Skip to content

plurigrid/asi / ies/music-topos/.codex/skills/deepwiki-mcp

deepwiki-mcp

Verified

DeepWiki MCP server for AI-powered GitHub repository documentation and Q&A

DeepWiki MCP Skill

AI-powered documentation and Q&A for any public GitHub repository

Version: 1.0.0 Trit: 0 (Ergodic - coordinates knowledge retrieval) Bundle: research Provider: Cognition (Devin AI) - Official, Free, No Auth Required

Overview

DeepWiki MCP provides programmatic access to AI-generated documentation for any public GitHub repository indexed on DeepWiki.com. It enables:

  1. Wiki Structure: Get table of contents for any repo's documentation
  2. Wiki Contents: Read AI-generated documentation for specific topics
  3. Ask Questions: Get AI-powered answers grounded in repository context

Server Configuration

Base URL

https://mcp.deepwiki.com/

Wire Protocols

ProtocolURLBest For
SSEhttps://mcp.deepwiki.com/sseClaude, most clients
Streamable HTTPhttps://mcp.deepwiki.com/mcpOpenAI, Cloudflare, Amp

Tools

1. read_wiki_structure

Get the documentation topic tree for a GitHub repository.

{
  "tool": "read_wiki_structure",
  "params": {
    "repo_owner": "AlgebraicJulia",
    "repo_name": "ACSets.jl"
  }
}

Returns: List of documentation topics/sections

2. read_wiki_contents

Read documentation for a specific topic.

{
  "tool": "read_wiki_contents",
  "params": {
    "repo_owner": "AlgebraicJulia",
    "repo_name": "ACSets.jl",
    "topic": "Overview"
  }
}

Returns: AI-generated documentation content

3. ask_question

Ask any question about a repository with AI-powered, context-grounded response.

{
  "tool": "ask_question",
  "params": {
    "repo_owner": "AlgebraicJulia",
    "repo_name": "Catlab.jl",
    "question": "How do wiring diagrams compose?"
  }
}

Returns: AI-powered answer with repository context

Client Configuration

Amp / Codex (.mcp.json)

{
  "mcpServers": {
    "deepwiki": {
      "serverUrl": "https://mcp.deepwiki.com/mcp"
    }
  }
}

Claude Desktop

{
  "mcpServers": {
    "deepwiki": {
      "serverUrl": "https://mcp.deepwiki.com/sse"
    }
  }
}

Claude Code (CLI)

claude mcp add -s user -t http deepwiki https://mcp.deepwiki.com/mcp

Cursor / Windsurf

Add to .cursor/mcp.json:

{
  "mcpServers": {
    "deepwiki": {
      "serverUrl": "https://mcp.deepwiki.com/sse"
    }
  }
}

GF(3) Triad Integration

TritSkillRole
-1hatchery-papersValidates academic sources
0deepwiki-mcpCoordinates repo knowledge
+1bmorphism-starsGenerates from starred repos

Conservation: (-1) + (0) + (+1) = 0 ✓

Additional Triads

hatchery-papers (-1) ⊗ deepwiki-mcp (0) ⊗ bmorphism-stars (+1) = 0 ✓  [Research]
persistent-homology (-1) ⊗ deepwiki-mcp (0) ⊗ gay-mcp (+1) = 0 ✓  [Documentation]
sheaf-cohomology (-1) ⊗ deepwiki-mcp (0) ⊗ topos-generate (+1) = 0 ✓  [Knowledge]
three-match (-1) ⊗ deepwiki-mcp (0) ⊗ cider-clojure (+1) = 0 ✓  [Clojure Repos]
polyglot-spi (-1) ⊗ deepwiki-mcp (0) ⊗ gay-mcp (+1) = 0 ✓  [Cross-Lang Docs]

Use Cases

1. Understand New Libraries

"Read the documentation structure for react/react and explain the hooks system"

2. Answer Technical Questions

"How does Catlab.jl implement natural transformations?"

3. Compare Implementations

"Compare how ACSets.jl and Catlab.jl handle graph homomorphisms"

4. Explore Category Theory Libraries

"What topics are covered in AlgebraicJulia/AlgebraicDynamics.jl documentation?"

Indexing Your Repository

To make your public GitHub repo available via DeepWiki MCP:

  1. Visit DeepWiki.com
  2. Enter your repository URL
  3. Wait for indexing to complete
  4. Add the DeepWiki badge to your README:
[![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/owner/repo)

Related Resources

ACSet Skill Integration

Both deepwiki-mcp and acsets-algebraic-databases are ERGODIC (trit 0) — they substitute for each other in triads and coordinate knowledge transport.

Qualified Workflow

Phasedeepwiki-mcpacsets skillVerification
Discoveryread_wiki_structureSchema patterns✓ Catlab.jl has 16 topic pages
Q&Aask_questionFormal definitions✓ ACSet = Functor C → Set confirmed
ApplyCode examplesSpecter navigation✓ oapply documented in Catlab
Debug"Why does X fail?"Check naturality✓ HomSearch uses BacktrackingSearch

Verified DeepWiki ↔ ACSets Correspondence

From DeepWiki ask_question("AlgebraicJulia/Catlab.jl", "How do ACSets work..."):

DeepWiki ResponseACSets SkillMatch
"ACSet represents a functor from schema to Set"C-set = Functor X: C → Set✓
"ACSetFunctor wraps ACSet for functorial view"∫G category of elements✓
"BacktrackingSearch (CSP-based, MRV heuristic)"homomorphisms(G, complete_graph(k))✓
"VMSearch (compiled virtual machine)"Specter zero-overhead navigation✓

Repository Indexing Status (Verified 2025-12-22)

RepositoryDeepWiki StatusTopics
AlgebraicJulia/Catlab.jl✅ Indexed16 pages (GATs, CSets, HomSearch, WiringDiagrams...)
AlgebraicJulia/ACSets.jl❌ Needs indexingVisit https://deepwiki.com/AlgebraicJulia/ACSets.jl
AlgebraicJulia/AlgebraicDynamics.jl❌ Needs indexingVisit https://deepwiki.com/AlgebraicJulia/AlgebraicDynamics.jl
AlgebraicJulia/StructuredDecompositions.jl❌ Needs indexingVisit https://deepwiki.com/AlgebraicJulia/StructuredDecompositions.jl
redplanetlabs/agent-o-rama✅ Indexed28 pages (Rama PStates, Agent Topologies, Tool Calling...)
discopy/discopy✅ Indexed23 pages (Monoidal Categories, Quantum Circuits, QNLP...)

Cross-Skill Examples

Example 1: ACSets + Catlab.jl

# 1. Query DeepWiki for oapply semantics
mcp__deepwiki__ask_question("AlgebraicJulia/Catlab.jl", 
  "How does oapply compose undirected wiring diagrams?")

# 2. Apply via ACSets skill patterns
@present SchUWD(FreeSchema) begin
  Box::Ob; Port::Ob; Junction::Ob; OuterPort::Ob
  box::Hom(Port, Box)
  junction::Hom(Port, Junction)
  outer_junction::Hom(OuterPort, Junction)
end

# 3. oapply = colimit of component diagram (verified by DeepWiki)
composite = oapply(wiring_diagram, components)

Example 2: DisCoPy for Quantum/Categorical Diagrams

# Query DisCoPy documentation
mcp__deepwiki__ask_question("discopy/discopy",
  "How do monoidal categories compose with tensor products?")

# DisCoPy has 23 pages covering:
# - Monoidal, Rigid, Symmetric, Frobenius categories
# - Quantum circuits and gates
# - QNLP (Quantum Natural Language Processing)
# - Tensor network backends

Example 3: Agent-o-rama for Rama Integration

;; Query agent-o-rama patterns
mcp__deepwiki__ask_question("redplanetlabs/agent-o-rama",
  "How do PStates store agent invocation state?")

;; 28 pages covering:
;; - Agent Modules and Topology
;; - PStates and Depots storage
;; - Tool Calling Integration
;; - Human-in-the-Loop Workflows

See Also

  • hatchery-papers - Academic paper research
  • bmorphism-stars - GitHub stars index
  • librarian - Codebase understanding agent
  • exa - Web search MCP
  • acsets-algebraic-databases - ACSet computational patterns (trit 0, substitutes in triads)

Skill Name: deepwiki-mcp Type: Repository Documentation / Q&A Trit: 0 (ERGODIC) GF(3): Coordinates knowledge flow Auth: None required (free) Scope: All public GitHub repos indexed on DeepWiki.com Qualified: 2025-12-22 (verified against acsets skill)

rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization.Stars: 469kUpdated Claude CodeCodexVerifiedInstall
academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content.Stars: 197kUpdated Claude CodeCodexVerifiedInstall
claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).Stars: 197kUpdated Claude CodeCodexUnverifiedInstall
doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.Stars: 197kUpdated Claude CodeCodexVerifiedInstall