Skip to main content
Glama
SongPilotAI

SongPilot MCP Server

Official
by SongPilotAI

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
LOG_LEVELNoLogging level (DEBUG, INFO, WARNING, ERROR)INFO
SONGPILOT_API_KEYYesYour SongPilot API key (sp_...)
SONGPILOT_MCP_BASE_URLNoAPI base URLhttps://mcp.songpilot.ai
SONGPILOT_WORKSPACE_IDYesYour workspace ID

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
run_orchestratorA

Run the SongPilot orchestrator to interact with AI agents.

This is the primary interface for interacting with SongPilot's AI system. The orchestrator routes your requests to appropriate specialists (visual-director, manager, publicist, etc.) based on your needs.

Args: message: Your request or question for the SongPilot AI. Examples: - "Create artwork for my song 'Midnight Dreams'" - "Help me plan a release strategy for my new album" - "Write a bio for my artist profile" - "Which of my songs are ready for release?"

session_id: Optional session identifier for conversation continuity.
           If omitted, the server maintains session continuity automatically.
           Use this if you want to explicitly reference a previous conversation.

context: Optional context about your current activity.
        Providing context helps the AI give more relevant responses:
        {
            "currentPage": "/songs",
            "activeTab": "albums",
            "focusedResource": {"type": "album", "name": "My Album"}
        }

ctx: FastMCP context (auto-injected, used for logging).

Returns: The AI's response as text. This may include suggestions, questions, generated content, or action items depending on your request.

Examples: >>> result = await run_orchestrator("Create artwork for my song 'Midnight Dreams'") >>> print(result) "I'd be happy to help create artwork for 'Midnight Dreams'! What style are you envisioning? Minimal, artistic, or something else?"

>>> # Continue conversation with context
>>> result = await run_orchestrator(
...     "Make it minimal with blue tones",
...     context={"currentPage": "/songs", "activeTab": "singles"}
... )

Raises: SongPilotError: If the API call fails (network error, auth error, etc.)

Note: - Session continuity is maintained automatically within a Claude conversation - The orchestrator remembers context from previous messages - API calls may take 10-30 seconds for complex generation tasks

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

A4/5.0

Scored across 1 tool

Disambiguation5/5

There is only one tool, so there is no possibility of an agent confusing it with another tool. Its purpose (routing natural-language requests to SongPilot specialists) is unambiguous by construction.

Naming Consistency5/5

The lone name 'run_orchestrator' follows a clear verb_noun snake_case pattern. With a single tool, consistency is trivially satisfied and the name is readable and descriptive.

Tool Count2/5

A single catch-all tool is very thin for the apparent breadth of the domain (artwork, release planning, bios, song status, artist profiles). The router pattern is deliberate, but agents get no discoverable capability surface beyond one opaque entry point.

Completeness2/5

There are no structured operations for core entities like songs, albums, artists, or releases — no list/get/create/update equivalents. Everything must go through free-text routing, so agents cannot perform predictable, verifiable actions and will fail on tasks requiring structured access.

Maintenance

ActivityMaintained
ResponsivenessNo issues