MCP.Market

Hermes Agent MCP server

by woonyong-choi·io.github.woonyong-choi/hermes-agent-mcp·v0.1.1
No reviews yet

Operate a local Hermes Agent install over stdio: tasks, cron, config, gateway, doctor. No network.

C65/100grade C
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
C65/100

full report

Adoption
New

0 stars45 downloads/wk

Reviews

Write one

Nobody has reviewed Hermes Agent yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Hermes Agent tools (16, 5 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • config_get

    Read one config.yaml value by dotted key, e.g. `display.show_reasoning`.

  • config_setwrite action

    Write one config.yaml value with an explicit type.

  • cron_createwrite action

    Create a scheduled job.

  • cron_edit

    Change a scheduled job in place, keeping its id and run history.

  • cron_list

    List scheduled jobs with their schedules and next run times.

  • cron_runwrite action

    Queue a job to run on the next scheduler tick instead of waiting.

  • cron_runs

    Show recorded execution attempts, newest first.

  • doctorwrite action

    Run `hermes doctor` and return its health report.

  • gateway_restart

    Restart the messaging gateway so configuration changes take effect.

  • gateway_status

    Show whether the messaging gateway is running and supervised.

  • hermes_ask

    Give the Hermes agent a task and return its reply.

  • hermes_status

    Report how this server is configured and whether the Hermes CLI answers.

  • model_info

    Show the configured default model and provider, plus Nous Portal status.

  • sessions_list

    List recent sessions so you can resume or inspect one.

  • shellwrite action

    Run a shell command on the Hermes host.

  • skills_list

    List installed skills with category, source and enabled state.

Public scan report

scanner v0.1.10 · 2026-11-01 · same rubric, same numbers if you re-run it

no findings
  • Code scan9 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancerepository not readable: repo not found3/15
  • Maintainer identityno repository or website to verify2/10
Overall 65/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Hermes Agent compares

Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
65/100
higher than 25% of 4,460 AI and agents servers
Tools
16
the typical AI and agents server has 6
Tools that change things
31%
typical: 0%. Fewer write tools means less an agent can break
Downloads a week
45
more than 37% of 1,538 AI and agents servers with a package

What its tools let an agent do: 11 read · 4 change · 1 run or deploy

Install Hermes Agent in Claude Code, Cursor or VS Code

claude mcp add hermes-agent-mcp -- uvx hermes-agent-mcp
Add to Cursor

What the publisher says

From the Hermes Agent repository's README, as published. We do not edit it. Read it on GitHub

hermes-agent-mcp

Operate your local Hermes Agent install from any MCP client — without exposing it to the network.

hermes-agent-mcp is a Model Context Protocol server that wraps the local hermes CLI over stdio. Point Claude Code, Cursor, Codex or any other MCP-capable agent at it and they can hand Hermes a task, read and change its config, manage cron jobs, restart the gateway and run hermes doctor — without a terminal and without ever seeing a token.

uvx hermes-agent-mcp

That is the whole install. No ports, no tunnel, no OAuth. It runs as a child process of your MCP client, on the same machine as Hermes, and nothing leaves the box.

mcp-name: io.github.woonyong-choi/hermes-agent-mcp

Why this exists

Hermes is a great always-on agent, but everything about operating it happens in a terminal: hermes cron edit, hermes config set, hermes gateway restart. If the agent that wants to do those things has no terminal — a desktop app, a coding assistant sandboxed away from your shell — it is stuck asking a human to type for it.

There is already a good project called hermes-mcp by mlennie. It solves a different problem: reaching Hermes remotely, over HTTP through a cloudflared tunnel with OAuth, so a hosted client can delegate tasks. If that is what you need, use it.

This project was written by someone who did not want that. Opening a Hermes gateway to the internet means an agent with a shell is one leaked token away from anyone. hermes-agent-mcp stays local on purpose:

  • it never listens on a port — MCP over stdio only
  • it never handles credentials — it calls the CLI, which already has them
  • it exposes the operations surface (cron, config, gateway, doctor, skills), not just "send a prompt"

Tools

bridge_ask keeps the phone in the loop

hermesask runs a one-shot CLI turn: fine for work, but it runs outside the gateway, so nothing appears in the user's chat. bridgeask goes through the gateway's own webhook adapter instead: your prompt is posted into the chat (prefixed ▸ Claude Code · — the caller name comes from HERMESMCPCALLER, the format from HERMESMCPLABELFORMAT), the agent runs inside the gateway with its full toolset, and the reply lands in the chat and* comes back to you. The person can pick the thread up on their phone as if they had typed it themselves.

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Grade history

  • 2026-11-01downgradeA → Cscore 65

Hermes Agent: common questions

Is Hermes Agent MCP server safe?
With care: it is graded C, so read the findings first (65/100). Read the Hermes Agent safety report
How do I install Hermes Agent?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Hermes Agent need an API key?
No secret keys are declared. It reads 3 settings from the environment.
Is Hermes Agent maintained?
The last commit was 43 days ago (2026-09-21). The latest release is v0.1.1.
What can I use instead of Hermes Agent?
Servers from other publishers that do the same job: agent-device MCP server, HOL Guard MCP server and Pm Claude Skills MCP server.
How does Hermes Agent compare with other AI and agents MCP servers?
safety score 65/100 (higher than 25% of 4,460 AI and agents servers); tools 16 (the typical AI and agents server has 6); tools that change things 31% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Hermes Agent

Same job from other publishers: the closest match first, then the best rated.

  • agent-device
    Open source device layer for AI agents: control mobile, web, TV, and desktop apps over MCP
    A
  • HOL Guard
    Local-first AI agent security evidence and approval workflows through HOL Guard's stdio MCP server.
    A
  • Pm Claude Skills
    1310 professional Agent Skills + workflow recipes — searchable & fetchable over MCP.
    A
  • Mockserver
    Mock, record/replay, verify and chaos-test any HTTP, REST, gRPC or LLM dependency over MCP.
    A
  • freellmpool
    OpenAI-compatible MCP gateway cataloging 22 LLM providers, with routing, failover, and tools.
    A