docmole

Docmole is an MCP server that helps AI assistants query documentation sites. It supports a local RAG mode (crawl docs, generate embeddings with OpenAI, store/search in LanceDB) and a Mintlify mode (proxy to Mintlify’s assistant API for certain Mintlify-powered documentation sites). It also provides a CLI to set up projects, serve/stop them, and list available projects.

Evaluated Mar 30, 2026 (21d ago)
Homepage ↗ Repo ↗ Ai Ml mcp documentation rag lancedb typescript bun mintlify ai-assistant-integration
⚙ Agent Friendliness
56
/ 100
Can an agent use this?
🔒 Security
54
/ 100
Is it safe for agents?
⚡ Reliability
30
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
78
Documentation
65
Error Messages
0
Auth Simplicity
85
Rate Limits
20

🔒 Security

TLS Enforcement
80
Auth Strength
55
Scope Granularity
20
Dep. Hygiene
55
Secret Handling
60

TLS is expected for external API calls (OpenAI/Mintlify), but HTTPS enforcement is not explicitly stated in the excerpt. Secrets are provided via environment variable (OPENAI_API_KEY), but there is no evidence here about logging hygiene, redaction, or secure storage. Scope granularity and access controls for the MCP server are not described. Dependency hygiene cannot be fully assessed from the provided dependency list alone.

⚡ Reliability

Uptime/SLA
0
Version Stability
45
Breaking Changes
40
Error Recovery
35
AF Security Reliability

Best When

You want to connect an MCP-capable assistant (Claude/Cursor/other MCP clients) to documentation search, either via self-hosted RAG or Mintlify proxy mode.

Avoid When

You cannot provide required secrets (e.g., OPENAI_API_KEY for local RAG mode) or you require strong, explicitly documented operational guarantees (SLA, idempotency semantics, structured retry behavior).

Use Cases

  • Ask questions against your documentation site(s) using an MCP-capable assistant
  • Build a private documentation search experience via self-hosted RAG (LanceDB + OpenAI embeddings)
  • Use zero-setup querying for Mintlify-powered documentation using an MCP client

Not For

  • Public, untrusted browsing use-cases where you cannot control or sandbox crawled/processed content
  • Use cases that require a documented HTTP REST/SDK interface (the primary interface is MCP + CLI)
  • Organizations needing guaranteed guarantees around rate limits, data residency, or compliance specifics (not stated in provided materials)

Interface

REST API
No
GraphQL
No
gRPC
No
MCP Server
Yes
SDK
No
Webhooks
No

Authentication

Methods: Environment variable OPENAI_API_KEY (local RAG mode embeddings)
OAuth: No Scopes: No

README specifies OPENAI_API_KEY is required for local RAG mode. Mintlify mode is described as proxying to Mintlify’s assistant API with 'no API key needed' (details of upstream auth/authorization not provided in the excerpt).

Pricing

Free tier: No
Requires CC: No

The npm package itself is MIT licensed; operational cost depends on upstream services (OpenAI embeddings in local mode; Mintlify API usage in Mintlify mode). No pricing tiers or free tier are stated in the provided materials.

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • MCP server is started via CLI (bunx docmole serve/args); ensure the MCP client uses the correct command/args per project id.
  • Local RAG mode requires OPENAI_API_KEY; missing/invalid keys will block embedding/indexing.
  • Mintlify mode depends on the upstream 'project-id' being recognized; if the project id is wrong or changes upstream, zero-setup behavior may fail.
  • Crawling/indexing happens during setup; long indexing may require operational patience and may not be incremental unless additional (not-yet-documented) features are enabled.

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for docmole.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-03-30.

8642
Packages Evaluated
17761
Need Evaluation
586
Need Re-evaluation
Community Powered