RagdocsSAFE
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://smithery.ai/server/@rahulretnan/mcp-ragdocs)
An MCP server implementation that provides tools for retrieving and processing documentation through vector search, enabling AI assistants to augment their responses with relevant documentation context.
Table of Contents
- Features
- Quick Start
- Docker Compose Setup
- Web Interface
- Configuration
- Cline Configuration
- Claude Desktop Configuration
- Acknowledgments
- Troubleshooting
Features
Tools
- search_documentation
- Search through the documentation using vector search
- Returns relevant chunks of documentation with source information
- list_sources
- List all available documentation sources
- Provides metadata about each source
- extract_urls
- Extract URLs from text and check if they're already in the documentation
- Useful for preventing duplicate documentation
- remove_documentation
- Remove documentation from a specific source
- Cleans up outdated or irrelevant documentation
- list_queue
- List all items in the processing queue
- Shows status of pending documentation processing
- run_queue
- Process all items in the queue
- Automatically adds new documentation to the vector store
- clear_queue
- Clear all items from the processing queue
- Useful for resetting the system
- add_documentation
- Add new documentation directly to the system by providing a URL
- Automatically fetches, processes, and indexes the content
- Supports various web page formats and extracts relevant content
- Chunks content intelligently for optimal retrieval
- Required parameter:
url(must include protocol, e.g.,
2cfd305d7880OBSERVED · 2026-10-07Connect
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. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add mcp-ragdocs --env OPENAI_API_KEY=${OPENAI_API_KEY} --env QDRANT_API_KEY=${QDRANT_API_KEY} -- npx -y @rahulretnan/[email protected]{
"mcpServers": {
"mcp-ragdocs": {
"command": "npx",
"args": [
"-y",
"@rahulretnan/[email protected]"
],
"env": {
"OPENAI_API_KEY": "${OPENAI_API_KEY}",
"QDRANT_API_KEY": "${QDRANT_API_KEY}"
}
}
}
}Exposed tools (14)
6 read · 5 write · 3 destructive. Blast radius: 3 tools can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.
| Tool | Risk | Description |
|---|---|---|
add_documentation | write | Add new documentation to the system by providing a URL. The tool will fetch the content, process it into chunks, and store it in the vector database for future searches. Supports various web page formats and automatically extracts relevant content. |
add_repository | write | Add a local code repository to the documentation system. This tool indexes all files in the repository according to the specified configuration, processes them into searchable chunks, and stores them in the vector database for future searches. |
clear_queue | destructive | Clear all URLs from the queue |
extract_urls | read | Extract all URLs from a given web page |
get_indexing_status | read | Get the current status of repository indexing operations. This tool provides detailed information about ongoing or completed indexing processes, including progress percentage, file counts, and timing information. |
list_queue | read | List all URLs currently in the documentation processing queue |
list_repositories | read | List all local repositories currently indexed in the system. Returns details about each repository including path, include/exclude patterns, and watch mode status. |
list_sources | read | List all documentation sources currently stored in the system. Returns a comprehensive list of all indexed documentation including source URLs, titles, and last update times. Use this to understand what documentation is available for searching or to verify if specific sources have been indexed. |
remove_documentation | destructive | Remove one or more documentation sources by their URLs |
remove_repository | destructive | Remove a repository from the system by its name. This removes both the repository configuration and all indexed documents from the vector database. |
run_queue | write | Process URLs from the queue one at a time until complete |
search_documentation | read | Search through stored documentation using natural language queries. Use this tool to find relevant information across all stored documentation sources. Returns matching excerpts with context, ranked by relevance. Useful for finding specific information, code examples, or related documentation. |
update_repository | write | Update an existing repository index. This re-processes all files in the repository according to the current configuration and updates the vector database. |
watch_repository | write | Start or stop watching a repository for changes. When watching is enabled, the system automatically detects file changes and updates the index accordingly. |
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 | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (1 observation(s))
- Network
- declared (5 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (3)
clear_queue, remove_documentation, remove_repository
return crypto.createHash('md5').update(content).digest('hex');axios, cors, express, file-type, glob, net, ollama, @types/cors
Gates applied: no_behavioural_pass.
2cfd305d7880full audit observations/trust-audit/mcp-server/rahulretnan__ragdocs-3.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 |
|---|---|---|---|---|---|
| 2026-10-07 | 2cfd305d7880 | SAFE | B | 89 | first audit |
Questions
What tools does Ragdocs expose?
14 in total: 6 read-only, 5 that write, and 3 that can delete or overwrite (clear_queue, remove_documentation, remove_repository). Every one is listed on this page with its risk.
Is Ragdocs 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. Separately from the audit: 3 of its tools can destroy data, so scope the token you give it to what you actually need.
What credentials does Ragdocs need?
It reads OPENAI_API_KEY and QDRANT_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Ragdocs run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as @rahulretnan/mcp-ragdocs at 1.0.0.
How current is this page?
The grade is for one exact copy of the source (2cfd305d7880), read on 2026-10-07. The repository is watched and re-audited when it changes.