All servers / Project management / Agile Monster MCP server
Agile Monster MCP server
Official Model Context Protocol (MCP) server Orchestrator for Agile Monster (Cursor, Claude Code, Antigravity, Codex, Hermes, Windsurf)
Tested by ConnectATDScore 90 out of 100. Tested 2026-11-18 on package version 1.0.32. Package: @agilemonster/mcp-server · source
Score breakdown
| Runs | 18 / 20 | |
|---|---|---|
| Tool descriptions | 20 / 20 | |
| Package safety | 20 / 20 | |
| Maintenance | 20 / 20 | |
| Adoption | 12 / 20 |
What we saw
- Starts and answers the MCP handshake: yes (2.5 seconds including download)
- Tools offered: 14
- Last published: 2026-11-14
- Weekly downloads (npm): 2,790
- License: MIT · Direct dependencies: 1
Want this server set up for your team?
ConnectATD builds AI automation and wires up MCP servers like this one. Tell us what you are trying to do.
Talk to ConnectATDTools and how they are described
Agents choose tools from these descriptions. Under each name you can see how many of its parameters are explained.
agilemonster_get_context2 of 2 parameters describedInspect Agile Monster board and project context for this repository. Automatically reads .agilemonster.json if present or finds matching board.
agilemonster_init_project4 of 4 parameters describedBind the current repository to an Agile Monster workspace and board by creating a .agilemonster.json file and generating AGENTS.md.
agilemonster_list_my_tasks3 of 3 parameters describedList tasks assigned to the AI agent on Agile Monster boards (queued, in_progress, waiting_for_input, review).
agilemonster_claim_task3 of 3 parameters describedClaim a task assigned to this agent to begin working on it. Marks card as "in_progress" in Agile Monster.
agilemonster_ask_question4 of 4 parameters describedAsk the user a clarifying question about the task. Posts a tagged comment on the card and updates status to "waiting_for_input".
agilemonster_add_progress5 of 5 parameters describedPost a progress update or implementation notes to the Agile Monster task activity/comments.
agilemonster_record_spend5 of 5 parameters describedRecord LLM token and cost consumption on a card to enforce circuit breakers against runaway billing.
agilemonster_set_budget3 of 3 parameters describedConfigure spend and token circuit-breaker limits for an Agile Monster task to protect against infinite loops.
agilemonster_submit_for_review7 of 7 parameters describedHandoff task to human: moves card to Testing/QA/Review column, reassigns the card to the human who requested it, sets status to "review", and posts step-by-step verification instructions.
agilemonster_create_followup_tasks3 of 3 parameters describedSuggest and create follow-up tasks on the board (e.g., "Deploy to Test", "Deploy to Production", "Write integration tests").
agilemonster_block_task3 of 3 parameters describedBlock a task and reassign back to human user with a reason (e.g. missing credentials, ambiguous requirements, or upstream blockers). Sets status to blocked / waiting_for_input.
agilemonster_complete_task3 of 3 parameters describedMark task as complete and advance to the board Done list after testing and verification pass. Adds structured completion comment detailing deployment status (automated CI/CD run or user-controlled trigger instructions).
agilemonster_get_deploy_profileno parametersHow THIS project is deployed: the route (GitHub Actions, local Docker Compose, deploy script, cloud CLI, manual), the exact command, confidence, the evidence behind it, alternatives found, and recent deployment history on this machine. Call this before deploying or before writing a deployment note, instead of guessing.
agilemonster_record_deployment8 of 8 parameters describedRecord how a deployment of this project actually went, so every future task (including cards started from the Agile Monster web app while no IDE is open) deploys the same proven way. Call it after you deploy successfully, when a deployment fails, or when the user tells you how the project is deployed (set pin=true).
Tested in a sandbox with an empty environment: no API keys, a throwaway folder, nothing from a real account. A passing test shows the server runs and responds. It is not a security audit.