# bruce601080102/ccc-mcp

Source: https://glimind.com/server/github%2Fbruce601080102%2Fccc-mcp
Registry id: `github/bruce601080102/ccc-mcp`
Status: unknown

## Tools (37)

- `advance_project`: PM refines one completed Agent result; backend starts the next role and waits for progress. Continue this turn whenever workflow says so. If the result has a no
- `bootstrap_project`: Recover current work, decisions, blockers and handoff without any chat history.
- `build_handoff`: Build a role-specific handoff. Over budget, bounded history lists (decisions, agent_results_awaiting_refinement) are compressed oldest-first; budget_omitted lis
- `call_installed_mcp_tool`: Call one tool of a local MCP server the operator installed for this project (see list_installed_mcp_tools). Only server+tool pairs the operator enabled with the
- `cancel_task`: Cancel a task and request termination of its worker's agent process tree.
- `collect_context_updates`: Collect events, reports and decisions for PM-driven context optimization.
- `commit_context_patch`: Revalidate optimistic version and commit context atomically; preserves evidence.
- `create_managed_project`: Create a new project only inside the locally configured projects directory, with a Git baseline.
- `create_task`: Compatibility alias: start the project request, dispatch SA, and wait. Do not call dispatch_agent again; continue according to workflow. If the result has a non
- `dispatch_agent`: Dispatch the configured provider with real execution and wait for progress; no simulated Agent option. If the result has a non-null action_required, do NOT end 
- `get_approval_status`: Read approval records; this tool cannot grant approval.
- `get_context`: Read a role-specific context package with a pinned version and provenance.
- `get_context_history`: Read immutable context versions and diffs (paginated).
- `get_meeting_transcript`: Full, unclipped Meeting Mode record (pre-implementation check, each round's SD/RD question, SA answer, PM decision). Call this and show `markdown` to the user w
- `get_project_settings`: Read role/provider/model/effort/fallback and operator-authorized paths.
- `get_source_reference`: Get the SHA256 of one registered project-relative evidence file.
- `get_task_result`: Read raw agent reports, immutable handoffs and observed evidence.
- `get_task_status`: Read the current project workstream; task_id is only for historical/internal lookup.
- `get_task_usage`: Read host invocation evidence and native CLI token usage; unavailable is never fabricated as zero.
- `get_workspace_edit`: Read one EDIT or multi-file BATCH: diffs, exact hashes, approval status and application receipt.
- `list_installed_mcp_tools`: Local MCP servers (for example codebase-memory-mcp) the operator installed for this project, with only the tools they enabled and each tool's description and in
- `list_projects`: List operator-registered repository roots.
- `list_workspace`: List one folder inside registered project, recorded task worktree, or operator-granted read root.
- `preview_role_prompt`: Preview exactly what a role (SA/SD/RD/SD-RD/REVIEW) would be sent given current settings, without dispatching anything.
- `propose_context_patch`: Collect/optimize/validate PM context; persist proposal and return reviewable diff.
- `read_workspace`: Read bounded UTF-8 source with SHA256; credentials and managed metadata are excluded.
- `recover_workers`: Clear executions stuck QUEUED/RUNNING with no live worker holding their lock (the worker crashed or never started); only touches executions that are provably no
- `resolve_clarification`
- `resume_pending_dispatch`: Finish an advance_project round interrupted after Context was committed but before the next role was confirmed dispatched (crash, worker spawn failure, a transi
- `review_changes`: Queue an independent Codex read-only review.
- `start_project_request`
- `submit_agent_report`: Finish an active ChatGPT role; save raw report, context suggestions and host-observed file evidence.
- `submit_clarification_request`: Finish an active ChatGPT Meeting Mode SD/RD check (the handoff whose expected_report_fields are blocking_question, no_blocking_question, rationale). Read-only r
- `submit_clarification_response`: Finish an active ChatGPT Meeting Mode SA answer (the handoff whose expected_report_fields are response_type, content). Read-only role. Meeting Mode then continu
- `validate_context`: Check source hashes, projection drift and evidence integrity.
- `wait_for_task`: Wait for background Agent work to settle. If timed_out or must_continue_in_this_turn is true, do not end the chat turn: wait again or perform the returned PM/Ch
- `write_task_file`: Edit the authorized project's original files through an approved implementation execution. SA/REVIEW stays read-only.

Measured by Glimind (https://glimind.com): MCP handshake + tool list only, no tool is ever called. CC BY 4.0.