mcpField
H
hermes-agent-mcp

hermes-agent-mcp

Local
github.com/woonyong-choiAI & Agents

About hermes-agent-mcp

hermes-agent-mcp is a local stdio MCP server for operating an installed Hermes Agent through its CLI. It lets MCP clients manage tasks, cron jobs, configuration, gateway, and health checks without exposing Hermes to the network.

Key features

  1. 01Submit one-turn tasks to Hermes
  2. 02Manage cron jobs
  3. 03Read and write typed configuration
  4. 04Check and restart the gateway
  5. 05Inspect skills, sessions, and model details
  6. 06Control shell and write access with settings

Use cases

  1. 01Manage Hermes from an MCP client without a terminal
  2. 02Review or edit scheduled jobs
  3. 03Change configuration with typed values
  4. 04Check Hermes health and restart its gateway

MCP support

It exposes Hermes CLI operations as MCP tools over local stdio for MCP clients. The server runs as a child process and does not listen on a network port.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"woonyong-choi-hermes-agent": {
"command": "uvx",
"args": [
"hermes-agent-mcp"
],
"env": {
"HERMES_HOME": "<HERMES_HOME>",
"HERMES_MCP_ALLOW_WRITE": "<HERMES_MCP_ALLOW_WRITE>",
"HERMES_MCP_ALLOW_SHELL": "<HERMES_MCP_ALLOW_SHELL>"
}
}
}
}
Run commanduvx hermes-agent-mcp
Environment variables to set
HERMES_HOMEHermes data directory (default ~/.hermes)
HERMES_MCP_ALLOW_WRITEAllow state-changing tools (default 1)
HERMES_MCP_ALLOW_SHELLEnable the shell tool (default 0)

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
pypihermes-agent-mcp0.1.1

Tools

16

Saved tool list · updated 2w ago

This tool takes no parameters.

Details

The maintainer has not added details yet. Check the README in the repository.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.