"}}}{"mcpServers":{"bitmacrocode-charm":{"serverUrl":"https://mcp.chatwithcharm.com/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
2| Parameter | Type | Required | Description |
|---|---|---|---|
| make | any | No | |
| year | any | No | |
| model | any | No | |
| query | string | Yes | |
| system | any | No |
Details
From the project READMECHARM — OEM Automotive Data for AI Agents (MCP)
CHARM is an MCP server that gives AI agents authoritative OEM automotive repair data — factory service-manual part numbers, torque specs, fluid capacities, and procedures for vehicles 1982–2013, across 80+ makes.
Answers come straight from OEM factory service manuals, not a model's memory — so they're verifiable and source-attributed, not hallucinated. When a part number is identified, CHARM also returns links to purchase that exact part.
Built to be called by AI agents — Claude, ChatGPT, Gemini, and beyond.
Connect (hosted — no install)
Remote MCP endpoint (Streamable HTTP):
https://mcp.chatwithcharm.com/mcp
Claude Code
claude mcp add --transport http charm https://mcp.chatwithcharm.com/mcp
Claude Desktop — Settings → Connectors → Add custom connector → paste the URL above.
Config-file clients (Cursor, etc.)
{
"mcpServers": {
"charm": { "type": "http", "url": "https://mcp.chatwithcharm.com/mcp" }
}
}
Then just ask naturally:
What's the front brake caliper part number for a 2009 Ford Taurus X, and where can I buy it?
What's the spark plug gap for a 2001 Toyota Camry?
Tools
| Tool | Description |
|---|---|
charm_lookup(query, year?, make?, model?, system?) | Verified OEM part numbers, torque specs, fluid capacities, and service procedures. Pass year+make+model for a precise, isolated answer. |
charm_list_makes() | List all covered manufacturers. |
Coverage
- Model years 1982–2013 — the DIY-repair sweet spot (out-of-warranty, owner-serviced vehicles).
- 80+ makes.
- Data sourced directly from OEM factory service manuals — authoritative, not generated.
Self-hosting (optional)
You don't need to self-host to use CHARM — the hosted endpoint above is the easy path.
To run your own instance against the CHARM API, grab a free key at
https://chatwithcharm.com/api/v1/docs, then:
pip install mcp httpx
export CHARM_MCP_API_KEY="your_key_here"
python3 charm_mcp_http.py # Streamable HTTP (remote)
# or
python3 charm_mcp_server.py # stdio (local, e.g. Claude Desktop)
License
MIT © Bitmacro
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.