Schema | project-memory-mcp

project-memory-mcp

Describes the environment variables required to run the server.

Name	Required	Description	Default
`DATABASE_URL`	Yes	PostgreSQL connection string (required).
`EMBEDDING_MODEL`	No	Embedding model name (default: text-embedding-3-small).	text-embedding-3-small
`DATABASE_POOL_MAX`	No	Max PostgreSQL pool connections (default: 10).	10
`EMBEDDING_API_KEY`	Yes	API key for the OpenAI-compatible embedding service.
`EMBEDDING_BASE_URL`	No	Base URL for the embedding API (default: https://api.example.com/v1).	https://api.example.com/v1
`EMBEDDING_BATCH_SIZE`	No	Batch size for embedding requests (default: 64).	64
`EMBEDDING_DIMENSIONS`	No	Embedding vector dimensions (default: 1536).	1536
`PROJECT_MEMORY_HTTP_HOST`	No	HTTP server host (default: 127.0.0.1).	127.0.0.1
`PROJECT_MEMORY_HTTP_PORT`	No	HTTP server port (default: 8788).	8788
`PROJECT_MEMORY_HTTP_TOKEN`	No	Bearer token for REST endpoints (optional).
`EMBEDDING_REQUEST_TIMEOUT_MS`	No	Timeout for embedding API calls in ms (default: 30000).	30000
`DATABASE_POOL_IDLE_TIMEOUT_MS`	No	Idle client eviction timeout in ms (default: 30000).	30000
`PROJECT_MEMORY_PROJECT_CONFIG`	No	Path to project config JSON file (optional).
`PROJECT_MEMORY_SERVICE_CONFIG`	No	Path to service config JSON file (optional).
`DATABASE_POOL_CONNECTION_TIMEOUT_MS`	No	Connection timeout in ms (default: 10000).	10000

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.

Server capabilities have not been inspected yet.

Functions exposed to the LLM to take actions

Name	Description
No tools

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

This server cannot be deployed

ActivityStale

ResponsivenessNo issues