FrankenClaw is a minimal framework for building MCP tools. Drop a Python file in `tools/`, write one async function with a docstring, flip it on in
If you already use Frankenclaw, the frankenclaw mcp server is the piece that lets your assistant work with it directly. FrankenClaw is a minimal framework for building MCP tools. Drop a Python file in tools/, write one async function with a docstring, flip it on in your config — your agent has a new tool. No server edits, no registration boilerplate, no.
The toolset is worth reading before you wire it up, because it tells you what the integration is really for:
FrankenTool — What It Doesweb_scrape — Scrape any page to clean markdown — no ads, no navsearch_web — Web search returning title/url/snippetfile_find — Find files on this machine from a fuzzy descriptionand on PyPI is all you need. Most clients run it directly, so configuration is a few lines and a restart.
Configuration is passed through the environment: FIRECRAWL_API_KEY, FRANKENCLAW_KEYS_PATH. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.
web_scrape example (or remove it from enabled_tools and add your own tools) The chassis core is just FastMCP. Tools you add bring their own dependencies — install those yourself.Plenty of search and retrieval servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Frankenclaw's toolset — FrankenTool, web_scrape, search_web and 1 more — is a fair guide to whether it matches your workflow. It is maintained by guymanndude; worth a glance at recent repository activity before you build anything load-bearing on it.
We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.
| Tool | What it does |
|---|---|
| FrankenTool | What It Does |
| web_scrape | Scrape any page to clean markdown — no ads, no nav |
| search_web | Web search returning title/url/snippet |
| file_find | Find files on this machine from a fuzzy description |
{
"mcpServers": {
"frankenclaw": {
"command": "uvx",
"args": ["and"],
"env": {
"FIRECRAWL_API_KEY": "your-value",
"FRANKENCLAW_KEYS_PATH": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
web_scrape example (or remove it from enabled_tools and add your own tools) The chassis core is just FastMCP. Tools you add bring their own dependencies — install those yourself.| Variable | Description | Required |
|---|---|---|
| FIRECRAWL_API_KEY | Credential the server authenticates with. | Yes |
| FRANKENCLAW_KEYS_PATH | Credential the server authenticates with. | Yes |
The simplest web tool that matters — fetch any URL and get model-ready markdown back.
Industrial-strength web extraction — render, scrape, crawl and search entire sites into clean markdown.
Puppeteer-powered browser control that drives pages from the accessibility tree instead of pixels.
Search built for AI, not humans — semantic web search that returns model-ready content, plus code context.
Answers, not links — delegate questions to Perplexity's search-grounded models and get cited responses back.
Put 6,000+ pre-built scrapers at your assistant's fingertips through one MCP endpoint.