Skip to main content
Glama
Manikandaprabu99

Universal Knowledge MCP

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
PORTNoFallback server port when MCP_SERVER_PORT is not set, typically provided by PaaS platforms.
LOG_LEVELNoLog level. JSON logs are written to stderr; secrets are never logged.info
AUTO_MIGRATENoRun migrations at startup, useful on PaaS.false
DATABASE_URLYesPostgreSQL connection string. Required. One PostgreSQL database is used for everything.
EMBEDDINGS_URLNoOptional OpenAI-compatible embeddings endpoint, for example Ollama, used with pgvector.
MCP_AUTH_TOKENNoBootstrap admin bearer token for HTTP transport. Required for HTTP; minimum 32 characters.
MCP_USER_TOKENNostdio only: act as this user instead of the bootstrap admin.
MCP_SERVER_PORTNoServer port for Streamable HTTP. Falls back to PORT.3000
EMBEDDINGS_MODELNoOptional embeddings model name for the OpenAI-compatible embeddings endpoint.
MCP_AUTH_USER_IDNoBootstrap admin identity user id.owner
MCP_HTTP_SESSIONSNoHTTP session mode. Use stateless to survive restarts and cold starts better.stateful
DEFAULT_VISIBILITYNoDefault visibility for new documents. Valid values are private or shared.private
KNOWLEDGE_NAMESPACENoDefault project namespace for new documents.default

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

Server capabilities have not been inspected yet.

Tools

Functions exposed to the LLM to take actions

NameDescription

No tools

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Maintenance

ActivityMaintained
ResponsivenessNo issues