10 actions in 4 pieces of software · ranked by words, meaning and measured trust · 632 ms
- 1latticefound in code, not yet checkedno passport yet
MCP serveralexnodeland/lattice
- get_run
Return a run as JSON: its status, attempts, error, output and checkpoint.
- list_runs
List runs, newest first, as JSON lines, optionally of one rule, scope or status.
- retry_run
Make a run runnable now, with a fresh retry budget if it had finished.
- cancel_run
Cancel a run that has not finished, stopping it if it is running.
- get_run
- 2lattice-mcpfound in code, not yet checkedno passport yet
MCP serveraidenappl/lattice-mcp
- lattice_run_automation
Fire an automation now and wait for the verdict (a run is bounded to 50s). Returns {result, run}: result is succeeded | failed | skipped | disabled, and run.steps has every step's outcome. This performs the real actions — it redeploys containers and sends HTTP requests
- lattice_list_automation_runs
An automation's run history, newest first — the first thing to reach for when an automation 'didn't work'. Every firing is a row, including skipped ones (disabled, already running, no runner slot, stale schedule slot) with skip_reason; failed_step names the first failing step, error explains a refus
- lattice_run_automation
- 3lattice-graftfound in code, not yet checkedno passport yet
MCP serverjeromyjsmith/lattice-graft
- testrail_add_run
Create a new test run in a project
- testrail_add_run
- 4latticefound in code, not yet checkedno passport yet
MCP serversjlynch/lattice
- list_workflow_runs
- run_task
- start_workflow_run
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.