Prototype · Preview: every server in the official registry, synced every 30 minutes. Sign in with Google to write reviews.Prototype · updated every 30 min
PopNx MCPMCP servers for people who use AI · explained in plain words

Agent Roast

by Nari-Abversion 0.27.0i★ 11iRuns on your computer
Registry nameio.github.Nari-Ab/agent-roast

How to install

What it does

Offline, read-only review that flags agent changes weakening tests, assertions, coverage or CI.

  • Connects Runs on your computer
  • Account or key No key needed
  • Category Other

Why it ranks here

Lists are ordered by a usage score (out of 100) built from these parts

Popularity24/80GitHub stars or weekly downloads: the larger counts 60, the smaller 20
Freshness12/12Full marks for a release or code change within 30 days
Still answering0/8The cloud endpoint answered at the last check
Usage score36/100

Quality: Passed 3/3 basic checks (shown, not used for ordering) · Momentum: No data yet (Used only on the Trending tab)

Install

Pick the AI app you use, then copy the settings.

Passed 3/3 checks · Runs on your computer · ✓ Commands checked Nov 16, 2026

First: which AI do you use?

Pick your app and the steps appear below.

Works with Claude, with some setup first

Install Node.js on your computer first (one time) · Only the Claude desktop app (Windows or Mac), not the web or phone

Let AI install it

Copy this message into a Claude chat. The AI checks your computer, tells you which file it will change, and waits for your OK every time.

Please install the MCP server Agent Roast for Claude on this computer, in this order: 1) Check Node.js with node -v. If it is missing, tell me to install it from https://nodejs.org/en/download; do not install it yourself. 2) Use only this config (already checked by PopNx MCP): { "mcpServers": { "agent-roast": { "command": "npx", "args": [ "-y", "agent-roast", "mcp" ] } } } 3) Tell me the full path of the file you will change, or the command you will run, and wait for my OK. 4) No key is needed. 5) Do what we agreed, then check that the Agent Roast tools really show up.

This message has no key in it. If a key is needed, the AI will ask you to paste it yourself into the file or the app’s field.

  1. Install Node.js (if you don’t have it)

    Already installed? Check first · Open Terminal, type this command and press Enter

    node -v
    • A version number such as v26.13.1 = installed, skip this step
    • "command not found" (on Windows: "is not recognized") = not installed yet, or installed but Terminal needs to be closed and reopened
    How to open Terminal

    Mac: press ⌘ + Space, type Terminal, press Enter

    Windows: open Start, type Windows PowerShell, then Open

    Not installed: Open the official download page, pick the LTS version and the click-through installer: .pkg on Mac · .msi on Windows. Double-click and follow it to the end. No curl command needed

    Open the Node.js download page ↗

    When it’s done, close Terminal, open it again and run the same command. You should see a version number: node -v

    Install once; it works for everything that needs Node.js

  2. Open the Claude desktop app’s settings file

    SettingsDeveloperEdit Config

  3. Paste these settings and save the file

    {
      "mcpServers": {
        "agent-roast": {
          "command": "npx",
          "args": [
            "-y",
            "agent-roast",
            "mcp"
          ]
        }
      }
    }
  4. Quit Claude and open it again

  5. Try it

    Use Agent Roast and tell me what you can do for me, then show me one thing

    ✓ If Claude says it is using Agent Roast or shows a Agent Roast tool in the answer, you are connected

Menu names checked against Anthropic’s help page on Nov 11, 2026 · your screen may differ slightly by app version

ChatGPT cannot connect Agent Roast yet

Agent Roast runs on your computer, but ChatGPT can only connect servers that run on the web

What you can do instead

A · Use an app that can connect Agent Roast

  • Install Node.js on your computer first (one time) · Only the Claude desktop app (Windows or Mac), not the web or phone
  • Install Node.js on your computer first (one time)
  • Install Node.js on your computer first (one time)
  • Install Node.js on your computer first (one time)

B · Others in Other that work with ChatGPT

Picked from the most used in the same category, only ones that connect by address with no key

Works with Claude Code, with some setup first

Install Node.js on your computer first (one time)

Let AI install it

Copy this message into a Claude Code chat. The AI checks your computer, tells you which file it will change, and waits for your OK every time.

Please install the MCP server Agent Roast for Claude Code on this computer, in this order: 1) Check Node.js with node -v. If it is missing, tell me to install it from https://nodejs.org/en/download; do not install it yourself. 2) Use only this config (already checked by PopNx MCP): claude mcp add --scope user agent-roast -- npx -y agent-roast mcp 3) Tell me the full path of the file you will change, or the command you will run, and wait for my OK. 4) No key is needed. 5) Do what we agreed, then check that the Agent Roast tools really show up.

This message has no key in it. If a key is needed, the AI will ask you to paste it yourself into the file or the app’s field.

  1. Install Node.js (if you don’t have it)

    Already installed? Check first · Open Terminal, type this command and press Enter

    node -v
    • A version number such as v26.13.1 = installed, skip this step
    • "command not found" (on Windows: "is not recognized") = not installed yet, or installed but Terminal needs to be closed and reopened
    How to open Terminal

    Mac: press ⌘ + Space, type Terminal, press Enter

    Windows: open Start, type Windows PowerShell, then Open

    Not installed: Open the official download page, pick the LTS version and the click-through installer: .pkg on Mac · .msi on Windows. Double-click and follow it to the end. No curl command needed

    Open the Node.js download page ↗

    When it’s done, close Terminal, open it again and run the same command. You should see a version number: node -v

    Install once; it works for everything that needs Node.js

  2. Open Terminal

    Mac: press Command+Space and type Terminal · Windows: open PowerShell

  3. Paste this command and press Enter

    claude mcp add --scope user agent-roast -- npx -y agent-roast mcp
  4. Type /mcp in Claude Code

    You should see Agent Roast listed as connected

  5. Try it

    Use Agent Roast and tell me what you can do for me, then show me one thing

    ✓ If Claude Code says it is using Agent Roast or shows a Agent Roast tool in the answer, you are connected

Menu names checked against Anthropic’s help page on Nov 11, 2026 · your screen may differ slightly by app version

Works with Cursor, with some setup first

Install Node.js on your computer first (one time)

Let AI install it

Copy this message into a Cursor chat. The AI checks your computer, tells you which file it will change, and waits for your OK every time.

Please install the MCP server Agent Roast for Cursor on this computer, in this order: 1) Check Node.js with node -v. If it is missing, tell me to install it from https://nodejs.org/en/download; do not install it yourself. 2) Use only this config (already checked by PopNx MCP): { "mcpServers": { "agent-roast": { "command": "npx", "args": [ "-y", "agent-roast", "mcp" ] } } } 3) Tell me the full path of the file you will change, or the command you will run, and wait for my OK. 4) No key is needed. 5) Do what we agreed, then check that the Agent Roast tools really show up.

This message has no key in it. If a key is needed, the AI will ask you to paste it yourself into the file or the app’s field.

  1. Install Node.js (if you don’t have it)

    Already installed? Check first · Open Terminal, type this command and press Enter

    node -v
    • A version number such as v26.13.1 = installed, skip this step
    • "command not found" (on Windows: "is not recognized") = not installed yet, or installed but Terminal needs to be closed and reopened
    How to open Terminal

    Mac: press ⌘ + Space, type Terminal, press Enter

    Windows: open Start, type Windows PowerShell, then Open

    Not installed: Open the official download page, pick the LTS version and the click-through installer: .pkg on Mac · .msi on Windows. Double-click and follow it to the end. No curl command needed

    Open the Node.js download page ↗

    When it’s done, close Terminal, open it again and run the same command. You should see a version number: node -v

    Install once; it works for everything that needs Node.js

  2. Click this button to open Cursor

    Open in Cursor

    Cursor asks you to confirm; click Install

  3. Open the AI chat in Cursor in Agent mode

  4. Try it

    Use Agent Roast and tell me what you can do for me, then show me one thing

    ✓ If Cursor says it is using Agent Roast or shows a Agent Roast tool in the answer, you are connected

Menu names checked against Cursor’s help page on Nov 11, 2026 · your screen may differ slightly by app version

Works with VS Code, with some setup first

Install Node.js on your computer first (one time)

Let AI install it

Copy this message into a VS Code chat. The AI checks your computer, tells you which file it will change, and waits for your OK every time.

Please install the MCP server Agent Roast for VS Code on this computer, in this order: 1) Check Node.js with node -v. If it is missing, tell me to install it from https://nodejs.org/en/download; do not install it yourself. 2) Use only this config (already checked by PopNx MCP): { "servers": { "agent-roast": { "type": "stdio", "command": "npx", "args": [ "-y", "agent-roast", "mcp" ] } } } 3) Tell me the full path of the file you will change, or the command you will run, and wait for my OK. 4) No key is needed. 5) Do what we agreed, then check that the Agent Roast tools really show up.

This message has no key in it. If a key is needed, the AI will ask you to paste it yourself into the file or the app’s field.

  1. Install Node.js (if you don’t have it)

    Already installed? Check first · Open Terminal, type this command and press Enter

    node -v
    • A version number such as v26.13.1 = installed, skip this step
    • "command not found" (on Windows: "is not recognized") = not installed yet, or installed but Terminal needs to be closed and reopened
    How to open Terminal

    Mac: press ⌘ + Space, type Terminal, press Enter

    Windows: open Start, type Windows PowerShell, then Open

    Not installed: Open the official download page, pick the LTS version and the click-through installer: .pkg on Mac · .msi on Windows. Double-click and follow it to the end. No curl command needed

    Open the Node.js download page ↗

    When it’s done, close Terminal, open it again and run the same command. You should see a version number: node -v

    Install once; it works for everything that needs Node.js

  2. Click this button to open VS Code

    Open in VS Code

    VS Code asks you to confirm; click Install

  3. Open the AI chat in VS Code in Agent mode

  4. Try it

    Use Agent Roast and tell me what you can do for me, then show me one thing

    ✓ If VS Code says it is using Agent Roast or shows a Agent Roast tool in the answer, you are connected

Menu names checked against VS Code’s help page on Nov 11, 2026 · your screen may differ slightly by app version

Other apps that use MCP, such as Windsurf, Zed or Gemini CLI, each add servers differently. See how in the app list.

See every app that uses MCP →

JSON settings are under “For developers” below

Stuck? Ask people who use Agent Roast💬 Discussion →
For developers: Terminal commands and JSON settings

Installed on your computer

Claude Code

claude mcp add --scope user agent-roast -- npx -y agent-roast mcp

Claude Desktop (claude_desktop_config.json)

{
  "mcpServers": {
    "agent-roast": {
      "command": "npx",
      "args": [
        "-y",
        "agent-roast",
        "mcp"
      ]
    }
  }
}

Cursor (~/.cursor/mcp.json)

{
  "mcpServers": {
    "agent-roast": {
      "command": "npx",
      "args": [
        "-y",
        "agent-roast",
        "mcp"
      ]
    }
  }
}

VS Code (mcp.json)

{
  "servers": {
    "agent-roast": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "agent-roast",
        "mcp"
      ]
    }
  }
}

These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.

At a glance

Downloads per weeki
696/wk
Connection
Runs on your computer
Latest versioni
0.27.0
Categoryi
Other
Published to registryi
Nov 16, 2026
Code last changedi
Nov 16, 2026
Maker
Nari-Ab
Packages
npm: agent-roast
Website
github.com
Registry status
Active

Which apps can use it

Based on how this server connects and on each app’s own docs, checked Nov 10, 2026.

Run on your computer in

ClaudeGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatRaycast

All apps, with pros and cons →

Related guides

What it can do

Runs on your computer; the tool list appears in your AI app after you install it.

Basic checksi

We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 16, 2026

  • ✓ Pass

    Maker matches the repo

    The registry name was verified with the GitHub account Nari-Ab, which owns the repo

  • ✓ Pass

    Still maintained

    Code last changed today

  • ✓ Pass

    Has a licence

    Uses MIT

  • – Not applicable

    Endpoint responds

    This one runs on your computer; there is no internet endpoint

  • – Not applicable

    Sign-in with OAuth

    Runs on your computer and uses local settings instead

  • … Not checked yet

    No hidden instructions in tool descriptions

    Runs on your computer; we can only read tool lists from internet endpoints

Published vulnerabilities (OSV.dev)

Not checked yet

What we check → · JSON

Makers: ask for a re-check or report wrong info
For makers: add a badge to your README

If you made this, paste this code into your README. The badge links back to this page.

[![Featured on PopNx MCP](https://mcp.popnx.com/badge/nari-ab-agent-roast.svg)](https://mcp.popnx.com/en/servers/nari-ab-agent-roast)

Discussion

Ask, share a tip or report that it does not work. Sorted by what people marked helpful.

No posts yet. Be the first to ask or share.

Posts here are written by users, not the PopNx team.

Sign in to post

User reviews

No reviews yet

Sign in to write a review

Compared with others in Otheri

  • More stars than 96% of the other 20087 servers in this category
  • Published to the registry more recently than 99% of the other 20087 servers in this category
  • Basic checks equal to or better than 100% of the other 20087 servers in this category

Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.

Common questions

Is Agent Roast safe?

It passed 3 of 3 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.

What keys or codes does it need?

The registry does not list a required key, though some servers ask you to sign in on first use.

Does it run on my computer or in the cloud?

It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).

Is it still maintained?

The GitHub repo last changed today, and the latest version (0.27.0) reached the registry today.

Which apps can use it?

Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Node.js on your computer.

What can I use instead?

In the same category: World Monitor, openstatus, Oh My Posh Validator, Strata, Jitsu

Similar alternatives

Same category, other makers, commands already checked. Official ones first, then by stars.

Reading a card:↓ Downloads per weeki★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi

World Monitor

Real-time global intelligence on conflict, markets, energy, trade, shipping and cyber. 97 tools.

by koala73Widely used★ 90.7KUpdated 2 days ago

Runs in the cloud✓ service owner · worldmonitor.app

openstatus

Manage monitors, status pages, incidents and maintenances in your openstatus workspace.

by openstatusHQWidely used★ 9.3KUpdated 2 months ago

Runs in the cloud✓ service owner · openstatus.dev

Oh My Posh Validator

Validate oh-my-posh configurations and segment snippets against the official schema.

by JanDeDobbeleerWidely used★ 23.8K Stars for the whole repoUpdated 27 days ago

Runs in the cloud✓ service owner · ohmyposh.dev

Strata

MCP server for progressive tool usage at any scale (see https://klavis.ai)

by Klavis-AIGrowing★ 5.8KUpdated 14 months ago

Runs in the cloudRepo archived✓ klavis.ai

Jitsu

Manage Jitsu data pipelines: destinations, streams, connections, functions, live events.

by jitsucomWidely used★ 5.1KUpdated 4 months ago

Runs in the cloud✓ service owner · jitsu.com
Compared with similar ones
This one
Agent Roast
World MonitoropenstatusOh My Posh ValidatorStrataJitsu
Runs whereInstalls on your computerRuns in the cloud, nothing to installRuns in the cloud, nothing to installRuns in the cloud, nothing to installRuns in the cloud, nothing to installRuns in the cloud, nothing to install
Needs a keyNoNoNoNoNoNo
Add with + in ClaudeNoNoNoNoNoNo
Basic checks3/34/44/44/41/44/4
LicenseMITAGPL-3.0AGPL-3.0MITApache-2.0MIT
PriceNo cost listed in the registryNo cost listed in the registryNo cost listed in the registryNo cost listed in the registryNo cost listed in the registryNo cost listed in the registry

README from the maker

Open the README

Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.

Your AI agent made the tests pass. Did it fix the code, or the tests?

agent-roast catches the changes that turn a red build green by weakening the *checks* instead of fixing the *code*: a loosened assertion, a skipped or deleted test, a lowered coverage threshold, a CI step allowed to fail. A linter cannot see these, because every new line looks fine on its own. agent-roast compares the before and after of each change, as an agent hook, a Git hook and a pull request check. It is deterministic and offline: no model, no tokens, no network.

Real output of npx agent-roast demo , shortened. The scenario is scripted; the review is not.

Try it

npx agent-roast demo     # ten seconds: a scripted example in a temporary repository, nothing of yours is read

npx agent-roast # review what you have not committed yet (on a clean tree: replay your last commits)

Stop your coding agent from doing it

npx agent-roast hook install          # Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Factory Droid, Kiro and Antigravity CLI

For Claude Code there is also a plugin: /plugin install agent-roast --marketplace Nari-Ab/agent-roast. Any agent that speaks MCP can also call agent-roast as a read-only tool, agent-roast mcp (setup).

When the agent is about to finish, agent-roast reviews everything it changed. If a check got weaker, the agent is sent back once, with the file, the line and the before and after, and told to fix the code instead. If it tries again, you get a warning rather than an endless loop. Anything agent-roast cannot check lets the agent finish: it never breaks a session. An intended change is accepted by committing it. Not sure yet? npx agent-roast hook install --advisory only warns you and never sends the agent back. Setup for each agent, what it does not do, and how to pause it: docs/integrations.md.

The agent hooks follow each agent's documented hook protocol and are tested with simulated hook input, not yet in long live

sessions with every agent. Reports of what you see are welcome.

Check every pull request

# .github/workflows/agent-roast.yml

name: Agent Roast on: pull_request permissions: { contents: read, pull-requests: write } jobs: audit: runs-on: ubuntu-latest steps:

  • uses: actions/checkout@v4 with: { fetch-depth: 0 }
  • uses: Nari-Ab/agent-roast@v1 with: { comment: true } # one comment, updated on every push; add advisory: true to try it without failing PRs

Also: npx agent-roast review --base origin/main in any CI, npx agent-roast init --hook or the pre-commit framework for the next commit, and SARIF output for code scanning. Policy is read from the base branch, so a pull request cannot switch off the rules that review it. Before you decide, npx agent-roast replay shows what it would have said about your last 50 commits.

What it catches

RuleFires whenBy default
assertion-weakenedan exact check is replaced by a weaker one: toBe(42) → toBeDefined(), toBe(2) → toBeLessThanOrEqual(2), toBe(2) → not.toBe(0), toEqual(x) → toMatchObject(x), assert x == 1 → assert xblocks
guard-weakeneda coverage threshold is lowered, strict is switched off, a lint rule is downgraded, a CI step may fail, a workflow stops running tests, a conftest.py hook sets a report to passedblocks
test-skipa test that was already there is switched off or expected to fail: it.skip, @pytest.mark.skip, @pytest.mark.skipif(True), @pytest.mark.xfail, it.fails, test.fixme, t.Skip, #[ignore], @Disabled, [Ignore], xit, ... (a new test that is skipped is not reported)blocks
test-focus, trivial-assert.only / fit; expect(true).toBe(true) and its relatives in ten languages, assert x or True; a test that asserts on a function it mocked itselfblocks
assertion-removed, test-removed, expectation-rewrittena test loses assertions, disappears, or its expected value is edited next to production codewarns
swallowed-error, type-escape, stub-abandonmentcatch {} / except: pass, as any / # type: ignore / # pragma: no cover / istanbul ignore, throw new Error("Not implemented")warns

Renames, moved tests, parametrization, moved assertions and reformatting are recognized and not reported, and neither is a skip that depends on the environment (if testing.Short() { t.Skip() }, test.skip(isMobile, ...)). JavaScript/TypeScript, Python and Go get the full before/after comparison; skips and placeholder assertions also cover Rust, Java, Kotlin, C#, Ruby, PHP and Swift; CI and config files are checked whatever the language. Each rule with examples and limits: docs/rules.md.

Configure

Rules, severities and paths live in .agentroastrc.json at the repository root (npx agent-roast init writes a starting file):

{

"failOn": ["assertion-weakened", "guard-weakened", "test-skip", "test-focus", "trivial-assert"], "rules": { "type-escape": "off" }, "ignorePaths": ["/generated/"] }

A change cannot edit this file to relax its own review, because it is read from HEAD or the base branch. To accept one intentional finding, add an expiring exception instead of turning a rule off, and adopt an existing project without blocking on old debt with a baseline: docs/reference.md.

Does it work?

Measured, with the denominators and the caveats in docs/benchmarks.md. Weakened checks are rare, mostly deliberate, and not specific to AI. agent-roast is a tripwire that asks about them. On repositories it had not seen, between a quarter and two thirds of its blocks were questions with a harmless answer, depending on the sample.

  • 169 of 169 hand-labeled cheating edits are caught and 158 of 158 harmless look-alikes (reformats, moves, raised thresholds, environment-gated skips) stay silent. The cases were written with the detector, so they guard against regressions; they do not prove accuracy. One gap is documented and still open.
  • A catalog of cheats that someone else wrote. Of the nine hacks in reward-hack-zoo (hand-written specimens; none from a model) four are reported (a skip, a patched target, a conftest.py that rewrites reports, an edited expected value as a warning) and none of its six honest solutions. The five that are not (special-casing, swallowed errors, overfitting) live in the code, and a search of 126,486 commits shows why a tool that reads text cannot report them: their shape is the shape of ordinary code (section 13).
  • 12,645 commits that touch tests or CI/config in 166 public repositories: blocking rules fired on 0.3% of AI-signed commits (Claude, Copilot, Cursor, Codex, Devin, aider) and on 0.3% of the others. Inside the same repositories the odds for an AI-signed commit were 0.81 times those of another commit (95% CI 0.40–1.67). There is no sign that AI-signed commits weaken checks more often.
  • On repositories it was not written from, between a quarter and two thirds of the blocked commits were false alarms. Twelve samples of 39 or 40 public repositories (476 in all, 135,095 commits) were replayed and every blocked commit was read. The share was 69% for 0.17.0 on the first sample and on the fourth, 51% for 0.18.0 on the fourth and 27% on the fifth, which it had not seen either. This version, frozen before the sixth sample was drawn, blocked 100 of its 11,335 commits: 34 changed a check a reviewer should see (an assertion that got weaker, a gate that was relaxed, a test switched off or left focused) and 66 were false alarms, but 51 of the 66 were one defect in one repository, an array of mypy overrides read as one table, which is fixed in this release; the released build blocks 44 of those commits, 34 and 10. A new test that asserts nothing counts as a block for a reviewer; counted as false alarms, 13 of 33 on the fifth sample and 72 of 100 on the sixth. Most of the rest, in the earlier measurements too, were deliberate and explained. One reader (an AI assistant) sorted them, and the fixes were made from the same sorting, so treat the figures as a first estimate. The published 0.19.0 blocked 31 of the 12,000 commits of the seventh sample: 16 for a reviewer and 15 false alarms (48%, 6 of them one repository's lint configuration); the build with the fixes from reading it, tried on an eighth sample that it had not seen, blocked 26 of 11,081 commits: 16 for a reviewer and 10 false alarms (38%), and the fixes from reading that one are in this release too; 0.21.0 as it was frozen blocked 46 of 11,286 commits of a ninth sample that it had not seen: 28 for a reviewer and 18 false alarms (39%), and five of those are fixed in it; 0.21.0 as it shipped blocked 40 of the 11,191 commits of a tenth sample that it had not seen either: 27 for a reviewer and 13 false alarms (33%), and three of those 13 are fixed in this release; 0.25.0 as it ships blocked 26 of the 10,633 commits of an eleventh sample that it had not seen either: 19 for a reviewer and 7 false alarms (27%; between 23% and 85% with its 16 arguable calls made the other way); 0.27.0 as it ships blocked 28 of the 11,061 commits of a twelfth sample that it had not seen: 18 for a reviewer and 10 false alarms (36%; between 25% and 54% with its 11 arguable calls made the other way), the same 28 that 0.26.0 blocks (section 9, section 10, section 11, section 12, section 14, section 15, section 16, section 18, section 19, section 20).
  • **9,732 commits com

Only the beginning is shown; read the rest in the repo