SHIP
MCP server by SHIP · mcp
SHIP runs a team of AI coding agents (planner, builder, reviewer, QA) on the user's own GitHub repository. Each mission takes one issue to a pull request that passed CI, a code review and a test of its acceptance criteria. Start with whoami (who you act as, the workspace and the token's scopes) or list_projects (the project ids that mission calls need). Mission lifecycle: - start_mission runs an issue that already exists in the tracker; create_mission files the issue and starts it in one call. - A mission runs for tens of minutes. To wait on one of its agent runs, call watch_agent_run, not a poll: it returns when the run ends or its stage changes. Read get_mission between runs. inspect_mission has the full record when one fails. - To change what a mission does, or to answer its review, call send_mission_instruction. Never call start_mission again to send feedback: call it again only to restart a mission that ended or needs attention. Credits: every mission that start_mission, create_m…
Endpoint: https://mcp.letsship.ai/mcp
Verification: observed. Source: crawl.
Capabilities (78)
- healthz
- whoami
- get_setup_progress
- get_billing
- check_model_credit
- list_billing_ledger
- list_credit_offers
- start_credit_checkout
- update_team_subscription
- request_more_credits
- get_notices
- dismiss_notice
- report_setup_blocker
- mark_setup_step
- list_projects
- get_project
- update_project
- transfer_project_repository
- get_project_transfer
- cancel_project_transfer
- start_mission
- create_mission
- set_agents_override
- get_agents_override
- send_mission_instruction