headroom_agent_mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| HEADROOM_PROXY_URL | No | Optional URL of the Headroom proxy to route the configured LLM profile through. | |
| HEADROOM_AGENT_API_KEY | No | The API key for the LLM provider. | |
| HEADROOM_AGENT_BASE_URL | No | The base URL of the LLM provider API. | |
| HEADROOM_AGENT_MODEL_NAME | No | The model name to use for the discovery subagent. | |
| HEADROOM_AGENT_MODEL_PROVIDER | No | The LLM provider for the discovery subagent (e.g. openai, anthropic). |
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 |
|---|---|
| run_discoveryA | Explore noisy docs, logs, or codebases and return only the evidence a parent agent needs. Use this tool when the parent agent needs discovery or triage before reading raw files itself. Best cases: docs research, logs/output triage, or codebase discovery over broad scopes. Do not use it for final file edits or precise patch generation. Inputs:
|
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 1 tool
With only one tool, there is no possibility of confusion or overlap between tools. run_discovery has a clearly defined purpose and inputs, making it unambiguous for an agent to select.
The single tool name run_discovery follows a clear verb_noun convention. There are no other tools to create naming inconsistencies or mixed conventions.
One tool is minimal, but it is appropriate for a narrowly scoped discovery/triage subagent. The count feels slightly thin compared to typical multi-tool servers, but the server's purpose is focused enough that a single tool can reasonably fulfill it.
The tool covers the stated discovery domain across docs research, logs triage, and codebase discovery, with support for scope paths, query hints, and safe terminal commands. Minor gaps exist around iterative refinement or returning raw context, but the core triage workflow is well covered.