Skip to main content
Glama

wiki_parser

Extract tables of contents and chapter content from DeepWiki AI-generated docs for GitHub repositories, with depth control and file saving options.

Instructions

A comprehensive tool for parsing and extracting content from DeepWiki documentation pages. This tool helps you navigate and extract specific content from DeepWiki's AI-generated documentation for GitHub repositories. DeepWiki analyzes codebases and creates detailed, structured documentation making complex projects easier to understand.

When to use this tool:

  • Getting a table of contents or structure overview of a repository's documentation

  • Extracting specific chapters or sections from the documentation

  • Understanding the organization of a project's documentation

  • Pulling detailed explanations of specific components or features

  • Gathering comprehensive documentation for offline use or analysis

Key features:

  • View documentation structure with customizable depth levels

  • Extract single or multiple chapters/sections

  • Support for nested section extraction using "Chapter##Section" format

  • Flexible depth control per chapter

  • Optional file saving with customizable paths

  • Efficient caching for repeated requests

Usage examples:

  1. Get overview of documentation structure: action: "structure", depth: 2

  2. Extract a complete chapter: action: "extract", chapters: ["Introduction"]

  3. Extract specific sections from multiple chapters: action: "extract", chapters: ["Setup##Installation", "Configuration##Environment Variables", "API##Core Methods"]

  4. Extract with custom depth per chapter: action: "extract", chapters: ["API", "Examples"], chapterDepths: {"API": 4, "Examples": 2}

  5. Save documentation for offline use: action: "extract", chapters: ["Introduction", "Setup", "Configuration"], saveToFile: "save-and-show"

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
repoYesGitHub repository in 'owner/repo' format (e.g., 'facebook/react')
depthNoFor structure view, how many header levels deep to show (1-4)
actionYes'structure' to see table of contents, 'extract' to get chapter content
chaptersNoChapter names to extract, can include sections like 'Setup##Installation'
saveToFileNo'save-only' returns just file path, 'save-and-show' returns content + saves
saveLocationNoCustom file path for saving (defaults to ~/.deepwiki-mcp/output/)
chapterDepthsNoOverride depth for specific chapters (e.g., {'Introduction': 2, 'API': 3})
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full transparency burden and performs well: it discloses behaviors like optional file saving, caching for repeated requests, custom depth control, and nested section extraction. It does not cover error handling or authentication requirements, but the core behavioral traits are transparently described.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long but well-structured with clear sections: overview, when-to-use, key features, and usage examples. It is front-loaded with the core purpose and every section adds value for a tool with 7 parameters, though some repetition exists across sections.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a relatively complex tool with no output schema and no annotations, the description covers actions, parameters, examples, and even file-saving behavior. It lacks explicit return-value descriptions, but given the detailed examples and 100% schema coverage, it is substantially complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, and the description adds substantial semantics beyond the schema. Usage examples clarify the 'Chapter##Section' format, per-chapter depth overrides via chapterDepths, saveToFile options, and how action values map to behavior, making parameter usage significantly easier to understand.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it parses and extracts content from DeepWiki documentation pages, with specific verbs ('navigate', 'extract', 'structure') and a defined resource. It distinguishes itself from the sibling wiki_question tool by focusing on structured extraction rather than Q&A.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides a clear 'When to use this tool' list with concrete scenarios like getting a table of contents, extracting chapters, and gathering offline documentation. It does not explicitly mention alternatives or when not to use it, but the usage contexts are specific and helpful.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/ai-vivid/deepwiki-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server