PluginBench
MCP Server
Active
MIT

ai.byteask/embedded-docs MCP Server

ai.byteask/embedded-docs

Page-cited retrieval for embedded docs, datasheets, and firmware references—exact facts for coding agents.

What is the ai.byteask/embedded-docs MCP server?

The ByteAsk Embedded MCP server is a source-grounded, page-cited evidence-retrieval system for coding agents that need exact facts from embedded and firmware reference documentation. It returns verbatim snippets with page citations from datasheets, MISRA standards, CMSIS, RTOS references, and other technical specs, and returns "no match" rather than fabricate when uncertain. The server supports both local stdio and remote Streamable HTTP transports, with a pluggable retrieval backend.

ByteAsk Embedded MCP provides coding agents (Claude Code, Cursor, Codex) with reliable, cited answers from embedded systems documentation. Instead of relying on hallucinated register values, Modbus codes, or SCPI commands, agents can search a corpus of datasheets, protocol specs, and standards and receive verbatim source text with precise page citations. It's built for firmware, driver, and protocol development where accuracy is non-negotiable.

How to install ai.byteask/embedded-docs

Copy-paste configuration for popular MCP clients.

transport: http
Config generated by PluginBench — verify against the source before use.
~/.cursor/mcp.json
{
  "mcpServers": {
    "embedded-docs": {
      "url": "https://mcp.byteask.ai/mcp"
    }
  }
}

Tools & capabilities

Tools this server exposes to the agent.

  • search_docs — Search the corpus with natural language or exact identifiers; returns ranked, page-cited evidence with document title, section, page citation, verbatim snippet, and result_id. Returns "no confident match" rather than fabricate.
  • get_context — Expand a search result to its full source section for deeper context.
  • request_document — Submit a request for a missing document to be added to the corpus (logged server-side).

Use cases

  • Look up exact register offsets and bit fields from MCU datasheets while writing firmware drivers
  • Find the correct Modbus function code and parameter format for protocol implementations
  • Retrieve MISRA C rule citations and compliance thresholds during code review
  • Search CMSIS and RTOS API signatures and configuration parameters
  • Verify SCPI command syntax and IEEE standard clause references in test automation

ai.byteask/embedded-docs MCP server FAQ

What is the ByteAsk Embedded MCP server?

It's an MCP server that retrieves exact, page-cited facts from embedded systems documentation (datasheets, standards, protocols) for coding agents. Every answer is verbatim source text with a citation; if nothing matches, it says "no match" instead of guessing.

Is it free to use?

The hosted server at https://mcp.byteask.ai/mcp is available for use. The open-source server code in this repo is MIT-licensed and runs locally with a sample backend out of the box; the full licensed corpus is behind the hosted endpoint.

How do I use it in Cursor or Claude?

For Cursor, click the badge in the README to install via deeplink. For Claude Code, run `claude mcp add --transport http byteask-embedded-docs https://mcp.byteask.ai/mcp`. For local use, clone the repo and run `uv run byteask-embedded-mcp`.

Do I need an API key or authentication?

The hosted endpoint at mcp.byteask.ai/mcp requires no API key. If you run the server locally with HTTP, you can optionally set a bearer token via MCP_HTTP_AUTH_TOKEN; the default sample backend requires no setup.

What documents are included?

The bundled sample backend includes a few illustrative public-knowledge records. The hosted server is backed by a full licensed corpus of embedded systems datasheets, MISRA standards, CMSIS, RTOS references, and protocol specifications.

Can I plug in my own document corpus?

Yes. The server depends on a two-method SearchBackend interface (search and get_context). Implement it in your own package and point BYTEASK_BACKEND to your factory function to use custom retrieval and documents.

README (reference)

Source of truth, from the repository.

<div align="center">

ByteAsk Embedded MCP

Page-cited answers from embedded & firmware reference docs — for coding agents that can't afford to guess a register value.

smithery badge License: MIT Python 3.10+ Model Context Protocol Status: beta PRs welcome Hosted

Official MCP Registry Namespace: ai.byteask/embedded-docs · Remote MCP Endpoint: https://mcp.byteask.ai/mcp

Quickstart · Tools · Connect a client · Configuration · Hosted server · Contributing

<img src="assets/demo.gif" alt="A coding agent reaches for ETH_DMATDLAR from memory; byteask reads the corpus and the line snaps to the cited ETH_DMACTXDLAR with a page citation." width="820"> </div>

ByteAsk Embedded MCP is the open-source server behind ByteAsk Embedded Docs: a source-grounded, page-cited evidence-retrieval MCP server for coding agents (Claude Code, Codex, Cursor) that write firmware / driver / protocol code and need exact facts — SunSpec points, register offsets, Modbus function codes, trip thresholds, SCPI commands, API symbols.

It returns verbatim snippets with page citations — never an authored answer — and when nothing is relevant enough it says no match rather than fabricate. Every document is treated equally: no authority layer, no filters.

[!NOTE] What's in this repo: the MCP server — tools, transports (stdio + Streamable HTTP), bearer auth, DNS-rebinding protection, result rendering — plus a small, pluggable retrieval interface.

What's not in this repo: the retrieval engine and the document corpus. How documents are parsed, chunked, embedded, and ranked, and the licensed source material itself, sit behind the SearchBackend seam and power the hosted endpoint at https://mcp.byteask.ai/mcp. This repo ships an in-memory SampleBackend (a few illustrative, public-knowledge records) so the server runs out of the box.

Why

  • Cited, or nothing. Every hit is verbatim source text with a section + page citation. On a miss it returns an honest "no confident match" — it never invents a register value.
  • Built for coding agents. The tool descriptions and triggers are tuned so agents call search_docs reflexively the moment they see a hex literal, a Modbus code, an IEEE clause, a SCPI verb, or an MCU part number — before answering from memory.
  • Two transports, one server. stdio for local agents, Streamable HTTP for hosted.
  • Bring your own retrieval. The search engine is a two-method interface — swap in anything behind BYTEASK_BACKEND without touching the server.
  • Zero-setup demo. The bundled SampleBackend runs immediately. No API keys.

Quickstart

Requires Python ≥ 3.10 and uv.

uv sync
uv run byteask-embedded-mcp        # run as an MCP server (stdio)

That's it — the bundled SampleBackend serves a couple of illustrative records, so search_docs works immediately. Run the offline tests with uv run pytest.

Connect a client

Hosted (no install)

The hosted server speaks Streamable HTTP at https://mcp.byteask.ai/mcp and is backed by the full licensed corpus.

Add to Cursor

Claude Code:

claude mcp add --transport http byteask-embedded-docs https://mcp.byteask.ai/mcp
<details> <summary><strong>Codex, Cursor, and other clients (mcp-remote)</strong></summary>
{
  "mcpServers": {
    "byteask-embedded-docs": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://mcp.byteask.ai/mcp"]
    }
  }
}
</details>

Local (this repo)

The project-scoped .mcp.json registers the stdio server for clients that read it. Manually, for Claude Code:

claude mcp add byteask-embedded-docs -- uv run byteask-embedded-mcp

Tools

Input is natural language (or an exact identifier). Output is compact markdown.

ToolWhat it does
search_docs(query, limit=8)Search the corpus; return ranked, page-cited evidence. Each hit has a document title, a section + page citation, the verbatim snippet, and a result_id. A "no confident match" response means not found — do not fabricate.
get_context(result_id)Expand a hit to its full source section.
request_document(request)Ask for a missing document to be added (logged server-side).

Example output:

## Results for "what Modbus function code writes multiple registers"

### Sample — Modbus Application Protocol (illustrative) — §6.12, p.30
> Function code 16 (0x10), Write Multiple Registers, writes a block of contiguous
> holding registers (1 to 123 registers) in a remote device. ...
_ref: sample:modbus-fc16_

Plug in your own retrieval

The server depends only on a two-method interface (backend.py):

class SearchBackend(Protocol):
    def search(self, query, limit=8, effort=None) -> dict: ...
    def get_context(self, result_id, effort=None) -> dict: ...

Implement it, expose a factory make_backend(config) -> SearchBackend, and point the server at it:

BYTEASK_BACKEND="my_pkg.my_module:make_backend"

The exact return-value contracts are documented at the top of backend.py.

Configuration

All settings are environment variables (loaded from .env; see .env.example).

VariableDefaultNotes
BYTEASK_BACKEND—module:callable returning a SearchBackend; empty → SampleBackend
BYTEASK_LOGSlogswhere query / request JSONL logs are written
MCP_TRANSPORTstdiostdio (local agents) or http
MCP_HTTP_HOST / MCP_HTTP_PORT127.0.0.1 / 8000HTTP bind address
MCP_HTTP_AUTH_TOKEN—bearer token for HTTP (empty = unauthenticated, dev only)
MCP_ALLOWED_HOSTS—comma-separated hosts allowed in the Host header (* disables)
LOG_LEVELINFOstderr log verbosity
<details> <summary><strong>Running over HTTP</strong></summary>
MCP_TRANSPORT=http MCP_HTTP_AUTH_TOKEN=$(openssl rand -hex 32) \
  uv run byteask-embedded-mcp --host 0.0.0.0 --port 8000

Clients then send Authorization: Bearer <token>. The bundled bearer check is a shared-secret stub — replace it with real auth (OAuth 2.1 resource server, mTLS, or a trusted reverse proxy) before exposing publicly. DNS-rebinding protection stays on independently via MCP_ALLOWED_HOSTS.

</details>

Hosted server

You don't need to run anything to use ByteAsk Embedded Docs. The hosted server gives Claude Code, Codex, Cursor, and any MCP client exact, page-cited facts from embedded and firmware reference docs — register maps, protocol function codes, SCPI commands, standard thresholds, datasheet specs. The guarantee: verbatim source, or "no match" — never an invented value.

Namebyteask-embedded-docs
Endpointhttps://mcp.byteask.ai/mcp (Streamable HTTP)
Docs & per-client setuphttps://docs.byteask.ai/embedded

This repository is the open-source server that powers that endpoint.

Project layout

src/byteask_embedded_mcp/
  server.py     # FastMCP app + 3 tools (search_docs, get_context, request_document)
  backend.py    # SearchBackend protocol + in-memory SampleBackend (swap for real retrieval)
  render.py     # structured result -> compact markdown
  http_auth.py  # Streamable HTTP entrypoint + stub bearer-token guard
  config.py     # server config (transport, logging, backend selection)
  schemas.py    # Hit / Section result types
  obs.py        # per-call JSONL logging
tests/          # offline unit tests (renderer, backend, server tools)
assets/         # README demo GIF + its deterministic generator

Security

  • stdout stays clean in stdio mode (it is the JSON-RPC channel); all logs go to stderr / logs/*.jsonl.
  • The HTTP bearer check is a stub — unauthenticated if no token is set, a shared secret at best. Harden it before exposing widely.
  • DNS-rebinding protection is on by default for the HTTP transport.

Contributing

PRs and issues are welcome.

uv sync            # install (incl. dev tools)
uv run pytest      # run the offline test suite

A few conventions to keep the server clean:

  • The backend seam is the extension point. Retrieval internals (parsing, chunking, embeddings, ranking) are intentionally out of scope here — build them behind SearchBackend in your own package, not in this repo.
  • Keep the dependency surface small and the stdio path free of the HTTP stack.
  • Add a test for new behavior; the suite is fully offline (no network, no keys).

License

MIT © ByteAsk

Related MCP servers

Hunt zero-days by talking to binaries. 40+ tools. Hosted, OAuth + SSO, invite: hi@byteray.ai

US equity data for AI agents — 23 years intraday + daily, SEC filings. x402 USDC payments.

1
Python
MIT
View repository →

The website platform for AI agents. One API to build, host, and operate real websites.

CACalaf logo

Calaf

Maintained

Run your Calaf recruiting book from chat: firms, people, pipeline, calendar, notes, and prep.

0
View repository →
CACalaf Seed Tools logo

Author and validate Calaf workspace seeds against the app's real importer. No account needed.

0
View repository →
CACalendarMCP logo

Hosted Google Calendar MCP server for AI agents. No self-hosting or Google Cloud setup.

0
View repository →