5 tagged human-ai-collaboration, measured the same way as everything else here.
MCP server Claude CodeCodexCursor +2
Auditable records of human decisions over AI agent work. Approvals, edits, overrides, escalations. Runs locally from the @brightbeamai/chap-coordinator-mcp npm package. Needs 2 environment variables to run.
MCP server Claude CodeCodexCursor +2
MCP server "trace" as configured in Thru-Echoes/TRACE. Runs locally from the . Python package. Needs 1 environment variable to run.
linxule/interpretive-orchestration
MCP server Claude CodeCodexCursor +2
Adds a structured step-by-step reasoning tool the agent can call to break a problem into revisable thoughts. Runs locally from the @modelcontextprotocol/server-sequential-thinking npm package.
linxule/interpretive-orchestration
MCP server Claude CodeCodexCursor +2
Contemplative reasoning MCP server — Lotus Sutra wisdom framework with interactive ext-apps journey visualization. Runs locally from the lotus-wisdom-mcp npm package.
MCP server Claude CodeCodexCursor +2
MCP server "watercooler" as configured in mostlyharmless-ai/watercooler. Runs locally from the git+https://github.com/mostlyharmless-ai/[email protected][local] Python package.