rea
Reverse engineer anything with agents, from app behavior down to native binaries.
Deterministic, offline root-cause analysis and pre-commit fix verification for coding agents.
Skills that teach the AI this kind of work; they work alongside this one
Reverse engineer anything with agents, from app behavior down to native binaries.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Lists are ordered by a usage score (out of 100) built from these parts
| Popularity | 10/80 | GitHub stars or weekly downloads: the larger counts 60, the smaller 20 |
|---|---|---|
| Freshness | 7/12 | Full marks for a release or code change within 30 days |
| Still answering | 0/8 | The cloud endpoint answered at the last check |
| Usage score | 17/100 |
Quality: Passed 3/3 basic checks (shown, not used for ordering) · Momentum: No data yet (Used only on the Trending tab)
Pick the AI app you use, then copy the settings.
Let your AI install it with one sentence
Please install culprit. Follow https://mcp.popnx.com/i/noordeen123-culprit.md, show me the commands and wait for my OK before running them.Paste it into an AI that can work on your computer (such as Claude Code or Cursor). It reads our steps, shows you the commands and waits for your OK. No key, no sign-up. · See the full text your AI reads
Passed 3/3 checks · Runs on your computer · ✓ Commands checked Nov 13, 2026
First: which AI do you use?
Pick your app and the steps appear below.
Works with Claude, with some setup first
Install Python (uv) on your computer first (one time) · Only the Claude desktop app (Windows or Mac), not the web or phone
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 culprit for Claude on this computer, in this order: 1) Check uv with uv --version. If it is missing, tell me to install it from https://docs.astral.sh/uv/getting-started/installation/; do not install it yourself. 2) Use only this config (already checked by PopNx MCP): { "mcpServers": { "culprit": { "command": "uvx", "args": [ "culprit" ] } } } 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 culprit 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.
Already installed? Check first · Open Terminal, type this command and press Enter
uv --versionMac: press ⌘ + Space, type Terminal, press Enter
Windows: open Start, type Windows PowerShell, then Open
Not installed: uv has no click-through installer. Copy the one-line command for your system (macOS or Windows) from uv’s official page into Terminal · no separate Python install needed; uv downloads it when required
When it’s done, close Terminal, open it again and run the same command. You should see a version number: uv --version
Install once; it works for everything that needs uv
SettingsDeveloperEdit Config
{
"mcpServers": {
"culprit": {
"command": "uvx",
"args": [
"culprit"
]
}
}
}Use culprit and tell me what you can do for me, then show me one thing✓ If Claude says it is using culprit or shows a culprit 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 culprit yet
culprit runs on your computer, but ChatGPT can only connect servers that run on the web
A · Use an app that can connect culprit
B · Others in Developer tools 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 Python (uv) on your computer first (one time)
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 culprit for Claude Code on this computer, in this order: 1) Check uv with uv --version. If it is missing, tell me to install it from https://docs.astral.sh/uv/getting-started/installation/; do not install it yourself. 2) Use only this config (already checked by PopNx MCP): claude mcp add --scope user culprit -- uvx culprit 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 culprit 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.
Already installed? Check first · Open Terminal, type this command and press Enter
uv --versionMac: press ⌘ + Space, type Terminal, press Enter
Windows: open Start, type Windows PowerShell, then Open
Not installed: uv has no click-through installer. Copy the one-line command for your system (macOS or Windows) from uv’s official page into Terminal · no separate Python install needed; uv downloads it when required
When it’s done, close Terminal, open it again and run the same command. You should see a version number: uv --version
Install once; it works for everything that needs uv
Mac: press Command+Space and type Terminal · Windows: open PowerShell
claude mcp add --scope user culprit -- uvx culpritYou should see culprit listed as connected
Use culprit and tell me what you can do for me, then show me one thing✓ If Claude Code says it is using culprit or shows a culprit 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 Python (uv) on your computer first (one time)
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 culprit for Cursor on this computer, in this order: 1) Check uv with uv --version. If it is missing, tell me to install it from https://docs.astral.sh/uv/getting-started/installation/; do not install it yourself. 2) Use only this config (already checked by PopNx MCP): { "mcpServers": { "culprit": { "command": "uvx", "args": [ "culprit" ] } } } 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 culprit 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.
Already installed? Check first · Open Terminal, type this command and press Enter
uv --versionMac: press ⌘ + Space, type Terminal, press Enter
Windows: open Start, type Windows PowerShell, then Open
Not installed: uv has no click-through installer. Copy the one-line command for your system (macOS or Windows) from uv’s official page into Terminal · no separate Python install needed; uv downloads it when required
When it’s done, close Terminal, open it again and run the same command. You should see a version number: uv --version
Install once; it works for everything that needs uv
Use culprit and tell me what you can do for me, then show me one thing✓ If Cursor says it is using culprit or shows a culprit 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 Python (uv) on your computer first (one time)
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 culprit for VS Code on this computer, in this order: 1) Check uv with uv --version. If it is missing, tell me to install it from https://docs.astral.sh/uv/getting-started/installation/; do not install it yourself. 2) Use only this config (already checked by PopNx MCP): { "servers": { "culprit": { "type": "stdio", "command": "uvx", "args": [ "culprit" ] } } } 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 culprit 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.
Already installed? Check first · Open Terminal, type this command and press Enter
uv --versionMac: press ⌘ + Space, type Terminal, press Enter
Windows: open Start, type Windows PowerShell, then Open
Not installed: uv has no click-through installer. Copy the one-line command for your system (macOS or Windows) from uv’s official page into Terminal · no separate Python install needed; uv downloads it when required
When it’s done, close Terminal, open it again and run the same command. You should see a version number: uv --version
Install once; it works for everything that needs uv
Use culprit and tell me what you can do for me, then show me one thing✓ If VS Code says it is using culprit or shows a culprit 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
Claude Code
claude mcp add --scope user culprit -- uvx culpritClaude Desktop (claude_desktop_config.json)
{
"mcpServers": {
"culprit": {
"command": "uvx",
"args": [
"culprit"
]
}
}
}Cursor (~/.cursor/mcp.json)
{
"mcpServers": {
"culprit": {
"command": "uvx",
"args": [
"culprit"
]
}
}
}VS Code (mcp.json)
{
"servers": {
"culprit": {
"type": "stdio",
"command": "uvx",
"args": [
"culprit"
]
}
}
}These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
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
Runs on your computer; the tool list appears in your AI app after you install it.
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 19, 2026
The registry name was verified with the GitHub account noordeen123, which owns the repo
Code last changed 3 months ago
Uses MIT
This one runs on your computer; there is no internet endpoint
Runs on your computer and uses local settings instead
Runs on your computer; we can only read tool lists from internet endpoints
No entries on OSV.dev for culprit@0.4.0
Checks only this package version, not every dependency · checked Nov 15, 2026
If you made this, paste this code into your README. The badge links back to this page.
[](https://mcp.popnx.com/en/servers/noordeen123-culprit)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.
No reviews yet
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
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.
The registry does not list a required key, though some servers ask you to sign in on first use.
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).
The GitHub repo last changed 3 months ago, and the latest version (0.4.0) reached the registry 4 months ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Python (uv) on your computer.
In the same category: GitDiagram, Appllama, Cloudflare MCP, Omnara, Repowise
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
Architecture diagrams, explanations and Mermaid source for public GitHub repositories.
Study screens, flows and paywalls from top-earning iOS apps, then build from what wins.
Cloudflare MCP servers
Deploy durable AI agents with Omnara, an open-source managed-agent platform.
Codebase intelligence for AI coding agents: graph, git history, docs, decisions, code health.
| This one culprit | GitDiagram | Appllama | Cloudflare MCP | Omnara | Repowise | |
|---|---|---|---|---|---|---|
| Runs where | Installs on your computer | Runs in the cloud, nothing to install | Runs in the cloud, nothing to install | Runs in the cloud, nothing to install | Runs in the cloud, nothing to install | Cloud or install on your computer |
| Needs a key | No | No | No | No | No | No |
| Add with + in Claude | No | No | No | Yes | No | No |
| Basic checks | 3/3 | 4/4 | 4/4 | 4/4 | 4/4 | 5/5 |
| License | MIT | MIT | MIT | Apache-2.0 | Apache-2.0 | AGPL-3.0 |
| Price | No cost listed in the registry | No cost listed in the registry | No cost listed in the registry | No cost listed in the registry | No cost listed in the registry | No cost listed in the registry |
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.
Root-cause analysis for agent-driven development.
Your coding agent finds what introduced a bug, and verifies its own fix is complete before it commits.
Quick start · Tools · Accuracy · Architecture · MCP registry
A real run. The fix patched one caller of parse_config and missed two, so it scores partial .
An agent can dig through git history to find what broke, and it is good at it. What it will not reliably do is spend a dozen tool calls on that every time, or stop and check whether the helper it just changed has three other callers before it commits. culprit turns both into one deterministic call that returns structured JSON it can act on:
| The agent asks | culprit answers |
|---|---|
| "What introduced this bug?" | Ranked suspect commits, the author's intent, the releases it shipped in |
| "Is my fix complete?" | verify_fix: missed call sites, whether a test shipped, a risk level |
| "What could this change break?" | Reverse-import dependents, covering tests, high-risk shared modules |
Benchmarked against 50 real regressions, 25 from git and 25 from systemd, where the introducing commit is known from each fix's Fixes: trailer (author-verified ground truth). Given only the fix commit, culprit blames the removed lines to rank the commits that introduced the bug.
| Metric | Result |
|---|---|
| Introducing commit ranked #1 | 50% (25/50) |
| Introducing commit in the top-5 suspect set | 66% (33/50) |
Deterministic and offline, on large C codebases the engine has never seen. Reproduce with python benchmarks/run.py, which clones the repos and scores every case.
git blame itselfIt can, and it is good at it. So the honest question is not whether culprit is accurate, but whether it beats or helps an agent that has git and no culprit. Same 10 regressions, three arms, isolated so no arm can read the answer from the fix commit:
| culprit alone | agent alone | agent + culprit | |
|---|---|---|---|
| Introducing commit ranked #1 | 80% | 90% | 90% |
| Introducing commit in top 5 | 90% | 100% | 100% |
| Mean tool calls to get there | 1 | 14.9 | 8.8 (-41%) |
| Mean tokens to get there | ~0 | 55,534 | 47,616 (-14%) |
The agent wins on accuracy, and culprit does not make it more accurate. What culprit does is get it there in roughly half the steps for about 8,000 fewer tokens per investigation. Tool calls dropped in 10 of 10 cases, tokens in 7 of 10. On the hardest case the agent needed 42 tool calls and 124k tokens alone, against 16 calls and 84k with culprit.
Those savings are already net of reading culprit's output, which is counted in the third column. culprit's own run is one deterministic call, no model, under a second.
So culprit is an accelerator for an agent, not a replacement for one, and not a smarter blamer than one. Method, caveats (n=10, and this slice is easier than the full 50), and reproduction: benchmarks/agent/.
Claude Code plugin (installs the MCP server plus a skill that tells the agent when to use it):
/plugin marketplace add noordeen123/culprit
/plugin install culprit@culprit
Any MCP client (Cursor, Windsurf, VS Code, Codex CLI, Zed, Continue, Cline, Amazon Q, Goose):
{
"mcpServers": { "culprit": { "command": "uvx", "args": ["--from", "culprit[mcp]", "culprit-mcp"] } } }
CLI, no agent required:
uvx culprit # run from PyPI on demand
rca --verify-fix patch.diff # exit 0 if complete, 1 otherwise
Needs Python 3.10+ and uv for the MCP server. The CLI runs on 3.9+.
| Tool | What it answers |
|---|---|
analyze | Full RCA in one call: classify, suspects or blast radius, risk, test impact |
verify_fix | Is this diff safe to commit? complete / partial / risky, plus the missed call sites |
find_suspects | Rank the commits that introduced the bug |
check_completeness | Call sites of the changed symbol the fix did not touch |
get_intent | The introducing commit's message, linked PR, referenced issues |
get_evolution | Per-commit history of the buggy lines via git log -L |
get_risk_score | QA gate score (0 to 100, low/medium/high) with contributing factors |
get_blast_radius | Feature impact: dependents, covering tests, high-risk files |
get_test_impact | Minimal test set to run for this change |
classify_change | Bugfix vs feature, with evidence |
from_trace | RCA straight from a stack trace, no diff or PR needed |
The agent runs this on its own diff before committing:
complete when no untouched call site is left behind, partial when one was missed, risky when risk is high. The verdict is the completeness axis; test coverage is the separate confidence axis on risk_level.Loop until complete, then commit. That is the whole idea.
rca # current branch vs the configured base
rca --last # the latest commit only rca --pr 16786 # a specific PR (uses the PR's own base) rca --trace crash.txt # RCA from a stack trace, no fix or PR needed rca --verify-fix patch.diff # check a diff before committing rca --select-tests # print the tests to run for this change rca --html report.html --open # a single self-contained HTML report rca --pr 16889 --fail-on high # exit non-zero when QA risk is high rca serve --repo /path # local web UI with a base picker
CI gate: risk via exit code only, no PR comments, no writes. Copy examples/github-actions/culprit-pr.yml into .github/workflows/:
- run: pip install "culprit>=0.3.0"
--html writes one self-contained file. No CDN, opens offline, attaches to CI. It opens with the verdict: a scored QA risk with the factors behind it, and the prime suspect with how long the bug lived.
Then it reconstructs how the bug got there. Every commit that touched the buggy line, from creation through the commit that broke it (red, with the exact diff) to the fix (green):
Every node expands to its diff. See the full report .
git bisectgit bisect | culprit | |
|---|---|---|
| Input | A reliable failing test | The fix diff (or a stack trace) |
| Method | Checks out commits and runs the test | Blames the fix's lines plus git log -L |
| Speed | Minutes (about log2(N) test runs) | Instant |
| Output | First bad commit | Suspect set, intent, lifecycle, completeness, risk |
| Confidence | Proof | Strong heuristic |
--bisect " " runs a real bisect as an optional confirmation layer, in a throwaway git worktree so your checkout is never touched. When the first failing commit matches the blamed suspect, the report stamps it confirmed by git bisect.
One normalized context in, one structured JSON result out. The only non-deterministic step is the optional LLM narrative, isolated behind an adapter so the engine runs with no API key.
Two lanes, one engine. Every module writes one slice of the result, so nothing cares whether the target came from gh, the REST API, local git, or a pasted stack trace. Full module map: docs/ARCHITECTURE.md.
The base branch resolves in order: the --base flag, then CULPRIT_BASE, then .culprit.toml (base = "origin/main"), then HEAD~1. --last forces the latest-commit view.
PR titles and labels use the GitHub CLI when present, or the unauthenticated REST API for public repos (set GITHUB_TOKEN or GITLAB_TOKEN to raise limits). Deep links cover GitHub, GitLab, Bitbucket, and Gitea. Blast radius reads imports across JS/TS, Python, Go, Java/Kotlin, Ruby, C/C++, C#, PHP, Rust, Scala, and Swift.
pip install -e ".[dev]" && pytest
Module map and data shapes: docs/ARCHITECTURE.md. Publishing the MCP server to the registries: docs/PUBLISHING.md. MIT licensed.