deepwiki-mcp

An MCP server that takes a Deepwiki URL, crawls Deepwiki pages under deepwiki.com, sanitizes/rewrites the HTML into Markdown, and returns either a single aggregated Markdown document or per-page Markdown/structured output. It also provides an HTTP transport mode via localhost.

Evaluated Mar 30, 2026 (21d ago)

Repo ↗ DevTools mcp web-scraping documentation markdown crawler typescript cursor-mcp

⚙ Agent Friendliness

/ 100

Can an agent use this?

🔒 Security

/ 100

Is it safe for agents?

⚡ Reliability

/ 100

Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality

Documentation

Error Messages

Auth Simplicity

100

Rate Limits

🔒 Security

TLS Enforcement

Auth Strength

Scope Granularity

Dep. Hygiene

Secret Handling

README indicates domain safety (only deepwiki.com) and HTML sanitization (strips headers/footers/navigation/scripts/ads) plus robots parsing mentioned in deps list. However, no auth is documented for the MCP/HTTP interfaces, and no rate limiting or abuse protections are described. TLS is not explicitly guaranteed; HTTP transport example uses http://localhost:3000 (likely fine for local dev, but not documented for external deployment).

⚡ Reliability

Uptime/SLA

Version Stability

Breaking Changes

Error Recovery

Best When

You want to provide an MCP-capable coding assistant a reliable way to transform Deepwiki documentation into Markdown for downstream reasoning.

Avoid When

You need formal API specs/SDKs, strong authentication, or documented rate-limit behavior; or you require operation over sites/domains other than deepwiki.com.

Use Cases

• Ingest Deepwiki documentation into an LLM-friendly Markdown form
• Let an editor/agent (Cursor, MCP clients) fetch and crawl a Deepwiki repo’s pages
• Generate a single contextual document for Q&A over multiple Deepwiki pages
• Search/understand a library by crawling relevant pages

Not For

• Fetching content from domains other than deepwiki.com
• High-assurance scraping/compliance workflows where you need strict contractual guarantees
• Use as a general web crawler or arbitrary URL fetcher

Interface

REST API

Yes

GraphQL

gRPC

MCP Server

Yes

SDK

Webhooks

Authentication

OAuth: No Scopes: No

No authentication mechanism is described for either MCP or the provided HTTP transport example.

Pricing

Free tier: No

Requires CC: No

Repository appears MIT-licensed; pricing is not described for any hosted service (this is presented as an MCP server you run/install).

Agent Metadata

Pagination

none

Idempotent

False

Retry Guidance

Not documented

Known Gotchas

⚠ README warns the server may not work because DeepWiki blocks scraping; agent workflows may fail intermittently.
⚠ The tool is domain-restricted to deepwiki.com; requests to other domains should be rejected.
⚠ Large repositories can hit timeouts; concurrency and timeout are configurable via env vars.
⚠ Progress events are emitted during crawling; agents should handle streaming/progress without assuming final output arrives immediately.

Alternatives

Use the official Deepwiki MCP server (referenced in README as available via devin.ai documentation) Use a custom scraper + HTML-to-Markdown pipeline you control (with your own allowlist and robots handling) Manually copy/curate Deepwiki content into Markdown for your specific use case

Full Evaluation Report

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

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

Score Monitoring

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

Continuous monitoring

$3/mo

API endpoint ↗ Agent guide ↗ Report inaccuracy

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