RagdocsSAFE
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
A Model Context Protocol (MCP) server that enables semantic search and retrieval of documentation using a vector database (Qdrant). This server allows you to add documentation from URLs or local files and then search through them using natural language queries.
Quick Install Guide
- Install the package globally:
npm install -g @qpd-v/mcp-server-ragdocs
- Start Qdrant (using Docker):
docker run -p 6333:6333 -p 6334:6334 qdrant/qdrant
- Ensure Ollama is running with the default embedding model:
ollama pull nomic-embed-text
- Add to your configuration file:
- For Cline:
%AppData%\Roaming\Code\User\globalStorage\saoudrizwan.claude-dev\settings\cline_mcp_settings.json - For Roo-Code:
%AppData%\Roaming\Code\User\globalStorage\rooveterinaryinc.roo-cline\settings\cline_mcp_settings.json - For Claude Desktop:
%AppData%\Claude\claude_desktop_config.json
{
"mcpServers": {
"ragdocs": {
"command": "node",
"args": ["C:/Users/YOUR_USERNAME/AppData/Roaming/npm/node_modules/@qpd-v/mcp-server-ragdocs/build/index.js"],
"env": {
"QDRANT_URL": "http://127.0.0.1:6333",
"EMBEDDING_PROVIDER": "ollama",
"OLLAMA_URL": "http://localhost:11434"
}
}
}
}- Verify installation:
# Check Qdrant is running curl http://localhost:6333/collections # Check Ollama has the model ollama list | grep nomic-embed-text
Version
Current version: 0.1.6
Features
- Add documentation from URLs or local files
- Store documentation in a vector database for semantic search
- Search through documentation using natural language
- List all documentation sources
Installation
Install globally using npm:
npm install -g @qpd-v/mcp-server-ragdocs
This will install the server in your global npm directory, which you'll need for the configuration
bb3910155a07OBSERVED · 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-server-ragdocs --env OPENAI_API_KEY=${OPENAI_API_KEY} -- npx -y @qpd-v/[email protected]{
"mcpServers": {
"mcp-server-ragdocs": {
"command": "npx",
"args": [
"-y",
"@qpd-v/[email protected]"
],
"env": {
"OPENAI_API_KEY": "${OPENAI_API_KEY}"
}
}
}
}Exposed tools (4)
3 read · 1 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
add_documentation | write | Add documentation from a URL to the RAG database |
list_sources | read | List all documentation sources currently stored |
search_documentation | read | Search through stored documentation |
test_ollama | read | Test embeddings functionality |
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
- declared (1 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (6)
"QDRANT_URL": "http://127.0.0.1:6333",
"QDRANT_URL": "http://127.0.0.1:6333",
"QDRANT_URL": "http://127.0.0.1:6333",
"QDRANT_URL": "http://127.0.0.1:6333",
"QDRANT_URL": "http://127.0.0.1:6333",
@qdrant/js-client-rest, axios, cheerio, ollama, openai, playwright, @types/node, typescript
Gates applied: no_behavioural_pass.
bb3910155a07full audit observations/trust-audit/mcp-server/qpd-v__ragdocs-2.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 | bb3910155a07 | SAFE | B | 89 | first audit |
Questions
What tools does Ragdocs expose?
4 in total: 3 read-only, 1 that write, and 0 that can delete or overwrite. 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.
What credentials does Ragdocs need?
It reads OPENAI_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 @qpd-v/mcp-server-ragdocs at 0.1.6.
How current is this page?
The grade is for one exact copy of the source (bb3910155a07), read on 2026-10-07. The repository is watched and re-audited when it changes.