embedded-docs — Claude Code MCP server: cited datasheet answers
Hands your coding agent verbatim documentation snippets with section and page citations. Useful when a register value has to be exact.
claude mcp add --transport http embedded-docs https://mcp.byteask.ai/mcpWhat embedded-docs does
Queries go in as plain language or an exact identifier. What comes back is ranked evidence from the corpus: document title, section and page reference, the source text itself, and a result_id. A miss returns "no confident match" instead of a made-up register value. The get_context tool expands a hit into its full section, and request_document logs a request for a document that is missing from the corpus.
Three tools, two transports. Local agents talk over stdio; the hosted endpoint speaks Streamable HTTP at https://mcp.byteask.ai/mcp. The retrieval engine and the licensed corpus live outside this repository, behind a two-method SearchBackend interface. A bundled SampleBackend with a few illustrative records lets search_docs answer right away, no API keys involved. Point the server at your own engine with BYTEASK_BACKEND set to module:callable.
Running it locally takes Python 3.10 or newer and uv. Settings come from environment variables and .env: transport, HTTP host and port, bearer token, allowed Host headers. Leaving MCP_HTTP_AUTH_TOKEN empty drops authentication from the HTTP server, which is fine on your machine and a bad idea anywhere reachable from the network.
What it helps with
- confirm a register offset before touching driver code
- look up the Modbus function code for writing multiple registers
- check an IEEE clause rather than trust recall
- pull the exact SCPI command syntax
- ask for a missing datasheet to be added to the corpus
Example prompts for the agent
- Search the docs for the Modbus function code that writes multiple registers
- Check the datasheet for the ETH_DMATDLAR register offset and cite the page
- Expand the full section for this
result_id
How to install embedded-docs
Platform CLI: remote server
claude mcp add --transport http embedded-docs https://mcp.byteask.ai/mcpPlatform CLI: remote server
codex mcp add embedded-docs --url https://mcp.byteask.ai/mcpConfig file
{
"mcpServers": {
"embedded-docs": {
"url": "https://mcp.byteask.ai/mcp"
}
}
}Config file
{
"servers": {
"embedded-docs": {
"type": "http",
"url": "https://mcp.byteask.ai/mcp"
}
}
}Platform CLI: remote server
gemini mcp add -t http embedded-docs https://mcp.byteask.ai/mcpStep by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about embedded-docs
How do I install embedded-docs in Claude Code?
Run claude mcp add --transport http embedded-docs https://mcp.byteask.ai/mcp. That connects the hosted server over Streamable HTTP, so there is nothing to install locally.
What does embedded-docs do?
It searches a corpus of embedded and firmware reference material and returns verbatim snippets with a section and page citation. When nothing matches closely enough, it says so rather than inventing an answer.
Can I use my own retrieval engine?
Yes. Implement the SearchBackend interface with search and get_context, expose a make_backend(config) factory, and set BYTEASK_BACKEND to module:callable.
