mark_complete

MCP tool from Claude Swarm by cj-vana

Mark feature done/failed (auto-retry)

How to use it

mark_complete is exposed by the Claude Swarm MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), and the mark_complete tool becomes available to the model automatically. See the full listing for setup details and every tool this server provides.

Install Claude Swarm

$claude mcp add claude-swarm --scope user -- node $(pwd)/dist/index.js

FULL CLAUDE SWARM LISTING

Other tools in Claude Swarm (39)

Add discovered work

auto_orchestrate

Hands-free orchestration until completion

check_all_workers

Check all active workers at once

Monitor review worker status

check_rollback_conflicts

Check for conflicts with other workers

Get worker output (supports heartbeat mode)

commit_progress

Create git checkpoint

configure_plan_mode

Enable/configure worker plan-before-implement mode

configure_ralph_loop

Enable/configure Ralph Loop execution defaults

configure_reviews

Set auto-review preferences

configure_verification

Set pre-completion verification commands

Compare plans and select winner

get_feature_complexity

Analyze complexity score

get_progress_log

View history (paginated)

get_review_results

Get aggregated findings (summary/detailed/json)

get_session_stats

Success rates and timing

get_worker_confidence

Get detailed confidence breakdown

implement_review_suggestions

Convert review findings into features

orchestrator_init

Start session with task and features

orchestrator_reset

Clear state and kill all workers

orchestrator_status

Get current state (use after compaction)

Pause and stop all workers

, python -m pytest

Resume paused session (supports crash recovery)

Reset failed feature for retry

rollback_feature

Restore files changed by a worker

Manually trigger code/architecture reviews

run_verification

Run tests/build commands

send_worker_message

Send instructions to running worker

set_confidence_threshold

Configure alert threshold

set_dependencies

Define feature dependencies

Analyze repo freshness and missing configs

Initialize repo configuration with parallel workers

shutdown_session

Graceful shutdown with checkpoint

start_competitive_planning

Spawn 2 planners with different approaches

start_parallel_workers

Launch multiple workers simultaneously

start_ralph_loop

Launch worker with Ralph Loop (fresh context per iteration)

Launch worker for a feature

validate_workers

Pre-flight validation before parallel execution