Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
AGENT_RELAY_BINDNoHTTP bind address127.0.0.1
AGENT_RELAY_PORTNoHTTP port8787
AGENT_RELAY_TOKENYesBearer token; minimum 32 characters
AGENT_RELAY_ADAPTERNoAgent adapter; only 'herdr' is currently implementedherdr
AGENT_RELAY_HERDR_BINNoHerdr executable pathherdr
AGENT_RELAY_STATE_DIRNoJobs and result files~/.local/state/agent-relay
AGENT_RELAY_POLICY_FILENoHot-reloaded policy file~/.config/agent-relay/policy.md
AGENT_RELAY_HERDR_TARGETNoUnique live Herdr agent namesupervisor
AGENT_RELAY_TASK_TIMEOUT_MSNoAgent task timeout in milliseconds1800000
AGENT_RELAY_MAX_PROMPT_CHARSNoMaximum submitted prompt size10000
AGENT_RELAY_RESULT_MAX_CHARSNoMaximum result returned to the MCP client1200

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

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/simozampa/agent-relay'

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