Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
HERMES_MODELNoModel identifier for chat completionshermes-agent
HERMES_API_KEYYesAPI_SERVER_KEY from the Hermes instance
HERMES_API_URLNoHermes gateway base URLhttp://localhost:8642
HERMES_TIMEOUTNoRequest timeout in seconds300

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

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
ask_hermesA

Delegate a task or question to the remote Hermes Agent.

Hermes runs a full agent loop with tool calling, so responses typically take 30 seconds to 5 minutes depending on complexity. Progress updates are streamed back while Hermes works.

Use this tool whenever you need Hermes to:

  • Control smart home devices via Home Assistant

  • Send or read WhatsApp messages

  • Interact with Google Workspace (Gmail, Calendar, Drive, Docs, Sheets)

  • Browse the web or scrape pages

  • Schedule cron jobs or recurring tasks

  • Access Hermes's persistent memory and skills

  • Perform any task that requires Hermes's own tool set

Args: prompt: The task instruction or question for Hermes. Be specific about what you want it to do. session_id: Optional session identifier. Pass the same value across related calls to let Hermes maintain conversational context (e.g. "draft an email" → "now send it").

hermes_healthA

Check if the remote Hermes Agent is reachable and healthy.

Returns the gateway health status including version information.

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/matthewmcneill/hermes-mcp-lite'

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