RTFMCAUTION
The open retrieval layer for AI coding agents. Indexes code, docs, legal, research, data — 22 parsers (incl. EPUB, DOCX, ODT), FTS5 + semantic search, knowledge graph. Serves surgical context via MCP. Open source, local, free.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
*Retrieve The Forgotten Memory*
The open retrieval layer your AI agent was missing
Index everything in your project — code, docs, PDFs, legal texts, research, data — and your agent finds the right context instantly. No hallucinations. No cloud. No API costs.
`Free · Local · Open Source · MIT`
[](https://pypi.org/project/rtfm-ai/) [](https://opensource.org/licenses/MIT) [](https://www.python.org/) [](https://modelcontextprotocol.io/) [](https://claude.ai/claude-code) [](https://github.com/roomi-fields/rtfm)
The problem
Your AI agent is flying blind.
It greps through thousands of files, misses the doc that answers the question, invents modules that don't exist, forgets what you decided last session. The bigger the project, the worse it gets. You've added a smarter model. It didn't help. Because the bottleneck isn't intelligence — it's retrieval.
Code indexers (Augment, Sourcegraph, Cursor) only see code. But your project isn't just code. It's specs, PRs, architecture decisions, research papers, PDFs, regulations, vault notes — the context your agent needs to stop guessing.
Why I built this
I was writing a French tax article (~50 pages of regulatory text, cross-references between code articles, case law, administrative doctrine). Claude Code kept grep-ing the same directories in loops, running out of
9a0042857546OBSERVED · 2026-10-10Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add rtfm-ai -- None rtfm-ai==0.52.0
Exposed tools (8)
8 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
rtfm_books | read | List indexed books with per-corpus summary and pagination. |
rtfm_context | read | Get sources relevant to a subject. Returns paths + line ranges, |
rtfm_coverage | read | How much of a project this index actually holds. |
rtfm_discover | read | Scan a project directory and return a structural map (file types, |
rtfm_expand | read | Read content of an indexed file with line numbers. |
rtfm_graph | read | Show graph neighbors of a file (imports, links, includes, citations). |
rtfm_history | read | Show version history of an indexed file, or retrieve a specific version. |
rtfm_search | read | Search the indexed knowledge base. Returns ranked source paths |
Trust audit
CAUTIONgrade B · trust 84/100 Install with care. The audit found things worth knowing before you trust its output.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | WARN |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (1 observation(s))
- Network
- none-observed
- Shell
- declared (2 observation(s))
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (9)
__import__(mod)
__import__(mod)
h = hashlib.md5()
h = hashlib.md5()
return hashlib.md5(text.encode()).hexdigest()[:12]
return hashlib.md5(text.encode()).hexdigest()[:12]
return hashlib.md5(text.encode()).hexdigest()[:12]
_write(tmp_path, "vendor/lib/.git", "gitdir: ../../.git/modules/lib\n")
`bin/rtfm-serve` already injected the plugin's extras venv (`~/.claude/plugins/data/rtfm/extras/venv`) into `sys.path` so the MCP server could import `pdftext`, `ebooklib`, `openpyxl`, `fastembed`, et
Gates applied: no_behavioural_pass.
9a0042857546full audit observations/trust-audit/mcp-server/roomi-fields__rtfm.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-10 | 9a0042857546 | CAUTION | B | 84 | first audit |
Questions
What is the RTFM MCP server?
The open retrieval layer for AI coding agents. Indexes code, docs, legal, research, data — 22 parsers (incl. EPUB, DOCX, ODT), FTS5 + semantic search, knowledge graph. Serves surgical context via MCP. Open source, local, free.
What tools does RTFM expose?
8 in total: 8 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is RTFM safe to connect to an agent?
With care. The audit graded it B (84/100) and found 9 things worth knowing before you trust this server, listed below with the exact line each was found on.
What credentials does RTFM need?
No credential environment variables were found in its source, so it appears to need none.
How does RTFM run?
It speaks stdio, so it runs as a local process your client starts. It is published on PyPI as rtfm-ai.
How current is this page?
The grade is for one exact copy of the source (9a0042857546), read on 2026-10-10. The repository is watched and re-audited when it changes.