Charm

io.github.bitMacrocodePublished by GitHub account bitMacrocodev1.0.2Updated Nov 2, 2026

OEM automotive repair data - part numbers, torque specs, procedures for 1982-2013 vehicles.

VerifiedStreamable HTTPWeb executableLocation & LifestyleBusiness & Commerce

Overview

AI-generated overview

Hosted MCP server that gives assistants verified OEM automotive repair data — part numbers, torque specs, fluid capacities and procedures for 1982–2013…

What you can do
  • Look up OEM part numbers, torque specs, fluid capacities and service procedures for a vehicle, optionally narrowed by year, make, model and system
  • List the 80+ vehicle manufacturers covered, to check coverage before a lookup
  • Return source-attributed answers drawn from factory service manuals rather than model memory, with purchase links when a part number is identified
When to use it
Useful when an assistant needs authoritative repair or maintenance details for an older, out-of-warranty car — finding a part number, a torque value, a fluid capacity or a service procedure — and you want answers traceable to factory manuals instead of generated text.
Requirements
Remote Streamable HTTP endpoint; no install or local runtime needed. The hosted endpoint is used without an API key. Self-hosting requires Python with the mcp and httpx packages and a free API key supplied via the CHARM_MCP_API_KEY environment variable.
Before you install
Coverage is limited to model years 1982–2013 and the listed makes, so newer vehicles are not answered. Lookups return links to purchase parts, which may lead to third-party sellers. Self-hosting requires an API key that should be kept out of shared configuration.

Installation

In SourceWeft

  1. Open Charm in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.bitMacrocode%2Fcharm/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "charm": {
      "type": "http",
      "url": "https://mcp.chatwithcharm.com/mcp"
    }
  }
}

README

CHARM — 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

bash
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.)

json
{  "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

ToolDescription
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:

bash
pip install mcp httpxexport CHARM_MCP_API_KEY="your_key_here"python3 charm_mcp_http.py        # Streamable HTTP (remote)# orpython3 charm_mcp_server.py      # stdio (local, e.g. Claude Desktop)

License

MIT © Bitmacro

Source: README.md at commit bef1afe

Tools

2

charm_lookup

Look up verified OEM part numbers, torque specs, fluid capacities, and service procedures for vehicles 1982-2013. Returns structured data sourced directly from factory service manuals (not model-generated). Provide year+make+model when known for a precise, isolated answer. Args: query: What you want to know (e.g. "front brake caliper part number", "spark plug gap", "engine oil capacity") year: 4-digit year, 1982-2013 make: Manufacturer (e.g. "Ford", "Honda", "Chevy Truck") model: Model name (e.g. "Taurus X", "Civic", "Silverado") system: Optional system filter (e.g. "brakes", "engine", "electrical")

Parametersmakeyearmodelqueryrequiredsystem

charm_list_makes

List all vehicle manufacturers covered by CHARM (1982-2013). Use to check coverage before a lookup.

Takes no parameters.

Version history

1
  1. v1.0.2LatestSep 16, 2026

Score

100% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts