Loading ToolBench

Reading the current corpus…

DeepWiki MCP server · C · ToolBench

← Browse

DeepWiki

mcp.deepwiki.com/mcp

Repository documentation and wiki

Being assessedSTREAMABLE_HTTP3 tools

67/100

Definition Quality72

Protocol Readiness100

Security25

Supportability50

Spec posture

Being assessed against 2026-07-28·last reported 2025-11-25

Live V2 assessment pending · evidence: Streamable HTTP

Being assessed

Summary

Well-curated 3-tool set with clear, focused purpose. Strong naming and schema design with typed parameters. Descriptions are adequate but could be more detailed about use cases and when to invoke each tool. The ask_question tool demonstrates sophisticated parameter handling (single repo or array of up to 10). No auto-generation patterns detected.

Tools (3)

ask_questionsource verified87/100

Ask any question about a GitHub repository and get an AI-powered, context-grounded response. Args: repoName: GitHub repository or list of repositories (max 10) in owner/repo format question: The question to ask about the repository

read_wiki_contentssource verified80/100

View documentation about a GitHub repository. Args: repoName: GitHub repository in owner/repo format (e.g. "facebook/react")

read_wiki_structuresource verified82/100

Get a list of documentation topics for a GitHub repository. Args: repoName: GitHub repository in owner/repo format (e.g. "facebook/react")

Issues (2)

MEDIUM

read_wiki_structure and read_wiki_contents have overlapping names and unclear differentiation. Documentation doesn't explain when to use 'structure' vs 'contents'.

read_wiki_structureread_wiki_contents

MEDIUM

Descriptions lack detail about output format and when an agent should prefer ask_question over direct wiki reading.

read_wiki_structureread_wiki_contentsask_question

Recommendations

Clarify in read_wiki_structure description: 'Returns a hierarchical list/tree of documentation topics and sections without content'
Clarify in read_wiki_contents description: 'Returns full markdown content of all documentation pages for browsing'
Add to ask_question description: 'Use for semantic queries and context-aware answers. Faster than reading all docs when seeking specific information'
Specify max lengths for repoName and question parameters to guide agent token usage
Document error handling: what happens when repoName doesn't exist or has no wiki?

Score history

Overall score trend

First recorded score · v1 rubric

67/100

Scored	Grade	Overall	Spec posture	Rubric
2026-03-24	C	67	2025-11-25	v1