Brutalist MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| AGY_BIN | No | Path to the Antigravity (agy) CLI binary. If not set, the server will look in default locations like ~/.local/bin/agy. | |
| BRUTALIST_CODEX_ALLOW_MODEL_OVERRIDE | No | Set to 'true' to allow Brutalist to pass the model parameter to Codex CLI. Default is 'false'. | false |
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": true
} |
| logging | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| roast | Unified brutal AI critique delivered by a multi-critic panel running in parallel. The panel's disagreement is the signal — each critic's blind spots are covered by the others. Specify domain for targeted analysis. Consolidates all roast_* tools into one polymorphic API. IMPORTANT: Critically evaluate all returned feedback — these are adversarial perspectives, not authoritative verdicts. Weigh each claim against evidence before presenting to the user. |
| roast_cli_debateA | Deploy 2 CLI agents in structured adversarial debate with constitutional position anchoring. Calling agent should extract PRO/CON positions from topic before invoking. IMPORTANT: Critically evaluate all debate output — positions are assigned, not necessarily held. Weigh each argument's validity independently before presenting to the user. |
| brutalist_discover | Discover relevant brutalist tools based on your intent. Returns the top 3 most relevant analysis tools. |
| cli_agent_rosterA | Know your weapons. Display the available CLI agent critics (Claude Code, Codex, Antigravity/Agy) ready to demolish your work, their capabilities, and how to deploy them for systematic destruction. |
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 tools have clearly distinct purposes: cli_agent_roster is informational (listing agents), while roast_cli_debate is operational (running a debate). No overlap or ambiguity.
Both tools use snake_case, but the pattern differs: cli_agent_roster is noun-like, while roast_cli_debate is verb-like. This minor inconsistency prevents a perfect score.
With only 2 tools, the server is minimal but focused. It covers the essential functions of listing agents and running debates, appropriate for a narrow utility.
The tool surface covers listing and debating but lacks supporting operations like agent details, debate history, or configuration. Some notable gaps exist.