Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
AI_R_EXTRASNoOptional extras to install: 'tokens', 'semantic', or 'http'. Used during installation, not at runtime.
AI_R_MCP_HOSTNoBind host for the HTTP transport.127.0.0.1
AI_R_MCP_PORTNoPort for the HTTP transport.8756
AI_R_HTTP_TOKENNoBearer token for HTTP transport. Required if AI_R_MCP_ALLOW_REMOTE=1.
AI_R_MCP_IDLE_SECNoIdle self-exit threshold for the HTTP server.
AI_R_MCP_TRANSPORTNoTransport for the MCP server: 'stdio' (default) or 'http'.stdio
AI_R_MCP_ALLOW_REMOTENoSet to '1' to allow non-loopback bind. Requires AI_R_HTTP_TOKEN.0
AI_R_SEMANTIC_THREADSNoMaximum CPU threads for onnxruntime semantic re-ranking.2
AI_R_SEMANTIC_IDLE_SECNoIdle seconds before unloading the semantic model (frees ~118 MB RAM).300
AI_R_HAYSTACK_CACHE_MAXNoSearch cache ceiling by entry count.
AI_R_HAYSTACK_CACHE_CHARS_MAXNoSearch cache ceiling by total size.

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/pro-target/ai-r'

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