MCP Servers

Hand-maintained catalog of MCP servers configured in this environment, organized by category.

36 configured servers

What is MCP?

The Model Context Protocol is an open standard for connecting AI agents to external tools and data sources. Each server below exposes one or more tools that agents can invoke during a session.

Source of truth for this page

This page is hand-maintained and currently summarizes the MCP server entries in the repository root mcp.json. That file includes a mix of local scripts, local packages, remote gateways, and third-party servers, so this list is broader than the repo-local mcp/ directory.

DuckDuckGo global setup (all supported clients)

Use server key duckduckgo-search with pinned package version duckduckgo-mcp-server==0.1.1.

{
  "mcpServers": {
    "duckduckgo-search": {
      "command": "uvx",
      "args": ["--from=duckduckgo-mcp-server==0.1.1", "duckduckgo-mcp-server"]
    }
  }
}

Client	Global config path	MCP key path	Notes
antigravity	~/.gemini/antigravity/mcp_config.json	mcpServers	Verify-before-apply (path/schema may vary by version).
claude-code	~/.claude.json	mcpServers	Supports stdio server blocks.
cursor	~/.cursor/mcp.json	mcpServers	Same JSON shape as example above.
gemini-cli	~/.gemini/settings.json	mcpServers	Same JSON shape as example above.
codex	~/.codex/config.toml	[mcp_servers.<name>]	Use TOML snippet below.
crush	$HOME/.config/crush/crush.json	mcp	Uses mcp root key.
github-copilot (CLI)	~/.copilot/mcp-config.json	mcpServers	Include tools: ["*"] (snippet below).
opencode	~/.config/opencode/opencode.json	mcp	Uses mcp root key and array-style command.

Client-specific variants

Codex (~/.codex/config.toml)

[mcp_servers.duckduckgo-search]
command = "uvx"
args = ["--from=duckduckgo-mcp-server==0.1.1", "duckduckgo-mcp-server"]

Crush ($HOME/.config/crush/crush.json)

{
  "mcp": {
    "duckduckgo-search": {
      "type": "stdio",
      "command": "uvx",
      "args": ["--from=duckduckgo-mcp-server==0.1.1", "duckduckgo-mcp-server"]
    }
  }
}

GitHub Copilot CLI (~/.copilot/mcp-config.json)

{
  "mcpServers": {
    "duckduckgo-search": {
      "type": "stdio",
      "command": "uvx",
      "args": ["--from=duckduckgo-mcp-server==0.1.1", "duckduckgo-mcp-server"],
      "tools": ["*"]
    }
  }
}

OpenCode (~/.config/opencode/opencode.json)

{
  "mcp": {
    "duckduckgo-search": {
      "type": "local",
      "command": [
        "uvx",
        "--from=duckduckgo-mcp-server==0.1.1",
        "duckduckgo-mcp-server"
      ]
    }
  }
}

Chrome DevTools global setup (all supported clients)

Use server key chrome-devtools with the chrome-devtools-mcp npm package. Requires Node.js v22+ and Chrome stable channel.

{
  "mcpServers": {
    "chrome-devtools": {
      "command": "npx",
      "args": ["-y", "chrome-devtools-mcp@latest"]
    }
  }
}

Client	Global config path	MCP key path	Notes
antigravity	~/.gemini/antigravity/mcp_config.json	mcpServers	Same JSON shape as example above.
claude-code	~/.claude.json	mcpServers	Supports stdio server blocks.
cursor	~/.cursor/mcp.json	mcpServers	Same JSON shape as example above.
gemini-cli	~/.gemini/settings.json	mcpServers	Add "type": "stdio" and "env": {}.
codex	~/.codex/config.toml	[mcp_servers.<name>]	Use TOML snippet below.
crush	$HOME/.config/crush/crush.json	mcp	Uses mcp root key.
github-copilot (CLI)	~/.copilot/mcp-config.json	mcpServers	Include tools: ["*"] (snippet below).
opencode	~/.config/opencode/opencode.json	mcp	Uses mcp root key and array-style command.

Client-specific variants

Codex (~/.codex/config.toml)

[mcp_servers.chrome-devtools]
command = "npx"
args = ["-y", "chrome-devtools-mcp@latest"]

Crush ($HOME/.config/crush/crush.json)

{
  "mcp": {
    "chrome-devtools": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "chrome-devtools-mcp@latest"]
    }
  }
}

GitHub Copilot CLI (~/.copilot/mcp-config.json)

{
  "mcpServers": {
    "chrome-devtools": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "chrome-devtools-mcp@latest"],
      "tools": ["*"]
    }
  }
}

OpenCode (~/.config/opencode/opencode.json)

{
  "mcp": {
    "chrome-devtools": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "chrome-devtools-mcp@latest"
      ]
    }
  }
}

---

Thinking and Reasoning (10)

Structured reasoning frameworks that guide agents through multi-step analysis, creative problem-solving, and decision evaluation.

sequential-thinking

Analysis Step-by-step reasoning with revision and branching. The reference implementation from Anthropic for dynamic, reflective thought processes.

atom-of-thoughts

Synthesis Decomposes complex problems into atomic, independent thought units that can be contracted and combined for robust answers.

shannon-thinking

Information Theory Information-theoretic reasoning inspired by Claude Shannon. Reduces noise and uncertainty through systematic problem decomposition.

structured-thinking

Memory Captures, retrieves, and revises thoughts with persistent history. Supports tagging and relevance-based retrieval across sessions.

cascade-thinking

Deep Dive Multi-stage reasoning cascade that escalates through progressively deeper analysis levels when simpler passes are insufficient.

crash

Verification Constraint-satisfaction reasoning with strict mode toggle. Enforces logical consistency checking on intermediate conclusions.

deep-lucid-3d

Exploration Three-dimensional problem analysis exploring depth, breadth, and lateral connections. Includes creative exploration mode.

lotus-wisdom-mcp

Perspective Eastern-philosophy-inspired reasoning combining multiple perspectives and reflective synthesis for balanced conclusions.

think-strategies

Routing Strategy-selection toolkit that matches reasoning patterns to problem types. Session management for ongoing analysis threads.

creative-thinking

Ideation Lateral and divergent thinking techniques for brainstorming, ideation, and breaking out of conventional solution spaces.

---

Search and Discovery (8)

Web search engines and content discovery services for retrieving up-to-date information from the internet.

brave-search

Web/Local Brave Search API with web, news, image, video, and local search. Includes AI-powered summarization of search results.

exa

Neural Search Neural search engine that understands meaning, not just keywords. Optimized for finding technical content, papers, and documentation.

web-search

General Web General-purpose web search with result extraction and content parsing. Lightweight alternative for quick lookups.

g-search

Google Google Search results via SerpAPI. Familiar ranking and broad coverage across the public web.

duckduckgo-search

Privacy First Privacy-focused web search via DuckDuckGo. No tracking, no API key required.

arxiv

Academic arXiv paper search and metadata retrieval for research workflows, including direct access to paper IDs and summaries.

wikipedia

Encyclopedic Wikipedia content retrieval and lookup tools for encyclopedic background, entities, and topic overviews.

wayback

Archive Access archived pages from the Internet Archive Wayback Machine for historical snapshots and link recovery.

---

Web Fetching and Extraction (3)

Tools for retrieving, rendering, and extracting structured content from web pages and URLs.

fetch

HTTP Fetch Core URL fetcher from the MCP reference servers. Retrieves web pages and returns content in multiple formats.

fetcher

JS Rendering Browser-based URL fetcher with JavaScript rendering. Handles SPAs and dynamic content that simple HTTP fetches miss.

trafilatura

Content Extraction High-quality web content extraction using the Trafilatura library. Strips boilerplate to return clean article text and metadata.

---

Knowledge and Documentation (3)

Access library documentation, open-source wiki knowledge, and codebase analysis tools.

context7

API Docs Retrieves up-to-date documentation for libraries and frameworks directly from source. Eliminates hallucinated APIs and outdated references.

deepwiki

GitHub Wikis Queries the DeepWiki knowledge base of open-source project documentation. Ask questions about repos and read generated wiki pages.

repomix

Codebase Context Packs entire codebases into AI-friendly context. Supports local directories and remote repositories with grep and directory browsing.

---

Development Tools (5)

Browser automation, package management, and document processing for development workflows.

chrome-devtools

CDP Automation Chrome DevTools Protocol automation via Puppeteer. Navigate, click, fill forms, trace performance, inspect network requests, and take screenshots. Requires Node.js v22+.

playwright

E2E Testing Full browser automation via Playwright. Navigate pages, fill forms, click elements, take screenshots, and run end-to-end test flows.

playwright-headless

CI/CD Ready Headless Playwright variant for isolated browser automation without extension requirements.

package-version

Dependency Mgmt Checks latest versions across npm, PyPI, Go, Maven, Gradle, Swift, Docker, Bedrock models, and GitHub Actions.

docling

Doc Processing Converts documents (PDF, DOCX, PPTX, HTML) into structured Docling format. Create, edit, search, and export documents as Markdown.

---

Productivity (3)

Email, task management, and personal productivity integrations.

gmail

Inbox Zero Full Gmail access: search, read, send, draft, label, filter, and batch-manage emails. Supports attachment downloads.

apple-mail

Native macOS Native macOS Mail.app integration. Read, search, and manage emails through Apple’s built-in mail client.

things

Task Mgmt Things 3 task manager integration. Create and manage todos, projects, areas, and tags. Query inbox, today, upcoming, and logbook.

---

Media (2)

Audio production and video processing tools.

ffmpeg

Video Processing Video and audio processing via FFmpeg. Get info, clip, scale, concatenate, overlay, extract frames, and play media files.

ableton

Music Production Ableton Live integration for music production. Control sessions, tracks, and clips programmatically.

---

Social (1)

Social media and professional network integrations.

linkedin

Professional Data LinkedIn profile scraping for professional networking data. Extract public profile information and connections.

---

Remote Gateway (1)

Cloud-hosted MCP endpoints providing aggregated or custom tool access.

default

Network Proxy Remote MCP gateway at mcp.w4w.dev providing a curated default toolset via mcp-remote proxy.