Deepwiki MCP Server
Deepwiki MCP-Server
Dies ist ein inoffizieller Deepwiki MCP-Server
Es nimmt eine Deepwiki-URL über MCP, crawlt alle relevanten Seiten, konvertiert sie in Markdown und gibt entweder ein Dokument oder eine Liste pro Seite zurück.
Merkmale
🔒 Domänensicherheit : Verarbeitet nur URLs von deepwiki.com
🧹 HTML-Bereinigung : Entfernt Kopf- und Fußzeilen, Navigation, Skripte und Anzeigen
🔗 Link-Neuschreibung : Passt Links an, damit sie in Markdown funktionieren
📄 Mehrere Ausgabeformate : Erhalten Sie ein Dokument oder strukturierte Seiten
🚀 Leistung : Schnelles Crawlen mit einstellbarer Parallelität und Tiefe
NLP : Es wird nur nach dem Bibliotheksnamen gesucht
Related MCP server: Markdown-To-Notion
Verwendung
Eingabeaufforderungen, die Sie verwenden können:
deepwiki fetch how can i use gpt-image-1 with "vercel ai" sdkdeepwiki fetch how can i create new blocks in shadcn?deepwiki fetch i want to understand how X worksVollständige Dokumentation abrufen (Standard)
use deepwiki https://deepwiki.com/shadcn-ui/ui
use deepwiki multiple pages https://deepwiki.com/shadcn-ui/uiEinzelne Seite
use deepwiki fetch single page https://deepwiki.com/tailwindlabs/tailwindcss/2.2-theme-systemErhalten Sie per Kurzform
use deepwiki fetch tailwindlabs/tailwindcssdeepwiki fetch library
deepwiki fetch url
deepwiki fetch <name>/<repo>
deepwiki multiple pages ...
deepwiki single page url ...Cursor
Fügen Sie dies der .cursor/mcp.json hinzu.
{
"mcpServers": {
"mcp-deepwiki": {
"command": "npx",
"args": ["-y", "mcp-deepwiki@latest"]
}
}
}
MCP-Tool-Integration
Das Paket registriert ein Tool namens deepwiki_fetch , das Sie mit jedem MCP-kompatiblen Client verwenden können:
{
"action": "deepwiki_fetch",
"params": {
"url": "https://deepwiki.com/user/repo",
"mode": "aggregate",
"maxDepth": "1"
}
}Parameter
url(erforderlich): Die Start-URL des Deepwiki-Repositorysmode(optional): Ausgabemodus, entweder „aggregate“ für ein einzelnes Markdown-Dokument (Standard) oder „pages“ für strukturierte SeitendatenmaxDepth(optional): Maximale Tiefe der zu crawlenden Seiten (Standard: 10)
Antwortformat
Erfolgsantwort (Aggregatmodus)
{
"status": "ok",
"data": "# Page Title\n\nPage content...\n\n---\n\n# Another Page\n\nMore content...",
"totalPages": 5,
"totalBytes": 25000,
"elapsedMs": 1200
}Erfolgsantwort (Seitenmodus)
{
"status": "ok",
"data": [
{
"path": "index",
"markdown": "# Home Page\n\nWelcome to the repository."
},
{
"path": "section/page1",
"markdown": "# First Page\n\nThis is the first page content."
}
],
"totalPages": 2,
"totalBytes": 12000,
"elapsedMs": 800
}Fehlerantwort
{
"status": "error",
"code": "DOMAIN_NOT_ALLOWED",
"message": "Only deepwiki.com domains are allowed"
}Teilweise Erfolgsantwort
{
"status": "partial",
"data": "# Page Title\n\nPage content...",
"errors": [
{
"url": "https://deepwiki.com/user/repo/page2",
"reason": "HTTP error: 404"
}
],
"totalPages": 1,
"totalBytes": 5000,
"elapsedMs": 950
}Fortschrittsereignisse
Wenn Sie das Tool verwenden, erhalten Sie während des Crawlens Fortschrittsereignisse:
Fetched https://deepwiki.com/user/repo: 12500 bytes in 450ms (status: 200)
Fetched https://deepwiki.com/user/repo/page1: 8750 bytes in 320ms (status: 200)
Fetched https://deepwiki.com/user/repo/page2: 6200 bytes in 280ms (status: 200)Lokale Entwicklung - Installation
Lokale Nutzung
{
"mcpServers": {
"mcp-deepwiki": {
"command": "node",
"args": ["./bin/cli.mjs"]
}
}
}Aus der Quelle
# Clone the repository
git clone https://github.com/regenrek/deepwiki-mcp.git
cd deepwiki-mcp
# Install dependencies
npm install
# Build the package
npm run buildDirekte API-Aufrufe
Für den HTTP-Transport können Sie direkte API-Aufrufe tätigen:
curl -X POST http://localhost:3000/mcp \
-H "Content-Type: application/json" \
-d '{
"id": "req-1",
"action": "deepwiki_fetch",
"params": {
"url": "https://deepwiki.com/user/repo",
"mode": "aggregate"
}
}'Konfiguration
Umgebungsvariablen
DEEPWIKI_MAX_CONCURRENCY: Maximale Anzahl gleichzeitiger Anfragen (Standard: 5)DEEPWIKI_REQUEST_TIMEOUT: Anforderungs-Timeout in Millisekunden (Standard: 30000)DEEPWIKI_MAX_RETRIES: Maximale Wiederholungsversuche für fehlgeschlagene Anfragen (Standard: 3)DEEPWIKI_RETRY_DELAY: Basisverzögerung für Wiederholungs-Backoff in Millisekunden (Standard: 250)
Um diese zu konfigurieren, erstellen Sie eine .env Datei im Projektstammverzeichnis:
DEEPWIKI_MAX_CONCURRENCY=10
DEEPWIKI_REQUEST_TIMEOUT=60000
DEEPWIKI_MAX_RETRIES=5
DEEPWIKI_RETRY_DELAY=500Docker-Bereitstellung (ungetestet)
Erstellen und führen Sie das Docker-Image aus:
# Build the image
docker build -t mcp-deepwiki .
# Run with stdio transport (for development)
docker run -it --rm mcp-deepwiki
# Run with HTTP transport (for production)
docker run -d -p 3000:3000 mcp-deepwiki --http --port 3000
# Run with environment variables
docker run -d -p 3000:3000 \
-e DEEPWIKI_MAX_CONCURRENCY=10 \
-e DEEPWIKI_REQUEST_TIMEOUT=60000 \
mcp-deepwiki --http --port 3000Entwicklung
# Install dependencies
pnpm install
# Run in development mode with stdio
pnpm run dev-stdio
# Run tests
pnpm test
# Run linter
pnpm run lint
# Build the package
pnpm run buildFehlerbehebung
Häufige Probleme
Berechtigung verweigert : Wenn beim Ausführen der CLI EACCES-Fehler auftreten, stellen Sie sicher, dass die Binärdatei ausführbar ist:
chmod +x ./node_modules/.bin/mcp-deepwikiVerbindung abgelehnt : Stellen Sie sicher, dass der Port verfügbar ist und nicht durch eine Firewall blockiert wird:
# Check if port is in use lsof -i :3000Timeout-Fehler : Erwägen Sie bei großen Repositories eine Erhöhung des Timeouts und der Parallelität:
DEEPWIKI_REQUEST_TIMEOUT=60000 DEEPWIKI_MAX_CONCURRENCY=10 npx mcp-deepwiki
Beitragen
Wir freuen uns über Beiträge! Weitere Informationen finden Sie unter CONTRIBUTING.md .
Lizenz
MIT
Links
X/Twitter: @kregenrek
Bluesky: @kevinkern.dev
Kurse
Cursor-KI lernen: Ultimativer Cursor-Kurs
Lernen Sie, Software mit KI zu erstellen: instructa.ai
Sehen Sie sich meine anderen Projekte an:
KI-Eingabeaufforderungen – Kuratierte KI-Eingabeaufforderungen für Cursor AI, Cline, Windsurf und Github Copilot
Codefetch – Wandeln Sie Code mit einem einfachen Terminalbefehl in Markdown für LLMs um
aidex Ein CLI-Tool, das detaillierte Informationen zu KI-Sprachmodellen bereitstellt und Entwicklern hilft, das richtige Modell für ihre Anforderungen auszuwählen.# tool-starter
Available Tools
1 tooldeepwiki_fetchC
Fetch a deepwiki.com repo and return Markdown
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | should be a URL, owner/repo name (e.g. "vercel/ai"), a two-word "owner repo" form (e.g. "vercel ai"), or a single library keyword | |
| maxDepth | No | Can fetch a single site => maxDepth 0 or multiple/all sites => maxDepth 1 | |
| mode | No | aggregate | |
| verbose | No |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions fetching and returning Markdown but omits critical details like authentication requirements, rate limits, error handling, or whether this is a read-only operation. For a tool with no annotation coverage, this is insufficient.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise—a single sentence that directly states the tool's purpose. Every word earns its place, with no unnecessary elaboration. It's front-loaded and efficiently communicates the core functionality.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (4 parameters, 50% schema coverage, no output schema, no annotations), the description is inadequate. It doesn't explain what 'fetching' entails, how the Markdown is structured, error conditions, or usage constraints. For a tool with significant undocumented aspects, more context is needed.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 50%, with only the 'url' parameter well-documented in the schema. The description adds no parameter-specific information beyond what the schema provides. It doesn't explain the meaning of 'maxDepth', 'mode', or 'verbose' parameters, leaving gaps in understanding.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('fetch') and resource ('deepwiki.com repo'), and specifies the output format ('return Markdown'). It distinguishes the tool by mentioning the specific domain (deepwiki.com) and output type. However, without sibling tools, there's no explicit differentiation from alternatives.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus other methods or tools. It lacks context about prerequisites, typical use cases, or limitations. With no sibling tools mentioned, it doesn't address alternatives within the server.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
1 tool update
- First observed
deepwiki_fetch
TDQS
Scored across 1 tool
With only one tool, there is no possibility of ambiguity or overlap between tools. The tool's purpose is clearly defined as fetching a Deepwiki repo and returning Markdown, making it impossible to confuse with any other tool.
The single tool name follows a consistent verb_noun pattern (deepwiki_fetch), and with only one tool, there is no inconsistency to evaluate. The naming is clear and adheres to a predictable structure.
A single tool is generally too few for a server's purpose, as it limits functionality and may indicate an incomplete surface. For a Deepwiki server, one tool feels thin and under-scoped, lacking operations like search, update, or list repos that might be expected.
The server is severely incomplete for interacting with Deepwiki repos. It only provides a fetch operation, missing essential CRUD/lifecycle coverage such as creating, updating, deleting, or searching repos, which are likely needed for full agent workflows in this domain.
Maintenance
Related MCP Connectors
MCP server for opencode documentation, generated by doc2mcp.
Document-to-Markdown MCP server — convert PDF, Office and HTML into LLM-ready Markdown.
MCP server for innovationlab documentation, generated by doc2mcp.
MCP server for accessing curated awesome list documentation
Related MCP Servers
- AlicenseAqualityDmaintenanceA powerful MCP server for fetching and transforming web content into various formats (HTML, JSON, Markdown, Plain Text) with ease.44,875 npm42MIT
- AlicenseCqualityDmaintenanceAn MCP server that converts Markdown content to Notion API-compatible formats, suitable for content management and development integration.11Apache 2.0
- FlicenseNot gradedqualityDmaintenanceA locally-hosted MCP server that provides AI assistants with advanced web crawling capabilities, including structured data extraction, deep site crawling, and page screenshots. It enables users to convert single or multiple URLs into clean Markdown content for processing by LLMs without requiring external API keys for basic features.-
- AlicenseAqualityDmaintenanceMCP server that allows AI agents to fetch and process llms.txt documentation from various sources. Fetch documentation from any HTTPS URL and automatically convert HTML content to readable markdown.24 npm2MIT