Server profile

DevDocs by CyberAGI MCP Server

Crawl technical documentation into organized Markdown, JSON, and MCP-accessible content for development assistants. The public DevDocs repository is marked as not publicly maintained.

Server facts

DevDocs by CyberAGI MCP Server

Project

License
Apache-2.0

Tech

Runtime / language
nodeTypeScript and Python
Transports
stdio
Remote available
No
Authentication
Not specified

Activity

GitHub stars
2,108
Last commit
Data as of

Tags

  • Documentation
  • Knowledge Retrieval
  • Self Hosted
  • Web Crawling

Overview

DevDocs by CyberAGI is a self-hosted documentation collection and retrieval project for developers and teams. Starting from a documentation URL, it discovers related pages, extracts their content, and organizes the results for use by an LLM. Crawl depth can be set from one to five levels, and selective crawling lets users choose which discovered material to collect. The README also describes parallel processing, caching, lazy-loaded content support, rate limiting, and retry behavior. Exported material can be consumed as Markdown or JSON, while an MCP integration makes documentation available to assistants.

The documented retrieval approach separates finding topics from reading their sections. A table-of-contents tool identifies relevant material, and a section-access tool retrieves the detailed content. These are described by human-readable labels rather than an explicit machine-name listing. Installation uses a Docker-based stack with frontend, backend, MCP, and Crawl4AI services. Users clone the repository, copy its environment template, set the frontend's backend URL, and run the startup script. macOS and Linux are the recommended path; the Windows instructions are explicitly experimental and untested. Most importantly, the README opens with a notice that the public project is not maintained and that an enhanced internal version exists at CyberAGI. That status should be considered before relying on it for a new documentation workflow.

Install & configure

Requirements

  • Docker
  • Git
  • A cloned DevDocs checkout
  • macOS or Linux for the recommended startup path
Documented launch / install command
./docker-start.sh

Run from the cloned repository after copying .env.template to .env. This script starts the complete application stack, not a standalone MCP client entry. Windows uses a separate experimental batch script.

Config file · macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

Windows: %APPDATA%\Claude\claude_desktop_config.json

Use Settings → Developer → Edit Config when available. Do not assume a Linux configuration path; check the client documentation for your platform. Remote servers use the app’s connector flow when supported, not the local stdio file shown here. Merge this example with existing settings; do not overwrite unrelated servers.

Claude Desktop configuration
{
  "mcpServers": {
    "DevDocs": {
      "command": "./docker-start.sh",
      "args": [],
      "env": {
        "NEXT_PUBLIC_BACKEND_URL": "<backend address reachable by the frontend browser>"
      }
    }
  }
}

Read the Claude Desktop setup guide

Config file · Project: .cursor/mcp.json

User: ~/.cursor/mcp.json

The project path is relative to the workspace root. The tilde denotes your user home directory. Use Cursor’s MCP settings to confirm which configuration and scope your installed version is reading. Merge this example with existing settings; do not overwrite unrelated servers.

Cursor configuration
{
  "mcpServers": {
    "DevDocs": {
      "command": "./docker-start.sh",
      "args": [],
      "env": {
        "NEXT_PUBLIC_BACKEND_URL": "<backend address reachable by the frontend browser>"
      }
    }
  }
}

Read the Cursor setup guide

Config file · Workspace: .vscode/mcp.json

For user scope, use the “MCP: Open User Configuration” command if available. Do not guess a user configuration path across operating systems, profiles, containers, or remote workspaces; check the client documentation. Merge this example with existing settings; do not overwrite unrelated servers.

VS Code configuration
{
  "servers": {
    "DevDocs": {
      "type": "stdio",
      "command": "./docker-start.sh",
      "args": [],
      "env": {
        "NEXT_PUBLIC_BACKEND_URL": "<backend address reachable by the frontend browser>"
      }
    }
  }
}

Read the VS Code setup guide

Config file · macOS/Linux: ~/.codeium/windsurf/mcp_config.json

Windows: %USERPROFILE%\.codeium\windsurf\mcp_config.json

Open the MCP configuration through Windsurf’s settings when possible to confirm the active file. Paths can differ in managed or future releases; check the client documentation if this location is not present. Merge this example with existing settings; do not overwrite unrelated servers.

Windsurf configuration
{
  "mcpServers": {
    "DevDocs": {
      "command": "./docker-start.sh",
      "args": [],
      "env": {
        "NEXT_PUBLIC_BACKEND_URL": "<backend address reachable by the frontend browser>"
      }
    }
  }
}

Read the Windsurf setup guide

Config file · Project scope: .mcp.json at the repository root

The project file uses mcpServers. For user scope, use claude mcp add --scope user rather than assuming .mcp.json in your home directory is the user configuration. Check the client documentation for managed settings and storage details. Merge this example with existing settings; do not overwrite unrelated servers.

Claude Code configuration
{
  "mcpServers": {
    "DevDocs": {
      "type": "stdio",
      "command": "./docker-start.sh",
      "args": [],
      "env": {
        "NEXT_PUBLIC_BACKEND_URL": "<backend address reachable by the frontend browser>"
      }
    }
  }
}

Read the Claude Code setup guide

Examples are translated from the published configuration. Supply your own credentials and verify requirements in the upstream README. Remote connectors are shown only where a supported configuration format is known.

Tools

Source: repository README. Tool descriptions are a documented snapshot, not a live capability check.

ToolWhat it does
Table Of Contents ToolFind documentation topics through a full or filtered index; the README supplies this descriptive label.
Section Access ToolRetrieve detailed documentation sections after index discovery; the README supplies this descriptive label.

Names, permissions, and defaults can change. Check the current upstream documentation before granting access.

Use cases

  • Collect linked technical documentation with controlled crawl depth.
  • Export cleaned documentation as Markdown or JSON.
  • Give an assistant indexed access to internal documentation.
  • Retrieve specific documentation sections after topic discovery.

Strengths

  • Supports selective crawling, depth control, and structured exports.
  • Provides a Docker startup path for the multi-service stack.
  • Describes a topic-index and section-retrieval workflow for assistants.

Limitations

  • The public repository is explicitly marked as not maintained.
  • Windows setup is described as experimental and untested.
  • Running the documented stack involves several services.

Frequently asked questions

The README says it is not publicly maintained and points to an enhanced internal CyberAGI version.

The documented depth selection ranges from one through five levels.

The README lists Markdown and JSON, as well as MCP integration for AI retrieval.

No. The Windows Docker instructions are labeled experimental and untested.

Independent listing, not an affiliation or security review. Grant the least access needed and verify the upstream instructions before running code.

Related MCP servers

MCP Advisor

Developer Tools

MCP Advisor helps assistants discover MCP servers from natural-language requests and obtain installation guidance. It combines registry providers with offline search and offers optional local Meilisearch integration.

Serena

Developer Tools

Serena gives coding agents symbol-aware retrieval, editing, refactoring, and debugging capabilities through MCP. It uses language servers or a JetBrains plugin to bring IDE-style code understanding to existing AI clients.

Context7

Developer Tools

Context7 retrieves current library documentation and code examples for AI coding assistants. It supports MCP tools or a CLI-and-skills workflow, with library IDs and version-aware requests helping narrow the documentation context.

FastAPI-MCP

Developer Tools

FastAPI-MCP exposes existing FastAPI endpoints as MCP tools while retaining schemas, endpoint documentation, and dependency-based authentication. It is a native extension for developers adding agent access to a FastAPI service.

GitMCP

Developer Tools

GitMCP turns public GitHub repositories and GitHub Pages projects into documentation sources for AI assistants. It offers repository-specific endpoints or a dynamic server for retrieving docs, searching code, and following referenced content.

XcodeBuildMCP

Developer Tools

XcodeBuildMCP provides an MCP server and CLI for AI agents working on iOS and macOS projects. One package supports direct terminal tools, simulator builds, and stateful operations such as debugging and log capture.

JetBrains MCP Proxy Server

Developer Tools

This legacy Node-based proxy connects MCP clients to a JetBrains IDE plugin. The repository is deprecated: IntelliJ-based IDEs include the core functionality from version 2025.2 onward.

MCP Language Server

Developer Tools

Expose an installed language server to MCP assistants for semantic code navigation and edits. It provides definitions, references, diagnostics, hover information, symbol renaming, and line-based file changes.