As A Judge MCP Server

MCP as a Judge is a behavioral MCP that strengthens AI coding assistants by requiring explicit LLM evaluations for: Research, system design, and planning Code changes, testing, and task-completion verification. Its 8 documented tools cover coding, judge, task, raise. It runs locally over stdio via the published package.

People connecting AI & ML tools to Claude, Cursor, VS Code, or another MCP client. The project is written in Python.

VERIFIED ACTIVE

LAST COMMIT 2025-12-15 · ★ 17 · #65 OF 95 MAINTAINED AI & ML · VERIFIED 2026-08-25

MIT · Python servers · how we verify → /methodology

01 · Install As A Judge

before you install - you'll need

LLM_API_KEY, LLM_MODEL_NAME are optional or environment-specific per the README.

Claude Code

claude mcp add othervibes-mcp-as-a-judge -- uvx mcp-as-a-judge

Claude Desktop / Cursor / VS Code - add to config

{
  "mcpServers": {
    "othervibes-mcp-as-a-judge": {
      "command": "uvx",
      "args": [
        "mcp-as-a-judge"
      ]
    }
  }
}

Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.

Using another client? Same JSON, different key

Claude Desktop · mcpServers

Cursor · mcpServers

VS Code · servers

Windsurf · mcpServers

Zed · context_servers

Cline · mcpServers

Roo Code · mcpServers

Continue · mcpServers

LibreChat · mcpServers

Gemini CLI · mcpServers

Codex CLI · mcp_servers

Full setup guides: every client.

02 · Evidence

Security posture

What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.

runs as local process (stdio) - runs on your machine with your user's permissions

license MIT - declared in the repository

pypi package mcp-as-a-judge - check the name against the project README before installing (PyPI has no namespace ownership)

registry namespace io.github.OtherVibes is GitHub-verified and matches the repo owner

03 · What As A Judge can do

Prose above is summarized from the project's README and registry record - no invented capabilities.

What you can build

With this server connected, an agent can validate plan/design, and validate tests using real runner output and optional coverage.

Capability map

Tools grouped from the project's README - what As A Judge lets an agent do.

Judge

4 tools - e.g. Validates plan/design; requires library selection and internal reuse maps; flags risks; Reviews unified Git diffs for correctness, reuse, security, and code quality; Validates tests using real runner…

judge_coding_plan · judge_code_change · judge_testing_implementation · judge_coding_task_completion

Raise

2 tools - e.g. Elicits missing details and decisions to unblock progress; Engages the user on trade‑offs, constraints, and enforced changes

raise_missing_requirements · raise_obstacle

update

1 tool - e.g. Creates/updates task metadata; classifies task_size; returns next-step workflow guidance

set_coding_task

read & search

1 tool - e.g. Recovers the latest task_id and metadata to resume work safely

get_current_coding_task

Latest releases

v0.5.0 · 2025-09-29

bump version to 0.5.0 · implement human plan approval workflow and enhanced judge response handling (#31) · implement human plan approval workflow and enhanced judge response handling

v0.4.0 · 2025-09-24

bump version to 0.4.0 · bind workflow guidance to plan system prompt with structured field specs (#28) · bump actions/download-artifact from 4 to 5 (#30) · bump actions/create-github-app-token from 1 to 2 (#29) · bump…

v0.3.20 · 2025-09-20

bump version to 0.3.20

04 · Who maintains As A Judge

mcp-as-a-judge is maintained by othervibes. It's the only MCP server we track from this author; the repo dates to Aug 2025.

05 · Facts

repository: github.com/othervibes/mcp-as-a-judge
category: AI & ML - ranked #65 of 95 actively-maintained AI & ML servers as of 2026-08-25.
registry: io.github.OtherVibes/mcp-as-a-judge (active, first published 2025-09-18 · 6 versions)
packages: pypi:mcp-as-a-judge

06 · As A Judge FAQ

Is As A Judge still maintained?

Yes - as of 2026-08-25, its last commit was 2025-12-15. We re-verify nightly.

What can As A Judge do?

With this server connected, an agent can validate plan/design, and validate tests using real runner output and optional coverage.

How do I install As A Judge?

Run `uvx mcp-as-a-judge`. The README documents 2 environment variables (LLM_API_KEY, LLM_MODEL_NAME) to set first. LLM_API_KEY, LLM_MODEL_NAME are optional or environment-specific per the README. You can also paste the ready-made client config above.

Does As A Judge run locally?

Yes - it's a stdio server: it runs on your machine (via uvx) with your user's permissions. Your data stays local unless the server itself calls external APIs.

07 · Alternatives to As A Judge

Alternatives to As A Judge

Maintained AI & ML servers if As A Judge isn't the fit.

Pairs well with

Servers that cover what As A Judge doesn't - only shown when the pairing reason fits the companion.

More AI & ML MCP servers · Ncp · Promptibus MCP · Nutrient DWS MCP Server · Predictalot

More Python MCP servers · Ouestcharlie Woof · Watch Skill · Global Agent Memory · Northdata MCP · GitHub PR Context · see all