Loading…
Cognition's DeepWiki exposes AI-generated documentation and Q&A over public GitHub repositories through a public, no-auth remote endpoint.
Do not connect
The assessed surface is high-risk. Remediate the findings before connecting.
Scanned 1 month ago Due for re-check
A server can change after it's graded. Re-run the automated scan to refresh this report.
This grade is deterministic and reproducible: the same server surface always yields the same grade under a given algorithm version. It is a real automated assessment computed by the MCPGrade engine from what the probe actually observed — not a fabricated or opinion score. It is not a manual human pentest, so it can miss context-specific risks.
Every signal below was measured directly by the automated probe. The grade is derived only from evidence like this — nothing is assumed.
The DeepWiki MCP Server MCP server exposes 3 tools, focused primarily on general-purpose capabilities. It is categorised under Dev Tools and maintained by Cognition. Its published description reads: "Cognition's DeepWiki exposes AI-generated documentation and Q&A over public GitHub repositories through a public, no-auth remote endpoint". It communicates over Streamable HTTP using the 2025-06-18 protocol revision, and does not require authorization to connect. MCPGrade currently rates DeepWiki MCP Server D — the assessed surface is high-risk and should be remediated before use. Its most notable findings include "Unguarded destructive tools" and "Cross-tool shadowing". This report is a deterministic, reproducible automated assessment: the same observed surface always yields the same grade under a given algorithm version, and it is refreshed as new scans arrive and free to read — but it is not a substitute for a manual human security review. Always re-check DeepWiki MCP Server's advertised tools, transport security, and authorization posture before connecting an autonomous agent or sharing sensitive context with it.
Add DeepWiki MCP Server to an MCP client using the endpoint below. Review the grade and findings above before granting an autonomous agent access.
MCP endpoint
https://mcp.deepwiki.com/mcpStreamable HTTP transport. This is the MCP endpoint, not a website — paste it into your MCP client server list rather than a browser.
Captured passively during the read-only scan. Click any value to find servers that match it.
Sorted worst-first. Each finding shows its severity, what it means, its OWASP MCP Top-10 mapping, and a recommended fix — the check id links to the exact methodology row that produced it.
tool: (server instructions)
Tools that execute commands / write files / make arbitrary requests are exposed without annotations or guards.
create, update, delete notes, view folder structure, list/view/dismiss knowledge suggestiRecommendationAnnotate destructive tools and require human approval.
tool: (server instructions)
A tool description tries to alter the model’s use of another tool.
a repository - ask_question: Ask any question about a repository and get anRecommendationDescriptions must describe only their own tool.
The server accepts tool enumeration (and likely invocation) with no authentication.
RecommendationRequire OAuth 2.1 authorization for any server exposing non-public tools.
DeepWiki (from Cognition, makers of Devin) serves structured, AI-generated documentation and question-answering over public GitHub repositories. Its remote MCP endpoint is public and requires no authentication, which makes it a common first server to wire into a coding agent.
https://mcp.deepwiki.com/mcpA no-auth public server means anyone can enumerate its tools — exactly what a grade tells you.
Upstash's Context7 pulls version-specific, up-to-date library documentation and code examples straight into the model's context.
Financial data service providing fundamental information for 30,000+ listed companies across the US, Japan, and Korea, sourced directly from SEC, EDINET, and DART regulatory filings.
Search tours, attraction tickets, and holiday packages across 24 countries.
Agentic visitor analytics with five tools for CRO and session analysis.
52 paid x402 API endpoints for AI agents — crypto, data, DeFi, and market intelligence, settled on Base.