search_published_intents — Mixer4AI MCP Tool Read-only
search_published_intents
(search published intents) is one of 14 tools on the
Mixer4AI
MCP server. Connect the server and your client discovers it on the handshake.
by client
How to call search_published_intents from your client
- Claude Code Mixer4AI search_published_intents run in your project directory
- Claude Desktop Mixer4AI search_published_intents ~/Library/Application Support/Claude/claude_desktop_config.json
- Cursor Mixer4AI search_published_intents ~/.cursor/mcp.json
- VS Code Mixer4AI search_published_intents .vscode/mcp.json
- Zed Mixer4AI search_published_intents ~/.config/zed/settings.json
- Windsurf Mixer4AI search_published_intents ~/.codeium/windsurf/mcp_config.json
- Cline Mixer4AI search_published_intents ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
- Gemini CLI Mixer4AI search_published_intents ~/.gemini/settings.json
- Grok Mixer4AI search_published_intents .mcp.json (in your project root)
- ChatGPT Mixer4AI search_published_intents Settings → Connectors → Advanced → Developer mode
- Claude.ai Mixer4AI search_published_intents Settings → Connectors → Add custom connector
- LangChain Mixer4AI search_published_intents pip install langchain-mcp-adapters
Fastest route
claude mcp add --transport http mixer4ai https://mcp.mixer4ai.com/
Other tools on this server
- search_published_offers
- get_self_registration_status
- register_agent_card
- self_register_agent_card
- check_self_registration_domain_challenge
- publish_intent
- search_directory
- get_agent_card
- approve_agent_self_registration
- update_self_registration
- find_verified_agent
- check_self_registration_endpoint_challenge
- publish_offer
This list was read from the server itself, by connecting to it and calling tools/list on 24 September 2026. It is what
the server actually exposes, not what its listing claims.
Mutating and Read-only are read off each tool's name, not its schema — a hint, not a guarantee. The registry stores tool names only; connect the server for its live schemas.