Skip to main content
Glama
Sign In
deenesjakoruzh
Spaceship MCP

Spaceship MCP

by Spaceship-AI
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote
       ███████╗██████╗  █████╗  ██████╗███████╗███████╗██╗  ██╗██╗██████╗    █████╗ ██╗
       ██╔════╝██╔══██╗██╔══██╗██╔════╝██╔════╝██╔════╝██║  ██║██║██╔══██╗  ██╔══██╗██║
       ███████╗██████╔╝███████║██║     █████╗  ███████╗███████║██║██████╔╝  ███████║██║
       ╚════██║██╔═══╝ ██╔══██║██║     ██╔══╝  ╚════██║██╔══██║██║██╔═══╝   ██╔══██║██║
       ███████║██║     ██║  ██║╚██████╗███████╗███████║██║  ██║██║██║       ██║  ██║██║
       ╚══════╝╚═╝     ╚═╝  ╚═╝ ╚═════╝╚══════╝╚══════╝╚═╝  ╚═╝╚═╝╚═╝       ╚═╝  ╚═╝╚═╝

Spaceship AI MCP Server

MCP server for Spaceship AI — build, run, and manage AI agents directly from Claude Code, Cursor, VS Code, and Windsurf.

Quick start

Don't want to manually configure your MCP server?

Run spaceshipai@latest init to set everything up automatically with one command:

npx spaceshipai@latest init

This works with Claude Code, Cursor, VS Code, and Windsurf. It will authenticate via your browser, create a Spaceship API key for you, and configure your editor automatically.

Related MCP server: MCP Plus

Manual installation

If you prefer to configure manually, add the following to your IDE's MCP config file.

Claude Code — run in your terminal:

claude mcp add --scope user --transport stdio spaceship --env SPACESHIP_API_KEY=sk_live_... -- uvx spaceship-mcp

Or add to ~/.claude.json:

{
  "mcpServers": {
    "spaceship": {
      "command": "uvx",
      "args": ["spaceship-mcp"],
      "env": {
        "SPACESHIP_API_KEY": "sk_live_..."
      }
    }
  }
}

Cursor — add to ~/.cursor/mcp.json:

{
  "mcpServers": {
    "spaceship": {
      "command": "uvx",
      "args": ["spaceship-mcp"],
      "env": {
        "SPACESHIP_API_KEY": "sk_live_..."
      }
    }
  }
}

VS Code — add to ~/.vscode/mcp.json:

{
  "servers": {
    "spaceship": {
      "command": "uvx",
      "args": ["spaceship-mcp"],
      "env": {
        "SPACESHIP_API_KEY": "sk_live_..."
      }
    }
  }
}

Windsurf — add to ~/.codeium/windsurf/mcp_config.json:

{
  "mcpServers": {
    "spaceship": {
      "command": "uvx",
      "args": ["spaceship-mcp"],
      "env": {
        "SPACESHIP_API_KEY": "sk_live_..."
      }
    }
  }
}

Get your API key from spaceshipai.io under Settings → API Keys.

Tools

Projects

Tool

Description

list_projects

List all projects in your organization

Agents

Tool

Description

list_agents

List agents, optionally filtered by project

get_agent

Get full details of a single agent including its system prompt and tools

create_agent

Create an agent — pass description for auto-generated system prompt

update_agent

Update name, prompt, or tools; re-scaffold by passing a new description

delete_agent

Permanently delete an agent and all its logs, memories, and threads

Running agents

Tool

Description

run_agent

Start an async run; returns execution_id for polling

get_run_status

Poll status: queued → running → completed / error / cancelled

get_run_logs

Fetch the full chronological event log for a completed run

list_executions

List recent runs for an agent with status and duration

test_agent

Quick sync test — runs an agent and waits up to 15s for the result

Orchestrations

Tool

Description

list_orchestrations

List orchestrations, optionally filtered by project

get_orchestration

Get full details of an orchestration including its members and tools

run_orchestration

Start an async orchestration run; returns execution_id

test_orchestration

Quick sync test — runs an orchestration and waits up to 15s for the result

Tools

Tool

Description

list_tools

List built-in and custom tools available to attach to agents

Example prompts

Once installed, you can talk to your agents naturally in any supported IDE:

List my projects, then show me all agents in the "production" project.
Create an agent called "Support Bot" in project 12 that handles customer refund requests.
Run the "Data Processor" agent with the prompt "Summarize last week's sales data".
Check the status of execution abc-123 for agent xyz-456, then show me the logs.
Test the "Email Classifier" agent with "Is this email spam: win a free iPhone now!"
List my orchestrations in the "production" project, then run the "Data Pipeline" orchestration.
Test the "Research Team" orchestration with input {"topic": "AI safety"} and show me the result.

Configuration

Variable

Required

Default

Description

SPACESHIP_API_KEY

Yes

—

Your API key (sk_live_...)

SPACESHIP_API_URL

No

https://spaceshipai.io

Override for local dev or staging

Development

python3 -m venv .venv
source .venv/bin/activate
pip install -e ".[dev]"
pytest tests/ -v

License

MIT

Available Tools

16 tools
create_agentA

Create a new agent.

Pass description to let the server auto-generate a detailed system prompt (scaffold_applied: true in the response). Pass prompt to set the system prompt directly. At least one of description or prompt is recommended.

Args: name: Display name for the agent. project_id: UUID of the project this agent belongs to (from list_projects). description: Natural-language description — triggers server-side prompt scaffolding. prompt: Raw system prompt to use as-is (skips scaffolding). framework: Execution framework. Defaults to langchain. tools: List of tool UUIDs to attach (from list_tools).

Inputs: name (required), project_id (required), description, prompt, +2 more.

delete_agentA

PERMANENTLY delete an agent and all its logs, memories, and threads.

This action is irreversible. Double-check the agent_id before calling.

Args: agent_id: The agent's UUID.

Inputs: agent_id (required).

get_agentA

Get full details of a single agent including its tools and system prompt.

Args: agent_id: The agent's UUID (from list_agents or create_agent).

Inputs: agent_id (required).

get_orchestrationA

Get full details of a single orchestration including its members and tools.

Args: orchestration_id: The orchestration's UUID (from list_orchestrations).

Inputs: orchestration_id (required).

get_run_logsA

Fetch the full event log for a completed run in chronological order.

Returns every event (start, tool_call, memory_access, completion, error, …) so you can see exactly what the agent did and what it returned.

Args: agent_id: The agent's UUID. execution_id: The execution UUID returned by run_agent.

Inputs: agent_id (required), execution_id (required). Returns: result

get_run_statusA

Poll the status of a specific run.

Status values: queued → running → completed | error | cancelled | paused (waiting for approval).

Poll every 3-5 seconds. Most agents complete within 30-60 seconds.

Args: agent_id: The agent's UUID. execution_id: The execution UUID returned by run_agent.

Inputs: agent_id (required), execution_id (required).

list_agentsA

List agents in the organization, optionally filtered by project.

Pass project_id (UUID from list_projects) to scope the results to a single project. Each agent record includes its tools and configuration.

Inputs: project_id, limit. Returns: result

list_executionsA

List recent runs for an agent with their status and duration.

Useful for reviewing run history or checking whether a previous run succeeded before starting a new one.

Args: agent_id: The agent's UUID. limit: Number of runs to return (default 10, max 50).

Inputs: agent_id (required), limit. Returns: result

list_orchestrationsA

List orchestrations in the organization, optionally filtered by project.

Pass project_id (UUID from list_projects) to scope results to a single project. Each orchestration includes its members and their attached tools.

Inputs: project_id, limit. Returns: result

list_projectsB

List all projects in the authenticated organization.

Use this to discover which projects exist before listing or creating agents. Returns each project's id, name, and slug.

Inputs: limit. Returns: result

list_toolsA

List all tools available to attach to agents.

Returns both built-in tools (shared across all orgs) and custom tools belonging to your organization. Use the uuid field when creating or updating agents with the tools parameter.

Inputs: no named parameters. Returns: result

run_agentA

Start an asynchronous agent run and return immediately.

Returns an execution_id — use get_run_status to poll for completion or get_run_logs to fetch the full output once done.

Args: agent_id: The agent's UUID. prompt: The user message / task for the agent to execute. thread_id: Conversation thread UUID for memory continuity across runs. params: Optional extra parameters passed to the agent.

Inputs: agent_id (required), prompt (required), thread_id, params.

run_orchestrationA

Start an asynchronous orchestration run and return immediately.

Returns an execution_id — use test_orchestration to block until completion or poll /executions for status updates.

Args: orchestration_id: The orchestration's UUID. input_data: Input data passed to the orchestration (e.g. {"query": "…"}). params: Optional extra execution parameters.

Inputs: orchestration_id (required), input_data, params.

test_agentA

Quick synchronous test of an agent with a 90-second timeout.

Starts a run and polls every 2 seconds until it completes (or times out). Reports progress via MCP notifications while waiting. Returns the final status and execution_id. Use get_run_logs afterwards to see the output.

For production usage, prefer run_agent + get_run_status (non-blocking).

Args: agent_id: The agent's UUID. prompt: The test prompt to send.

Inputs: ctx (required), agent_id (required), prompt (required).

test_orchestrationA

Quick synchronous test of an orchestration with a 90-second timeout.

Starts a run and polls every 2 seconds until it completes (or times out). Reports progress via MCP notifications while waiting. Returns the final status and execution_id.

Args: orchestration_id: The orchestration's UUID. input_data: Optional input data for the orchestration run.

Inputs: ctx (required), orchestration_id (required), input_data.

update_agentA

Update an agent's name, prompt, or tools.

Providing description re-runs server-side prompt scaffolding and overwrites the current system prompt. Providing prompt sets it directly. Providing tools replaces the full tool list.

Args: agent_id: The agent's UUID. name: New display name. description: New description — triggers re-scaffolding. prompt: New raw system prompt. tools: Replacement list of tool UUIDs.

Inputs: agent_id (required), name, description, prompt, +1 more.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Deploy Server
    Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

    TDQS

    A4.2/5.0

    Scored across 16 tools

    Disambiguation5/5

    All tools have clearly distinct purposes: create vs delete vs get vs list for agents, orchestrations, etc. Even similar tools like get_run_logs and get_run_status target different aspects of runs (logs vs status). test_agent and run_agent differ in synchronous vs asynchronous execution. No ambiguity.

    Naming Consistency5/5

    All tool names consistently follow the verb_noun pattern with underscores (e.g., create_agent, get_run_status, list_projects). No mixing of camelCase or other styles. Very predictable.

    Tool Count5/5

    16 tools is appropriate for a platform managing agents and orchestrations. It covers essential operations without being overwhelming. Each tool earns its place.

    Completeness4/5

    The tool set covers agent lifecycle (CRUD), run management (run, test, status, logs), orchestration operations (list, get, run, test), and listing of projects/tools. Missing delete/update for orchestrations and projects, but those may be out of scope. Minor gaps, but core workflows are complete.

    Resources

    Related MCP Connectors

    Related MCP Servers

    • SpaceTraders MCP Server

      TheValverde
      A
      license
      Not graded
      quality
      D
      maintenance
      An MCP server that enables AI agents to interact with the SpaceTraders API, managing agents, fleets, contracts, and trading operations in the SpaceTraders universe.
      MIT

    • MCP Plus

      David3u
      F
      license
      Not graded
      quality
      D
      maintenance
      A lightweight MCP server that enhances AI agents with tools for codebase analysis, task delegation to sub-agents, multi-agent coordination through chatrooms, and project todo management.
      -

    • Orchestration MCP

      dufangshi
      F
      license
      A
      quality
      D
      maintenance
      A TypeScript MCP server for launching, tracking, and managing external coding-agent runs across local and remote backends like Codex and Claude Code. It allows top-level agents to orchestrate subagents through tools for spawning tasks, polling events, and handling interactive sessions.
      7
      2
      -

    • anchor-mcp

      thewillmoss
      A
      license
      A
      quality
      D
      maintenance
      A portable MCP server that provides a shared persistent working state for AI coding agents, managing tasks, plans, notepads, memory, and project rules across different tools like Claude Code, OpenCode, and Cursor.
      6
      14 npm
      MIT