# embedded-docs (slim)

> embedded-docs, an MCP server by byteask.ai, listed from the official MCP registry. Indexed, not reviewed: facts and our own checks, no score or ranking. Page-cited retrieval for embedded docs, datasheets, MISRA, CMSIS, and RTOS references.

- Full: https://www.anchorterminal.com/tools/byteask-embedded-docs.md (~800 tokens) · this version ~730 tokens · JSON https://www.anchorterminal.com/tools/byteask-embedded-docs.json · canonical https://www.anchorterminal.com/tools/byteask-embedded-docs
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-05

# embedded-docs

> Indexed, not reviewed: facts from the official MCP registry and our own checks. No score, grade or rank, and not in the rankings until the panel reviews it. How the index works: https://www.anchorterminal.com/indexed/

- Kind: MCP server, by byteask.ai (https://docs.byteask.ai/embedded)
- Listed because: It's published in the registry under byteask.ai, a namespace the registry only gives to whoever proves they control that domain.
- What the official MCP registry says: Page-cited retrieval for embedded docs, datasheets, MISRA, CMSIS, and RTOS references.

## Facts

- MCP registry: `ai.byteask/embedded-docs` 1.0.1
- Endpoint: https://mcp.byteask.ai/mcp (streamable HTTP)
- Source: https://github.com/ByteAsk/ByteAsk-Embedded-MCP
- Website: https://docs.byteask.ai/embedded
- GitHub stars: 24
- Registry entry updated: 2026-06-19

## Tools

- Tools it lists (3, about 1,167 tokens of context, `tools/list` without credentials over MCP 2025-11-25, checked 2026-10-04 22:20 UTC):
  - `search_docs`: Search the indexed embedded / firmware / hardware reference corpus; return verbatim, page-cited evidence. The indexed corpus covers: grid-interconnection & DER…
  - `get_context`: Expand a previous search hit to its full verbatim section (markdown). Args: result_id: The id from a search_docs hit's `_ref:` line - the token inside the…
  - `request_document`: Request that a document be ADDED to the corpus - use this when search_docs returns 'no confident match' for material it should cover (a standard, protocol…
- How its tools read to an agent (0 errors, 6 warnings, 2 notes, about 1,167 tokens; rules at https://www.anchorterminal.com/check.md; not part of the score):
  - warn TC07 search_docs: the description is about 627 tokens
  - warn TC11 request_document: none of its 2 parameters has a description
  - warn TC11 search_docs: none of its 3 parameters has a description
  - warn TC16 get_context: no readOnlyHint or destructiveHint
  - warn TC16 request_document: no readOnlyHint or destructiveHint
  - warn TC16 search_docs: no readOnlyHint or destructiveHint
  - note TC11 get_context: parameters are documented in the description but not in the schema: effort, result_id
  - note TC29 server: about 94 tokens (7% of the definitions) are titles that repeat property or function names

- JSON: https://www.anchorterminal.com/api/v1/tools/byteask-embedded-docs.json
- Being indexed says nothing about quality, and nobody can pay for it. Ask for a review: https://www.anchorterminal.com/builders/#claiming