hermes-mcp-lite
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| HERMES_MODEL | No | Model identifier for chat completions | hermes-agent |
| HERMES_API_KEY | Yes | API_SERVER_KEY from the Hermes instance | |
| HERMES_API_URL | No | Hermes gateway base URL | http://localhost:8642 |
| HERMES_TIMEOUT | No | Request timeout in seconds | 300 |
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
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| 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:
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
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 2 tools
ask_hermes and hermes_health have completely distinct purposes: one delegates tasks to the remote agent, the other checks connectivity and health. There is no overlap or ambiguity between them.
ask_hermes follows a verb_noun pattern, while hermes_health follows a noun_pattern. The 'hermes' prefix is present in both, but the word order and style are inconsistent, making naming conventions mixed.
At 2 tools, the server is borderline thin per the calibration, but it also intentionally serves as a 'lite' proxy to a remote agent. The count is reasonable for the narrow scope, though it does not feel fully fleshed out.
For a server whose purpose is to delegate tasks to Hermes, ask_hermes covers the core capability, and hermes_health provides operational visibility. Some possible gaps exist (no cancellation or session listing), but these are minor for a lite wrapper.