async-mcp-tool-pattern-for-long-running-pipelines
Long-running MCP tools (like ResearchClaw’s 23-stage pipeline) should return immediately with a run_id rather than blocking — the caller polls status via a separate get_status tool. Expose gate-approval as dedicated tools (approve_gate, reject_gate) so the orchestrating agent can act as a programmatic HITL reviewer. Expose sub-capabilities (citation verification, claim verification, literature search) as standalone tools callable outside the pipeline to maximize reuse.
Related
- researchclaw-11-mcp-tools-three-standalone-cross-oracle
- researchclaw-gate-stages-need-dedicated-mcp-tools
- autoresearchclaw-mcp-server-integration-pattern
- oracle
- autoresearchclaw-mcp-server-11-tools-interface-design
- researchclaw-mcp-long-running-tool-pattern
- async-mcp-pattern-for-long-running-pipelines
- researchclaw-three-gate-stages-require-hitl-approval-tools