mcp-judge
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MCP_JUDGE_CONFIG | Yes | Path to the JSON config file used to run the MCP server (e.g. `MCP_JUDGE_CONFIG=./config.json mcp-judge-server`). The config supplies the preset/category vocabulary, model, backend, db_path, sources allowlist, and channel/notifier settings. | |
| ANTHROPIC_API_KEY | No | API key used only when `backend` is set to "anthropic" in the config file. Not needed for the default `claude-cli` backend, which drives a logged-in Claude CLI instead. |
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 |
|---|---|
| judge_ingestC | Classify one incoming message and record its triage decision. |
| judge_pendingB | List items still awaiting a decision (model error / not yet processed). |
| judge_getC | Read an item; source is required when the ID exists in multiple sources. |
| judge_healthA | Report preset and item status counts without exposing message content. |
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 4 tools
Each tool targets a distinct operation: reading a single item, checking health counts, ingesting/classifying a message, and listing pending items. The boundaries are clear, with only minor conceptual overlap between judge_get and judge_pending that the descriptions resolve.
All tools use a consistent judge_ prefix and snake_case, making the set predictable. The only minor deviation is judge_pending, which is adjectival rather than a verb like get/health/ingest, but it remains readable and consistent enough.
Four tools are well-scoped for a focused triage/judging server: ingest, inspect, list pending, and health. Each tool earns its place, and the set avoids unnecessary surface area.
The surface covers ingestion, item lookup, pending listing, and health status, but there is no explicit tool to resolve, retry, or manually decide pending items after a model error. This is a notable gap for a judging/triage workflow, even though core read and ingest operations exist.