Connection check
local install
martin-loop
One system around coding agents to run, verify, recover, and hand off software work.
Tools
20
GitHub stars
—
Installs / wk
587
Licence
—
Transport
stdio
Last checked
never
Tools & capabilities
20 toolsRead from the published package source — this server runs locally, so there is no endpoint to query. Names are taken from the code, not observed at runtime, and descriptions are often absent.
martin_arcade
from source
martin_arcade_status
from source
martin_cancel
from source
Record a durable cancellation request for a Martin run. This writes a control receipt; it does not silently kill a process without evidence. Record a durable cancellation request for a Martin run. This writes a control receipt; it does not silently kill a process without evidence.
martin_continue
from source
Record a durable continue or resume request for a Martin run after a human pause or approval checkpoint. Record a durable continue or resume request for a Martin run after a human pause or approval checkpoint.
martin_create_pr
from source
martin_doctor
from source
Read-only environment and run-store diagnostics for the Martin MCP server. This is the expected first call before governed work begins. Read-only environment and run-store diagnostics for the Martin MCP server. This is the expected first call before governed work begins.
martin_dossier
from source
Alias for martin_run_dossier with support for JSON, Markdown, or GitHub PR formatting. Use after martin_run to understand what happened and whether the result is actually safe to t… Alias for martin_run_dossier with support for JSON, Markdown, or GitHub PR formatting. Use after martin_run to understand what happened and whether the result is actually safe to trust.
martin_get_attempt
from source
Load one Martin attempt summary with artifact directory references for a canonical run. Load one Martin attempt summary with artifact directory references for a canonical run.
martin_get_run
from source
Load one Martin run and return its budget, cost, verification, artifact, and canonical path summary. Load one Martin run and return its budget, cost, verification, artifact, and canonical path summary.
martin_get_verification_results
from source
Load structured verification evidence for a MartinLoop run — verifier commands, pass/fail outcomes, and contradiction signals — from stored loop events and ledger entries. Load structured verification evidence for a MartinLoop run — verifier commands, pass/fail outcomes, and contradiction signals — from stored loop events and ledger entries.
martin_inspect
from source
Summarise Martin Loop run records from a saved loop file or run-store directory. Summarise Martin Loop run records from a saved loop file or run-store directory.
martin_list_runs
from source
List recent Martin runs from the run store with lightweight filters for status, lifecycle, engine metadata, and recency. List recent Martin runs from the run store with lightweight filters for status, lifecycle, engine metadata, and recency.
martin_logs
from source
Read recent MartinLoop events, ledger entries, and operator control receipts for a single run. Read recent MartinLoop events, ledger entries, and operator control receipts for a single run.
martin_pause
from source
Record a durable pause request for a Martin run so humans and runtimes can see that execution should pause before risky follow-up work. Record a durable pause request for a Martin run so humans and runtimes can see that execution should pause before risky follow-up work.
martin_plan
from source
Read-only planning step that turns an objective into a scoped implementation plan, verifier proposal, policy pack, and risk recommendation. Use before preflight and before any real… Read-only planning step that turns an objective into a scoped implementation plan, verifier proposal, policy pack, and risk recommendation. Use before preflight and before any real coding run.
martin_preflight
from source
Read-only validation of a planned Martin run before any execution or spend. This is the last required step before martin_run. Read-only validation of a planned Martin run before any execution or spend. This is the last required step before martin_run.
martin_run
from source
Execute a governed Martin Loop run on a coding task and return the run summary, spend, artifact rollup, and verification state. This hard-blocks until martin_doctor, martin_estimat… Execute a governed Martin Loop run on a coding task and return the run summary, spend, artifact rollup, and verification state. This hard-blocks until martin_doctor, martin_estimate, martin_plan, and martin_preflight receipts exist for the same task.
martin_run_dossier
from source
Return the full governed execution dossier for one Martin run, including attempts, events, artifacts, and related discovery surfaces. Return the full governed execution dossier for one Martin run, including attempts, events, artifacts, and related discovery surfaces.
martin_status
from source
Return the current budget and cost state of a Martin loop record. Return the current budget and cost state of a Martin loop record.
martin_triage_runs
from source