Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
MCP_TOKENNoBearer token for calling downstream API
MCP_BASE_URLNoDownstream API root URL (required if spec cannot infer)
OPENAI_MODELNoModel name
CORTEX_KB_DIRNoKnowledge base vector index persistence directorydata/knowledge_db
OPENAI_API_KEYYesLLM API Key (required)
CORTEX_API_HOSTNoHTTP service listen host0.0.0.0
CORTEX_API_PORTNoHTTP service listen port8000
CORTEX_RAG_DOCSNoComma-separated paths to RAG source documents
MCP_SWAGGER_URLNoOpenAPI / Swagger document URL or local path (default: Petstore example if not set)
OPENAI_BASE_URLNoCompatible gateway URL
CORTEX_AGENT_LOGNoEnable debug logs for agent/MCP
CORTEX_MEMORY_DBNoSQLite session database pathdata/memory.db
CORTEX_ENABLE_RAGNo0 to disable RAG, 1 to enable with existing index only
HUB_MAX_REVISION_ROUNDSNoNumber of revision rounds for Reflection1
CORTEX_DEFAULT_SESSION_IDNoDefault session namespace when none providedmem:tester_id:default
CORTEX_SESSION_ID_TEMPLATENoTemplate for short session keysmem:{session_id}:default
CORTEX_ENABLE_LONG_TERM_MEMORYNoEnable long-term memory (Neo4j/Qdrant) (default false)false

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

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/Zhong-y-j/Agent-Cortex'

If you have feedback or need assistance with the MCP directory API, please join our Discord server