find_specialist — AI Blocks MCP Tool Read-only
find_specialist
(find specialist) is one of 22 tools on the
AI Blocks
MCP server. Connect the server and your client discovers it on the handshake.
by client
How to call find_specialist from your client
- Claude Code AI Blocks find_specialist run in your project directory
- Claude Desktop AI Blocks find_specialist ~/Library/Application Support/Claude/claude_desktop_config.json
- Cursor AI Blocks find_specialist ~/.cursor/mcp.json
- VS Code AI Blocks find_specialist .vscode/mcp.json
- Zed AI Blocks find_specialist ~/.config/zed/settings.json
- Windsurf AI Blocks find_specialist ~/.codeium/windsurf/mcp_config.json
- Cline AI Blocks find_specialist ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
- Gemini CLI AI Blocks find_specialist ~/.gemini/settings.json
- Grok AI Blocks find_specialist .mcp.json (in your project root)
- ChatGPT AI Blocks find_specialist Settings → Connectors → Advanced → Developer mode
- Claude.ai AI Blocks find_specialist Settings → Connectors → Add custom connector
- LangChain AI Blocks find_specialist pip install langchain-mcp-adapters
Fastest route
claude mcp add --transport http library https://useaiblocks.com/mcpOther tools on this server
- start_outcome
- advance_outcome
- record_outcome_decision
- record_outcome_experiment
- read_back_outcome_experiment
- prepare_outcome_pattern
- prepare_job_context
- start_job
- advance_job
- get_approaches
- get_job_templates
- get_job_preferences
- set_job_preferences
- prepare_specialist
- search_library
- plan_workflow
- get_resource
- prepare_workflow
- get_item
- search
- fetch
This list was read from the server itself, by connecting to it and calling tools/list on 14 November 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.