Hermes - Automated Asynchronous REST API Monitoring

by agents-mcp-hackathonco.huggingface.agents-mcp-hackathon/hermes

Input any API configuration and monitor responses over time.

  • Remote endpoint
  • 3 tools
  • MIT

Uptime

Checked  · every day

100%from 4 days of checks

Up without downtime on 4 of 4 days with data.

  • No downtime
  • Degraded
  • Down over 5 minutes
  • No data
  • Not checked yet

Response time

Median 1090 ms, slowest 5% 1317 ms for the handshake and the tool list, over 30 days.

1500 ms750 ms0

How far each check got

  • Reached the address 100%
  • Completed the handshake 100%
  • Listed its tools 100%

3 tools at the last answer.

Every day
DayResultChecksMedian
3 Nov (today)No downtime11149 ms
2 NovNo downtime1of 11192 ms
1 NovNo downtime1of 11073 ms
31 OctNo downtime21063 ms

A failure counts as down time only when a second check five minutes later fails too. How we check

Connect to the publisher's own endpoint

Paste into Settings › Connectors › Add custom connector:

https://agents-mcp-hackathon-hermes.hf.space/gradio_api/mcp/sse
For agents: the install prompt

Every step above as one Markdown text, for an assistant installing it for you.

# Install the MCP server Hermes - Automated Asynchronous REST API Monitoring (`co.huggingface.agents-mcp-hackathon/hermes`)

Its page: https://plug.directory/servers/co.huggingface.agents-mcp-hackathon/hermes

It runs on the publisher's servers; the client connects to its URL.

Use the section for the person's client.

## Claude Desktop

Paste into Settings › Connectors › Add custom connector:

```text
https://agents-mcp-hackathon-hermes.hf.space/gradio_api/mcp/sse
```

## Claude Code

Run in a terminal:

```sh
claude mcp add --transport sse hermes https://agents-mcp-hackathon-hermes.hf.space/gradio_api/mcp/sse
```

## Cursor, Devin Desktop, LM Studio, Gemini CLI, oterm, ECA

Merge into the place for the person's client:

- Cursor: ~/.cursor/mcp.json
- Devin Desktop: ~/.config/devin/mcp_config.json
- LM Studio: mcp.json (Program › Install › Edit mcp.json)
- Gemini CLI: ~/.gemini/settings.json
- oterm: config.json in oterm's data folder (~/Library/Application Support/oterm on macOS, ~/.local/share/oterm on Linux, %APPDATA%\oterm on Windows)
- ECA: ~/.config/eca/config.json (global) or .eca/config.json in the project

```json
{
  "mcpServers": {
    "hermes": {
      "url": "https://agents-mcp-hackathon-hermes.hf.space/gradio_api/mcp/sse"
    }
  }
}
```

## VS Code

Merge into .vscode/mcp.json:

```json
{
  "servers": {
    "hermes": {
      "type": "sse",
      "url": "https://agents-mcp-hackathon-hermes.hf.space/gradio_api/mcp/sse"
    }
  }
}
```

## Zed

This server's endpoint speaks only SSE, which this client's documentation does not list among its transports; use another client for it.

## Cline, AnythingLLM, Augment Code

Merge into the place for the person's client:

- Cline: cline_mcp_settings.json (MCP Servers › Configure › Configure MCP Servers)
- AnythingLLM: anythingllm_mcp_servers.json in the AnythingLLM storage plugins directory
- Augment Code: Augment Settings Panel – MCP section – Import from JSON (VS Code extension)

```json
{
  "mcpServers": {
    "hermes": {
      "type": "sse",
      "url": "https://agents-mcp-hackathon-hermes.hf.space/gradio_api/mcp/sse"
    }
  }
}
```

## Continue

Merge into ~/.continue/config.yaml:

```yaml
mcpServers:
  - name: "hermes"
    type: sse
    url: "https://agents-mcp-hackathon-hermes.hf.space/gradio_api/mcp/sse"
```

## Goose

This server's endpoint speaks only SSE, which this client's documentation does not list among its transports; use another client for it.

## Codex

This server's endpoint speaks only SSE, which this client's documentation does not list among its transports; use another client for it.

## mcp-client-cli, TUUI, BoltAI, Bob Shell, Kiro, Kiro CLI

This server's endpoint speaks only SSE, which this client's documentation does not list among its transports; use another client for it.

## Agenvoy

This server's endpoint speaks only SSE, which this client's documentation does not list among its transports; use another client for it.

## Amp

Merge into ~/.config/amp/settings.json (user) or .amp/settings.json (workspace):

```json
{
  "amp.mcpServers": {
    "hermes": {
      "url": "https://agents-mcp-hackathon-hermes.hf.space/gradio_api/mcp/sse"
    }
  }
}
```

Then restart the client, or reload its MCP servers, and ask it to list the server's tools to confirm it started.

Tools 3

  • hermes_activate_monitoring TOOL: Activate periodic monitoring for a validated API configuration. PURPOSE: Start automated recurring API calls based on a previously validated configuration. This is STEP 2 of the monitoring setup process. PREREQUISITE: Must call validate_api_configuration() first and obtain a config_id from successful validation. Make sure that the sample_response is what you expect to see before proceeding with this function. WORKFLOW: 1. First call validate_api_configuration() to get config_id 2. If validation successful, call this function with the config_id 3. Monitoring will run automatically according to the validated schedule ARGUMENTS: - config_id: The ID from successful validate_api_configuration() execution (required) - mcp_api_key: User's MCP API key for verification (must match validation step). Input Examples: 1. Activate scheduler for stock monitoring: config_id: 123456789 mcp_api_key: "your_mcp_key_here" 2. Activate scheduler for weather alerts: config_id: 987654321 mcp_api_key: "yo
  • hermes_retrieve_monitored_data TOOL: Retrieve monitored data for a specific API configuration. PURPOSE: Fetch the latest monitored data for a given configuration ID. This is STEP 3 of the monitoring setup process. PREREQUISITE: Must call validate_api_configuration() first and obtain a config_id from successful validation, then activate_monitoring() to start monitoring. This function can be called at any time after monitoring activation to retrieve the latest data collected by the monitoring system. ARGUMENTS: - config_id: The ID of the API configuration to retrieve data for (required) - mcp_api_key: User's MCP API key for verification (must match validation step). - mode: Data return mode - "summary" (LLM-optimized), "details" (full responses, minimal metadata), "full" (everything) Input Examples: 1. Retrieve data for stock monitoring: config_id: 123456789 mcp_api_key: "your_mcp_key_here" 2. Retrieve data for weather alerts: config_id: 987654321 mcp_api_key: "your_mcp_key_here". Returns: Dictionary with monitoring s
  • hermes_validate_api_configuration TOOL: Validate and store API configuration for monitoring. PURPOSE: Test an API endpoint and store the configuration if successful. This is STEP 1 of the monitoring setup process. If validation fails, retry with corrected parameters. If successful, use the returned config_id in activate_monitoring() function. CRITICAL: Even if success=True, you MUST manually check the 'sample_response' field before proceeding to activate_monitoring(). The API call may return success=True but contain error messages (like "401 Unauthorized", "Invalid API key", etc.) in the sample_response. CRITICAL: Always try to add parameters that will limit the API response to a manageable size. CRITICAL: Be sure to always clearly inform the user of the config_id after a desired validation result. CRITICAL: If you don't have an MCP API KEY given by the user, prompt them to get it here: https://mcp-hackathon.vercel.app/ WORKFLOW: 1. Call this function to validate API configuration 2. If success=False: Fix parameters

From Hugging Face Spaces. Report a problem