Swarmnest MCP Server
Give your AI agent the whole Swarmnest directory: 3,813 hand-checked tools, APIs and MCP servers in 168 categories, 545 Agent Skills and the Marketplace. One remote URL, free, read-only, no API key.
Server URL
https://swarmnest.ai/mcp
Transport: Streamable HTTP. Protocol versions: 2026-07-28, 2025-11-25, 2025-06-18, 2025-03-26, 2024-11-05. Source and self-hosting notes on GitHub.
Set Up in Your Client
Claude Code
Run in your terminal:
claude mcp add --transport http swarmnest https://swarmnest.ai/mcp
Claude Desktop and Claude.ai
Settings → Connectors → Add Custom Connector, then paste this URL:
https://swarmnest.ai/mcp
Cursor
Add to ~/.cursor/mcp.json (all projects) or .cursor/mcp.json (one project):
{
"mcpServers": {
"swarmnest": {
"url": "https://swarmnest.ai/mcp"
}
}
}VS Code (GitHub Copilot)
Add to .vscode/mcp.json, or run MCP: Add Server and choose HTTP:
{
"servers": {
"swarmnest": {
"type": "http",
"url": "https://swarmnest.ai/mcp"
}
}
}Windsurf
Add to ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"swarmnest": {
"serverUrl": "https://swarmnest.ai/mcp"
}
}
}Codex
Add to ~/.codex/config.toml:
[mcp_servers.swarmnest] url = "https://swarmnest.ai/mcp"
Gemini CLI
Add to ~/.gemini/settings.json:
{
"mcpServers": {
"swarmnest": {
"httpUrl": "https://swarmnest.ai/mcp"
}
}
}Any Client Without Remote Support (npx mcp-remote)
For clients that only run local servers, including the Claude Desktop config file. Needs Node.js:
{
"mcpServers": {
"swarmnest": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://swarmnest.ai/mcp"
]
}
}
}If your config file already has other servers, add the swarmnest entry next to them. Restart or reload the client after editing a config file.
Tools
All 6 tools are read-only and return canonical swarmnest.ai links, so your agent can cite where each result came from.
search_directory | Search the Swarmnest Directory. Search the Swarmnest directory of AI agent tools: MCP servers, LLM APIs, agent frameworks, coding agents, browser automation, vector databases, web scraping, search, speech and text-to-speech APIs, data sources and more (thousands of hand-checked entries in 160+ categories). Keyword search over name, category and description with typo correction; all keywords must match. Filter by category slug (see list_categories), pricing, auth type or operating system. Returns name, description, category, pricing, auth, the vendor URL, docs URL and the canonical swarmnest.ai listing URL. Use it to find or compare tools for a job, e.g. "pdf parsing", "web search api", "postgres mcp server". Arguments: query (optional), category (optional), pricing (optional), auth (optional), os (optional), limit (optional), offset (optional) |
|---|---|
get_entry | Get a Directory Entry. Get the full Swarmnest directory record for one tool by its slug (from search_directory results): name, description, category, vendor URL, docs URL, auth, pricing, operating systems, open-source flag, last link check and the canonical swarmnest.ai URL. Unknown slugs return close matches. Arguments: slug |
list_categories | List Directory Categories. List every Swarmnest directory category with its slug, name, short description, entry count and group (e.g. Agent Building, AI Models, Data & Search). Use the slugs as the category filter in search_directory. Optionally limit to one group. Arguments: group (optional) |
search_skills | Search Agent Skills. Search the Swarmnest catalog of Agent Skills: SKILL.md skills, plugin bundles, Cursor rules, AGENTS.md templates and prompt packs for Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot and other agents. Keyword search over title, summary and category; filter by skill category, format, platform or operating system. Each result says whether the skill includes scripts, uses the network or needs credentials, plus its license, author, source URL and canonical swarmnest.ai URL. All skills are third-party: review the source before installing. Arguments: query (optional), category (optional), format (optional), platform (optional), os (optional), limit (optional), offset (optional) |
get_skill | Get an Agent Skill. Get one Agent Skill by slug (from search_skills): summary, format, declared platforms, install steps per platform, scripts/network/credentials labels, license, author, source URL and canonical swarmnest.ai URL. Third-party: review the source before installing. Arguments: slug |
list_marketplace_products | List Marketplace Products. List the agent skill packs, workflows and bundles sold in the Swarmnest Marketplace (US only), with name, type, summary, price in USD, what each bundle includes, the product page URL and the checkout URL. Arguments: type (optional) |
Results are capped at 25 per call; use offset to page. Agent Skills are made by third-party developers, so every skill result carries an install warning: review the source before installing.
Example Prompts
- Find three free web scraping APIs that work without an API key and link their Swarmnest pages.
- Which MCP servers can read and write Postgres? Compare their auth and pricing.
- List the Swarmnest categories in the Agent Building group with their entry counts.
- Search Agent Skills for PDF handling that work in Claude Code and show me how to install the best one.
- Find macOS automation tools for agents and tell me which are open source.
- What skill packs and bundles does the Swarmnest Marketplace sell, and what does each cost?
Try It With curl
curl -s https://swarmnest.ai/mcp \
-H 'Content-Type: application/json' \
-H 'Accept: application/json, text/event-stream' \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"search_directory","arguments":{"query":"web scraping","pricing":"freemium","limit":5}}}'Methods: tools/list, tools/call, initialize, server/discover and ping. Responses are plain JSON. Server card: /mcp/server-card.
More Ways to Use Swarmnest Data
- Search API and OpenAPI description
- Directory JSON, Categories JSON and Agent Skills JSON
- llms.txt for chatbots and crawlers
- Browse MCP Servers in the directory, or the MCP Server Starter Kit to build your own
Use of the server is covered by our API Terms. Questions: [email protected].