Schema | KDB.AI MCP Server

KDB.AI MCP Server

Official

Describes the environment variables required to run the server.

Name	Required	Description	Default
`KDBAI_DB_K`	No	Default number of results to return from vector searches	5
`KDBAI_DB_HOST`	No	KDB.AI server hostname or IP address	127.0.0.1
`KDBAI_DB_MODE`	No	API mode: 'qipc' or 'rest'	qipc
`KDBAI_DB_PORT`	No	KDB.AI server port number	8082
`KDBAI_DB_RETRY`	No	Number of connection retry attempts on failure	2
`KDBAI_MCP_HOST`	No	HTTP server bind address - ignored when using stdio transport	127.0.0.1
`KDBAI_MCP_PORT`	No	HTTP server port - ignored when using stdio transport	7000
`KDBAI_DB_PASSWORD`	No	Password for KDB.AI authentication
`KDBAI_DB_QIPC_TLS`	No	Enable TLS for QIPC mode (true/false)	False
`KDBAI_DB_USERNAME`	No	Username for KDB.AI authentication
`KDBAI_MCP_LOG_LEVEL`	No	Logging verbosity level	INFO
`KDBAI_MCP_TRANSPORT`	No	Communication protocol: 'stdio' or 'streamable-http'	streamable-http
`KDBAI_MCP_SERVER_NAME`	No	Name identifier for the MCP server instance	KDBAI_MCP_Server
`KDBAI_DB_DATABASE_NAME`	No	Default database name to use for operations	default
`KDBAI_DB_REST_PROTOCOL`	No	Select protocol for REST mode, not considered for QIPC mode	http
`KDBAI_DB_SPARSE_WEIGHT`	No	Weight for text similarity in hybrid search (0.0-1.0)	0.3
`KDBAI_DB_VECTOR_WEIGHT`	No	Weight for vector similarity in hybrid search (0.0-1.0)	0.7
`KDBAI_DB_EMBEDDING_CSV_PATH`	No	Path to embeddings csv	src/mcp_server/utils/embeddings.csv

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

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/KxSystems/kdbai-mcp-server'

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