Spaceship MCP
Provides tools to manage AI agents, projects, and executions on the Spaceship AI platform, allowing users to create, update, and run agents, as well as monitor execution status and retrieve logs.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Spaceship MCPrun the 'Support Bot' agent to process a refund for order #1234"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
███████╗██████╗ █████╗ ██████╗███████╗███████╗██╗ ██╗██╗██████╗
██╔════╝██╔══██╗██╔══██╗██╔════╝██╔════╝██╔════╝██║ ██║██║██╔══██╗
███████╗██████╔╝███████║██║ █████╗ ███████╗███████║██║██████╔╝
╚════██║██╔═══╝ ██╔══██║██║ ██╔══╝ ╚════██║██╔══██║██║██╔═══╝
███████║██║ ██║ ██║╚██████╗███████╗███████║██║ ██║██║██║
╚══════╝╚═╝ ╚═╝ ╚═╝ ╚═════╝╚══════╝╚══════╝╚═╝ ╚═╝╚═╝╚═╝spaceship-mcp
MCP server for Spaceship AI — manage agents from Claude Code, Cursor, and any other MCP client.
Quick start
Claude Code / Claude Desktop
Add to your .mcp.json (project-level) or claude_desktop_config.json:
{
"spaceship": {
"command": "uvx",
"args": ["spaceship-mcp"],
"env": {
"SPACESHIP_API_KEY": "sk_live_...",
"SPACESHIP_API_URL": "https://spaceshipai.io"
}
}
}Get your API key from the Spaceship AI dashboard under Settings → API Keys.
Local development (pointing at localhost)
{
"spaceship": {
"command": "uvx",
"args": ["spaceship-mcp"],
"env": {
"SPACESHIP_API_KEY": "sk_live_...",
"SPACESHIP_API_URL": "http://localhost:3000"
}
}
}Environment variables
Variable | Required | Default | Description |
| Yes | — | Your Spaceship API key ( |
| No |
| Override for local dev or staging |
Tools
Tool | What it does |
| List all projects in your org |
| List agents, optionally filtered by project |
| Get full details of a single agent |
| Create an agent (pass |
| Update name, prompt, or tools; re-scaffold with |
| Permanently delete an agent (irreversible) |
| Start an async run; returns |
| Poll run status: queued → running → completed / error / cancelled / paused |
| Fetch full chronological event log for a completed run |
| List recent runs for an agent with status and duration |
| Quick sync test (15s timeout) — start a run and wait for it to finish |
| List tools available to attach to agents |
Typical workflow in Claude Code
list_projects
→ list_agents project_id=1
→ create_agent name="Support Bot" project_id=1 description="Handles customer refund requests"
→ run_agent agent_id="..." prompt="Process refund for order #1234"
→ get_run_status agent_id="..." execution_id="..."
→ get_run_logs agent_id="..." execution_id="..."Or use test_agent to run and wait in one step:
test_agent agent_id="..." prompt="Hello, can you help me?"Development
python3 -m venv .venv
source .venv/bin/activate
pip install -e ".[dev]"
pytest tests/ -vThis server cannot be installed
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Spaceship-AI/spaceship-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server