AI & Machine Learning

letsship.ai

MCP server exposing SHIP workspace management tools for identity/RBAC, setup progress, billing credits and ledger, and API health.

1 endpoint71 known toolsFirst detected October 13, 2026Last detected October 13, 2026

ENDPOINT 1

https://mcp.letsship.ai/mcp

No auth detected

MCP server metadata

Name: ai.letsship/ship
Version: 0.24.4

Capabilities

tools

Server instructions

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: start_mission, create_mission and run_scheduled_task each start a mission, and every started mission spends workspace credits. Read get_billing before you start work for someone. Instructions to a mission that is already open are free. Handles are stable: an issue id (SHIP-123, WEB-42) and a project id name the same mission and project across calls and conversations. Keep them instead of searching again. A refusal that names a missing scope means this token cannot do that action. Ask the person to grant the scope; do not retry.

Known tools 71

healthz

Returns the upstream API status, environment, and version.

Inferred read-only

whoami

Returns the caller's identity, org, role, role-derived RBAC capabilities, and token scopes.

Inferred read-only

get_setup_progress

Read what the workspace has set up with SHIP so far, as the console's setup checklist shows it: up to 13 milestones in three groups, taken in order (get started, make it yours, make it autonomous).

Inferred read-only

get_billing

Read the workspace's credit balance by source and expiry, whether a new mission would start now, the per-mission credit ceiling, the project allowance and recent usage.

Inferred read-only

list_billing_ledger

List where the workspace's credits went, newest first: one entry per mission (its start, each further 3 agent-hours, and messages charged before messages became free), per grant, per adjustment and per expiry.

Inferred read-only

list_credit_offers

List what SHIP sells: the credit packs (credits, the tax-inclusive price in US dollars and the price per credit), the monthly plans under `team.

Inferred read-only

start_credit_checkout

Opens a payment page and returns its URL.

Potential side effects

update_team_subscription

Change the workspace's monthly plan subscription: plan switches between starter and scale from the next renewal on (nothing is charged or refunded for the current month; passing the current plan drops a waiting switch), or cancelAtPeriodEnd true ends it when the month already paid for ends, false resumes it before then.

Inferred read-only

request_more_credits

Ask for more credits for the workspace, saying what they are for.

Inferred read-only

get_notices

Read what needs attention in the workspace, critical first: a tracker connection its vendor no longer accepts (missions cannot start or report back until someone reconnects it), or credits running out.

Inferred read-only

dismiss_notice

Close a notice for the person this token acts for, as the console's close button does.

Inferred read-only

list_projects

List the projects accessible to the calling principal.

Inferred read-only

get_project

Fetch a single project by its UUID.

Inferred read-only

update_project

Change the settings of one project; a field you leave out keeps its value.

Inferred read-only

start_mission

Hand a mission off to the AI agent team.

Inferred read-only

create_mission

Create the tracker issue AND start the run in one call, for work that has no issue yet.

Potential side effects

set_agents_override

Patch one role's harness/model/effort/prompt for a single mission, layered over ship.

Inferred read-only

get_agents_override

Read the per-issue agents/baseBranch override record for one mission, or null when unset.

Inferred read-only

send_mission_instruction

Tell a mission what to change.

Inferred read-only

clear_agents_override

Delete the per-issue agents/baseBranch override — the mission resolves from ship.

Potential side effects

list_missions

List missions in the caller's accessible projects, newest activity first, with total for paging.

Inferred read-only

get_mission

Fetch one mission.

Inferred read-only

pause_mission

Hold a mission before its next stage.

Inferred read-only

resume_mission

Continue a paused mission.

Inferred read-only

stop_mission

Hard-stop a mission: every agent run of it stops and its work in progress is lost.

Inferred read-only

approve_mission_ceiling

A mission that reached its credit limit pauses until a member lets it continue.

Inferred read-only

merge_mission

Merge the mission's open pull request on GitHub with the repository's own merge method; the mission then becomes done, and the merge cannot be undone from here.

Inferred read-only

decline_mission

Close the mission's open pull request on GitHub without merging it; the mission becomes declined, and no call here reopens it.

Inferred read-only

set_mission_auto_merge

Set whether SHIP merges this mission's pull request by itself once the checks, the review and the test pass.

Inferred read-only

archive_mission

Hide a finished mission from list_missions and the board.

Inferred read-only

unarchive_mission

Show an archived mission in list_missions and on the board again.

Inferred read-only

set_mission_disposition

Record a person's reason for how a mission ended, which the delivery statistics use: product (real work, judged on its merits), probe (a test on purpose), superseded (another mission replaced it: give supersededBy) or takeover (a person finished the work outside SHIP); null clears it.

Inferred read-only

list_scheduled_tasks

List recurring agent missions (scheduled tasks) across the caller's accessible projects — schedule, enabled state, and next/last fire time for each.

Inferred read-only

list_scheduled_task_templates

Read-only gallery of curated scheduled task templates — a prepared prompt plus a suggested cadence.

Inferred read-only

get_scheduled_task

Fetch one scheduled task by id: its project, name, prompt, triggers (schedule), labels, template key, skip-if-previous-open setting, enabled state, and next/last run times.

Inferred read-only

create_scheduled_task

Create a recurring agent mission.

Potential side effects

update_scheduled_task

Patch a scheduled task's name, prompt, schedule, skip-guard, or enabled state — only the fields passed are changed.

Inferred read-only

run_scheduled_task

Fire a scheduled task immediately, bypassing both its schedule and the skip-if-previous-open guard — an explicit run always creates a new issue even while a prior fire's mission is still open.

Inferred read-only

list_scheduled_task_runs

Run history for one scheduled task, each row's status (dispatching/dispatched/skipped/failed) and, once its issue exists, the joined mission progress/cost.

Inferred read-only

delete_scheduled_task

Delete a scheduled task and its run history, which no call can bring back.

Potential side effects

list_mcp_servers

The MCP servers a project's repository declares in its MCP file (.

Inferred read-only

list_mcp_bindings

Every MCP server binding across the projects you can see in your org: project, server, transport, status, enabled roles, how it authenticates, and the NAMES of the credential fields set (never values).

Inferred read-only

set_mcp_config_path

Point the project at the repository file that declares its MCP servers, e.

Inferred read-only

bind_mcp_server

Create or update the binding for a server the repository declares.

Potential side effects

unbind_mcp_server

Delete a binding and its stored credential: no role receives the server from its next run.

Potential side effects

refresh_mcp_server_tools

Snapshot the bound server's current tools (with their readOnlyHint / destructiveHint annotations) for approval.

Inferred read-only

start_mcp_server_oauth

Begin the OAuth consent for a server bound as remote.

Inferred read-only

list_agent_runs

List the agent runs, live and finished, in the caller's accessible projects, newest first.

Inferred read-only

get_agent_run

Fetch one agent run: its run record, metric series (CPU/mem/disk over time), and the agent session summaries (role, outcome, cost, sessionId).

Inferred read-only

get_agent_run_logs

Fetch a session's log content from one agent run.

Inferred read-only

watch_agent_run

Wait on one agent run and follow what its agent does, instead of polling get_agent_run.

Inferred read-only

stop_agent_run

Stop the agent in one run before it finishes.

Inferred read-only

list_sandbox_templates

List the org's sandboxes (definitions agents start in), with each one's active version, size and latest build status.

Inferred read-only

get_sandbox_capacity

How many agents the org's missions are running at once against its limit (null while the org is unclassified), which missions wait for an agent slot and why, and whether every slot on the platform is taken.

Inferred read-only

list_sandbox_starters

Ready-made sandbox definitions (Python, Java, Go, Rust, Ruby) to create a sandbox from.

Potential side effects

list_sandbox_template_versions

Every saved version of a sandbox, newest first, with the active one marked and each one's latest build.

Inferred read-only

get_sandbox_build_log

A page of a build's log after sequence number `after`.

Inferred read-only

save_sandbox_template

Create a sandbox (omit templateId) or change one.

Potential side effects

activate_sandbox_template_version

Make a version the one missions use from their next dispatch.

Inferred read-only

build_sandbox_template

Build the sandbox's active version, or return the build already running for it.

Inferred read-only

list_sandbox_registries

The org's private package registries sandboxes install from: host, auth scheme, username.

Inferred read-only

save_sandbox_registry

Store (or replace) the credential for a registry host.

Inferred read-only

delete_sandbox_template

Delete a sandbox with all its versions and builds.

Potential side effects

delete_sandbox_registry

Delete the stored credential of a private registry (an id from list_sandbox_registries).

Potential side effects

list_environments

List per-mission preview environments for the caller's accessible projects.

Inferred read-only

get_environment

Fetch one preview environment's registry row (status, worker name, timestamps).

Inferred read-only

destroy_environment

Request teardown of a preview environment (its deployed Worker(s) + every provisioned datastore).

Inferred read-only

list_artifacts

List proof-of-work artifacts (QA screenshots/video/traces) for the caller's accessible projects.

Inferred read-only

get_artifact

Fetch one artifact's metadata + a long-lived signed serving url (open it to view the screenshot/video).

Inferred read-only

inspect_mission

Fetch the typed platform-inspection report for a mission, by its issue id.

Inferred read-only

list_orgs

List every organization on the platform with its owner email, member count, and pending invite status.

Potential side effects

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.ai-letsship-ship]
url = "https://mcp.letsship.ai/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "ai-letsship-ship": {
      "type": "http",
      "url": "https://mcp.letsship.ai/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: ai-letsship-ship
Remote MCP URL: https://mcp.letsship.ai/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "ai-letsship-ship": {
      "url": "https://mcp.letsship.ai/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "ai-letsship-ship": {
      "type": "http",
      "url": "https://mcp.letsship.ai/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "ai-letsship-ship",
  "transport": "streamable-http",
  "url": "https://mcp.letsship.ai/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Loading Trust v2 evidence…

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.