Mcp-RtfmSAFE
Ever been told to RTFM only to find there is no FM to R? MCP-RTFM helps you CREATE the F*ing Manual that people keep telling everyone to read! Transform your non-existent or unreadable docs into an intelligent, searchable knowledge base that actually answers those 'basic questions' before they're as
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://www.typescriptlang.org/) [](https://github.com/modelcontextprotocol) [](https://opensource.org/licenses/MIT)
"RTFM!" they say, but what if there's no FM to R? 🤔 Enter MCP-RTFM: an MCP server that helps you create the F*ing Manual everyone keeps telling people to read! Using advanced content analysis, metadata generation, and intelligent search capabilities, it transforms your non-existent or unreadable docs into an interconnected knowledge base that actually answers those "basic questions" before they're asked.
Plot twist: Instead of just telling people to RTFM, now you can actually give them an FM worth R-ing! Because the best response to "read the f*ing manual" is having a manual that's actually worth reading. 📚✨
📚 Table of Contents
- Quick Start
- Features
- Example Workflows
- Installation
- Advanced Features
- Development
- Debugging
🚀 Quick Start
# Install dependencies
npm install
# Build the server
npm run build
# Add to your MCP settings and start using
await use_mcp_tool({
server: "mcp-rtfm",
tool: "analyze_project_with_metadata", // Enhanced initialization
args: { projectPath: "/path/to/project" }
});
// This will:
// 1. Create documentation structure
// 2. Analyze content with unified/remark
// 3. Generate intelligent metadata
// 4. Build search index with minisearch
// 5. Add structured front matter
// 6. Make your docs actually readable!✨ Features
Documentation Management Tools
analyze_existing_docs- Analyze and enhance existing documentation with content analysis and metadataanalyze_project_with_metadata- Initialize documentation structure with enhanced
6393d4d0d516OBSERVED · 2026-10-08Connect
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 mcp-rtfm -- npx -y [email protected]
{
"mcpServers": {
"mcp-rtfm": {
"command": "npx",
"args": [
"-y",
"[email protected]"
]
}
}
}Exposed tools (11)
6 read · 5 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
analyze_existing_docs | read | Analyze existing documentation files with enhanced content analysis and metadata generation |
analyze_project | write | Analyze project structure and create initial documentation files |
analyze_project_with_metadata | write | Analyze project structure, create initial documentation files, and enhance with metadata/context |
customize_template | write | Create or update a custom documentation template |
get_doc_content | read | Get the current content of a documentation file |
get_project_info | read | Get information about the project structure and files |
get_related_docs | read | Find related documentation files based on metadata |
read_doc | read | Read a documentation file (required before updating) |
search_docs | read | Search across documentation files with highlighted results |
update_doc | write | Update a specific documentation file using diff-based changes |
update_metadata | write | Update metadata for a documentation file |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- declared (5 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (2)
minisearch, remark-parse, remark-stringify, unified, @types/node, typescript
Gates applied: no_behavioural_pass, no_license.
6393d4d0d516full audit observations/trust-audit/mcp-server/ryanjoachim__mcp-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 |
|---|---|---|---|---|---|
| 2026-10-08 | 6393d4d0d516 | SAFE | B | 89 | first audit |
Questions
What is the Mcp-Rtfm MCP server?
Ever been told to RTFM only to find there is no FM to R? MCP-RTFM helps you CREATE the F*ing Manual that people keep telling everyone to read! Transform your non-existent or unreadable docs into an intelligent, searchable knowledge base that actually answers those 'basic questions' before they're as
What tools does Mcp-Rtfm expose?
11 in total: 6 read-only, 5 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Mcp-Rtfm safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Mcp-Rtfm need?
No credential environment variables were found in its source, so it appears to need none.
How does Mcp-Rtfm run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as mcp-rtfm at 0.1.0.
How current is this page?
The grade is for one exact copy of the source (6393d4d0d516), read on 2026-10-08. The repository is watched and re-audited when it changes.