{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_dr84246av7d8","handle":"iflow-mcp-michaelayles-mcp-embedded-docs","url":"https://wellknown.network/agents/iflow-mcp-michaelayles-mcp-embedded-docs","links":{"self":"https://wellknown.network/agents/iflow-mcp-michaelayles-mcp-embedded-docs/record.json","html":"https://wellknown.network/agents/iflow-mcp-michaelayles-mcp-embedded-docs","markdown":"https://wellknown.network/agents/iflow-mcp-michaelayles-mcp-embedded-docs/record.md","api":"https://wellknown.network/api/v1/agents/iflow-mcp-michaelayles-mcp-embedded-docs","status":"https://wellknown.network/api/v1/agents/iflow-mcp-michaelayles-mcp-embedded-docs/status","claim":"https://wellknown.network/agents/iflow-mcp-michaelayles-mcp-embedded-docs/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/iflow-mcp-michaelayles-mcp-embedded-docs/claim.json","badge":"https://wellknown.network/agents/iflow-mcp-michaelayles-mcp-embedded-docs/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/iflow-mcp-michaelayles-mcp-embedded-docs/history","tools":"https://wellknown.network/api/v1/agents/iflow-mcp-michaelayles-mcp-embedded-docs/tools"},"ard":{"identifier":"urn:air::server:iflow-mcp-michaelayles-mcp-embedded-docs","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"iflow-mcp_michaelayles-mcp-embedded-docs","summary":"MCP server for embedded systems documentation","description":"# bitwise-mcp\n\nMCP server for embedded developers. Ingests PDF reference manuals (1000+ pages), extracts register definitions, and provides fast semantic search.\n\n## Features\n\n- **PDF Ingestion** - Parses large reference manuals preserving structure\n- **Register Table Extraction** - Detects and converts register definitions to structured JSON\n- **Hybrid Search** - Combines keyword matching (SQLite FTS5) with semantic similarity (FAISS)\n- **Compact Output** - Formats responses to minimize token usage\n\n## Installation\n\n```bash\npoetry install\n\n# Add to Claude Code\nclaude mcp add embedded-docs --command poetry --args \"run\" \"mcp-embedded-docs\" \"serve\" --cwd \"<path-to-this-repo>\"\n```\n\nRestart Claude Code after adding the server.\n\n## Usage\n\nPlace PDFs in a `docs/` directory, then in Claude Code:\n\n```\nWhat PDFs are available?\nIngest any files that haven't been ingested yet\nWhat's the base address for FlexCAN0?\n```\n\n### Example: Checking Available PDFs\n\n![Listing available PDFs](images/Screenshot%20(10).PNG)\n\n### Example: Searching Documentation\n\nThe MCP server automatically queries the indexed documentation when you ask questions:\n\n![Documentation search in action](images/Screenshot%20(11).PNG)\n\n### CLI Usage\n\nOr use CLI directly:\n\n```bash\npoetry run mcp-embedded-docs ingest docs/manual.pdf --title \"MCU Manual\"\npoetry run mcp-embedded-docs list  # View indexed documents\n```\n\n## MCP Tools\n\n- **search_docs** - Search documentation with hybrid retrieval\n- **find_register** - Find specific register definitions\n- **list_docs** - List all documentation files with status (indexed + available)\n- **ingest_docs** - Ingest documentation files into the search index\n- **remove_docs** - Remove documents from the search index by ID\n\n## Tech Stack\n\nPython 3.10+ • PyMuPDF • pdfplumber • sentence-transformers • FAISS • SQLite FTS5\n\n## Performance\n\n**Tested:** S32K144 Reference Manual (2,179 pages, 14MB)\n**Results:** 3min indexing, <500ms search, ~500MB memory\n\n## License\n\n[MIT](LICENSE)","publisher":{"name":"Your Name","url":null},"homepage":null,"repository":null,"version":"0.1.0","license":null,"protocols":["mcp"],"tags":["mcp"],"pricing":null,"endpoints":[{"url":"pypi:iflow-mcp_michaelayles-mcp-embedded-docs","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","summary":"pypi","version":"pypi","description":"pypi","publisherName":"pypi"}},"derived":{"capabilities":[{"slug":"dev.docs-lookup","name":"Documentation Lookup","confidence":1,"provenance":"derived"},{"slug":"dev.filesystem","name":"Filesystem","confidence":0.802,"provenance":"derived"}],"categories":["dev"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"iflow-mcp_michaelayles-mcp-embedded-docs","registry":"pypi","observedAt":"2026-09-15T19:23:17.071Z","publishedAt":"2026-01-04T04:05:13.924514Z","latestVersion":"0.1.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"iflow-mcp_michaelayles-mcp-embedded-docs","url":"https://pypi.org/project/iflow-mcp_michaelayles-mcp-embedded-docs/","firstSeenAt":"2026-09-09T20:24:10.140Z","fetchedAt":"2026-09-15T19:21:45.428Z","normalizedAt":"2026-09-15T19:21:45.428Z"}]},"firstSeenAt":"2026-09-09T20:24:10.140Z","updatedAt":"2026-09-15T19:23:17.071Z"}