# io.github.woonyong-choi/hermes-agent-mcp (pypi · hermes-agent-mcp)

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

- Trust score: 66/100 (medium)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-18

## Components

- pypi · `hermes-agent-mcp`: 66/100 (this document), [markdown](https://verifymcp.io/servers/woonyong-choi-hermes-agent-mcp/hermes-agent-mcp.md), [page](https://verifymcp.io/servers/woonyong-choi-hermes-agent-mcp/hermes-agent-mcp)

## Channel facts

- Registry: `pypi`
- Package: `hermes-agent-mcp`
- Version: `0.1.1`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-18.

- **Supply Chain Security**: 50/100
  - Malware scan not yet available for this package.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs hatchling.build at install time, a recognised build step with no custom scripting around it.
  - 1 of 29 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 48/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 26 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 75/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 733 tokens (~45/item across 16 items; 16 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 90/100
  - Stability observed for 27 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 71/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 16 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 17 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the io.github.woonyong-choi/hermes-agent-mcp server?

io.github.woonyong-choi/hermes-agent-mcp runs locally as a PyPI package, launched with uvx hermes-agent-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add woonyong-choi-hermes-agent-mcp -- uvx hermes-agent-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "woonyong-choi-hermes-agent-mcp": {
      "command": "uvx",
      "args": [
        "hermes-agent-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "woonyong-choi-hermes-agent-mcp": {
      "command": "uvx",
      "args": [
        "hermes-agent-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add woonyong-choi-hermes-agent-mcp -- uvx hermes-agent-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "woonyong-choi-hermes-agent-mcp": {
      "type": "local",
      "command": [
        "uvx",
        "hermes-agent-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add woonyong-choi-hermes-agent-mcp --command uvx --arg hermes-agent-mcp
```

### Hermes

```yaml
mcp_servers:
  woonyong-choi-hermes-agent-mcp:
    command: "uvx"
    args: ["hermes-agent-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "woonyong-choi-hermes-agent-mcp": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "hermes-agent-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add woonyong-choi-hermes-agent-mcp -t stdio -c uvx -a hermes-agent-mcp
```

### Other

```json
{
  "mcpServers": {
    "woonyong-choi-hermes-agent-mcp": {
      "command": "uvx",
      "args": [
        "hermes-agent-mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-17 (score 66, +1)

No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-16 (score 65, +40)

- [security improvement] Injection markers: unverified → pass
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] Stability: unverified → 0.83
- [functional improvement] MCP protocol: unverified → pass

### 2026-10-12 (score 25, −37)

- [security regression] Stability: 0.57 → unverified
- [security regression] Tool safety: pass → unverified
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional] First check of Schema quality: unverified

### 2026-10-08 (score 62, +2)

No change was recorded against any check on this day. Stability & Change Management went from 43 to 57. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 17 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-04 (score 60, −14)

- [security regression] Malware scan: pass → unverified

### 2026-10-02 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-01 (score 73, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-09-30 (score 58, −15)

- [security regression] Malware scan: pass → unverified

## MCP tools (16)

### `hermes_status` (~22 tokens)

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

Output parameters:

- `result` (string)

### `hermes_ask` (~71 tokens)

Give the Hermes agent a task and return its reply.

Runs one non-interactive turn with the agent's own tools, skills and memory.
Use this for work; use the specific tools below for inspection and config.

Input parameters:

- `model`
- `prompt` (string, required)
- `timeout_seconds`

Output parameters:

- `result` (string)

### `doctor` (~19 tokens)

Run `hermes doctor` and return its health report.

Output parameters:

- `result` (string)

### `gateway_status` (~18 tokens)

Show whether the messaging gateway is running and supervised.

Output parameters:

- `result` (string)

### `gateway_restart` (~18 tokens)

Restart the messaging gateway so configuration changes take effect.

Output parameters:

- `result` (string)

### `cron_list` (~19 tokens)

List scheduled jobs with their schedules and next run times.

Output parameters:

- `result` (string)

### `cron_create` (~64 tokens)

Create a scheduled job.

\`schedule` accepts what the Hermes CLI accepts, including natural language
such as "every day at 23:00".

Input parameters:

- `deliver`
- `name` (string, required)
- `prompt` (string, required)
- `schedule` (string, required)

Output parameters:

- `result` (string)

### `cron_edit` (~52 tokens)

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

Input parameters:

- `job_id` (string, required)
- `model`
- `prompt`
- `reasoning_effort`
- `schedule`

Output parameters:

- `result` (string)

### `cron_run` (~30 tokens)

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

Input parameters:

- `job_id` (string, required)

Output parameters:

- `result` (string)

### `cron_runs` (~22 tokens)

Show recorded execution attempts, newest first.

Input parameters:

- `job_id`

Output parameters:

- `result` (string)

### `config_get` (~33 tokens)

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

Input parameters:

- `key` (string, required)

Output parameters:

- `result` (string)

### `config_set` (~117 tokens)

Write one config.yaml value with an explicit type.

\`value_type` is one of str, int, float, bool, null, json. Passing a type
avoids the YAML trap where "off", "no" and "yes" silently become booleans -
several Hermes options compare against the string, so an auto-parsed value
quietly does nothing. A .bak copy is written before the file changes.

Input parameters:

- `key` (string, required)
- `value` (string, required)
- `value_type` (string)

Output parameters:

- `result` (string)

### `skills_list` (~19 tokens)

List installed skills with category, source and enabled state.

Output parameters:

- `result` (string)

### `sessions_list` (~26 tokens)

List recent sessions so you can resume or inspect one.

Input parameters:

- `limit` (integer)

Output parameters:

- `result` (string)

### `model_info` (~21 tokens)

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

Output parameters:

- `result` (string)

### `shell` (~60 tokens)

Run a shell command on the Hermes host.

Disabled unless HERMES_MCP_ALLOW_SHELL=1. Intended for agents that can reach
this MCP server but have no terminal of their own.

Input parameters:

- `command` (string, required)
- `timeout_seconds`

Output parameters:

- `result` (string)

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/woonyong-choi-hermes-agent-mcp/hermes-agent-mcp#diagnostics

## Score history

- 2026-10-18: 66
- 2026-10-17: 66
- 2026-10-16: 65
- 2026-10-15: 25
- 2026-10-14: 25
- 2026-10-13: 25
- 2026-10-12: 25
- 2026-10-08: 62
- 2026-10-04: 60
- 2026-10-03: 74
- 2026-10-02: 74
- 2026-10-01: 73
- 2026-09-30: 58
- 2026-09-29: 73
- 2026-09-28: 54
- 2026-09-27: 69
- 2026-09-26: 69
- 2026-09-25: 69
- 2026-09-24: 69
- 2026-09-23: 69
- 2026-09-22: 69
- 2026-09-21: 69

## Common questions

### What is the io.github.woonyong-choi/hermes-agent-mcp server?

io.github.woonyong-choi/hermes-agent-mcp is listed in the public MCP registry as io.github.woonyong-choi/hermes-agent-mcp. Operate a local Hermes Agent install over stdio: tasks, cron, config, gateway, doctor. No network. This page covers its PyPI package (hermes-agent-mcp).

### Is the io.github.woonyong-choi/hermes-agent-mcp server safe to use?

io.github.woonyong-choi/hermes-agent-mcp scores 66 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 18 October 2026. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the io.github.woonyong-choi/hermes-agent-mcp server expose?

io.github.woonyong-choi/hermes-agent-mcp exposes 16 tools: hermes_status, hermes_ask, doctor, gateway_status, gateway_restart, and 11 more. Their descriptions and schemas cost roughly 611 tokens of context every time the server is loaded.

### Is the io.github.woonyong-choi/hermes-agent-mcp server still maintained?

io.github.woonyong-choi/hermes-agent-mcp is still listed as active in the MCP registry. We last reached this channel on 18 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the io.github.woonyong-choi/hermes-agent-mcp server under?

io.github.woonyong-choi/hermes-agent-mcp declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- PyPI project: https://pypi.org/project/hermes-agent-mcp/
- Socket report: https://socket.dev/pypi/package/hermes-agent-mcp
- Repository: https://github.com/woonyong-choi/hermes-agent-mcp
- Changelog RSS feed: https://verifymcp.io/servers/woonyong-choi-hermes-agent-mcp/hermes-agent-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/woonyong-choi-hermes-agent-mcp/hermes-agent-mcp.json
- HTML version of this page: https://verifymcp.io/servers/woonyong-choi-hermes-agent-mcp/hermes-agent-mcp