Brooks Model MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GROK_MODEL | No | Default model for the server | grok-4 |
| GROK_API_KEY | Yes | API key for Grok, only allowed in local configuration (required) | |
| GROK_API_URL | Yes | OpenAI compatible API base URL (required) | |
| GROK_MAX_RETRIES | No | Maximum number of retries for retryable requests | 3 |
| GROK_REASONING_FIELD | No | Compatible endpoint request field; empty means not sent | reasoning_effort |
| GROK_TIMEOUT_SECONDS | No | Request timeout in seconds | 180 |
| GROK_REASONING_EFFORT | No | Default reasoning effort: low/medium/high/xhigh/max | high |
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 |
|---|---|
| codexB | Start a direct Codex CLI conversation and return a resumable thread ID. |
| codex_replyB | Continue a Codex CLI conversation using a prior thread ID. |
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
The two tools have completely distinct purposes: codex starts a new conversation and returns a thread ID, while codex_reply continues an existing conversation using that ID. There is no overlap or ambiguity between them.
Both tools use lowercase snake_case and share the 'codex' prefix, making them predictable. However, one is a bare noun and the other is a noun-reply compound, so the naming pattern is not strictly verb_noun, though it remains consistent in style.
With only two tools, the server sits at the thin end of the scale. For a focused Codex conversation interface, start and reply are the core operations, so the count is reasonable for the narrow purpose, but it feels minimal.
The core conversation lifecycle—initiate and continue—is fully covered, which is the primary use case. Missing capabilities like listing or ending threads are minor gaps that agents can work around.