Schema | cortexdb

cortexdb

Describes the environment variables required to run the server.

Name	Required	Description	Default
`CORTEXDB_PATH`	No	Database file (default ~/.cortexdb/cortexdb.db)	~/.cortexdb/cortexdb.db
`OPENAI_API_KEY`	No	Server: embeddings API key (fallback for cortexdb-mcp-stdio); unset = lexical mode
`CORTEXDB_REMOTE`	No	Use a shared cortexdb-grpc at host:port (plaintext) or https://host (TLS, behind a proxy) instead of a local file
`OPENAI_BASE_URL`	No	Server: embeddings endpoint (fallback for cortexdb-mcp-stdio); unset = lexical mode
`CORTEXDB_EMBED_DIM`	No	Embedding dimension for both server and cortexdb-mcp-stdio	1536
`CORTEXDB_GRPC_TOKEN`	No	Bearer token for that server
`CORTEXDB_EMBED_MODEL`	No	Embedding model for both server and cortexdb-mcp-stdio	text-embedding-3-small
`CORTEXDB_REVIEW_GATE`	No	Server and cortexdb-mcp-stdio: 1 leaves proposed and rejected documents and memories out of search and recall (default off; a curation filter, not access control)	off
`CORTEXDB_EMBED_API_KEY`	No	cortexdb-mcp-stdio: API key for the embeddings endpoint (falls back to OPENAI_API_KEY); unset = lexical mode
`CORTEXDB_EMBED_BASE_URL`	No	cortexdb-mcp-stdio: OpenAI-compatible embeddings endpoint (falls back to OPENAI_BASE_URL); unset = lexical mode

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

ActivityActive

ResponsivenessResponsive