rea
Reverse engineer anything with agents, from app behavior down to native binaries.
Catches your AI coding agent when it games the tests - locked-test hashes, tamper detection.
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 | 0/80 | GitHub stars or weekly downloads: the larger counts 60, the smaller 20 |
|---|---|---|
| Freshness | 3/12 | 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 | 3/100 |
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.
Passed 3/3 checks · Runs on your computer
First: which AI do you use?
Pick your app and the steps appear below.
Claude cannot connect Keel yet
The maker has not listed install details in the MCP Registry yet
ChatGPT cannot connect Keel yet
The maker has not listed install details in the MCP Registry yet
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
Claude Code cannot connect Keel yet
The maker has not listed install details in the MCP Registry yet
Cursor cannot connect Keel yet
The maker has not listed install details in the MCP Registry yet
VS Code cannot connect Keel yet
The maker has not listed install details in the MCP Registry yet
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 tdalbanmoreynas, which owns the repo
Code last changed 4 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
If you made this, paste this code into your README. The badge links back to this page.
[](https://mcp.popnx.com/en/servers/tdalbanmoreynas-keel)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 4 months ago, and the latest version (1.0.0) reached the registry 4 months ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code.
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 Keel | 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.
An observable autonomy harness for AI coding agents. — *by TokenDrift*
keel is an MCP server that gives your coding agent (Claude Code, Cline, …) the tools to run a long task end to end — without drifting, cheating, or losing its work — while recording everything it does so you can steer on cost and quality.
You start the task. The agent disciplines itself. You come back to a milestone report.
The name: a keel is the part of a boat you never see — the spine under the waterline that stops it from being blown sideways by the wind. That's the job.
An agent left alone on a long task tends to do four things you can't see until it's too late:
keel puts a tool on each of these, and the agent calls them itself — because the rules are injected into its CLAUDE.md at init. Every call emits an event, so the whole run is legible afterward.
A real run on a throwaway calc-kit project — the agent was told to implement add(a, b) so the locked tests pass, following the keel protocol. This is the actual sequence, unedited:
1. load_context → project loaded, tests intact
Then, to show the anti-cheat is real — we modified a locked test file by hand (simulating an agent tampering to force a green) and ran verify:
{
"tampered": true, "tests_changed": ["~ tests/test_calc.py (modified)"], "passed": true }
tampered: true and passed: true at the same time. keel doesn't confuse "the tests pass" with "the tests are intact" — it reports both axes separately. An agent can make the suite green *by rigging it*, and keel still sees it. That distinction is the whole point.
The hard problem with any optional-tool harness: an agent can ignore verify and just run pytest in the terminal, short-circuiting the one mechanism that catches cheating. A polite instruction in CLAUDE.md shapes what the agent *tries* to do — it doesn't *stop* anything.
keel closes this with three layers, on the principle that no single layer is perfect but together no path is simultaneously easy, silent, and untraced:
CLAUDE.md block tells the agent, in no uncertain terms, that verify is the only judge and direct test runs are forbidden. Handles the dominant case: an agent that drifts out of negligence, not malice.init_project installs a PreToolUse hook (keel-guard) into the project's .claude/settings.json. It intercepts pytest, python -m pytest, npm test, yarn test, go test before they execute and refuses them, redirecting the agent to verify. This runs in the Claude Code harness, outside the model's control. On our setup it holds even under `--dangerously-skip-permissions` (bypass mode skips interactive confirmations, not hooks — verify on your own machine, see *Honest limits*).verify emits a hash of the exact working-tree state it judged, and checkpoint only marks a milestone certified if a passing, untampered verify ran against *that same tree*. A bypass produces an uncertified milestone — visible in stats and report — rather than a silent one.Layer 2 makes the obvious bypass hard. Layer 3 makes *every* bypass visible. keel certifies what it witnessed; it doesn't claim to make evasion impossible — and that honesty is exactly what produces the "% certified milestones" signal worth tracking over time.
The golden rule that makes it work: you write the tests, never the agent. verify runs your locked suite and detects any change to it, file by file. If you change the tests yourself, re-run lock_tests (a human action).
keel is plain Python — one dependency (the MCP SDK, which pulls in FastMCP and pydantic), plus git. It is developed and hardened on Windows, and runs on macOS/Linux.
git clone https://github.com/tdalbanmoreynas/keel.git
cd keel python -m venv .venv pip install -r requirements.txt python keel_server.py # must start without error (Ctrl-C to quit)
On Windows the venv activation is .venv\Scripts\activate; on macOS/Linux it's source .venv/bin/activate. Activation is optional if you point your client at the venv's Python directly (below).
# from the keel folder, pointing at the venv's interpreter (absolute paths)
claude mcp add keel -- /absolute/path/to/keel/.venv/bin/python /absolute/path/to/keel/keel_server.py
Windows example:
claude mcp add keel -- "D:\path\to\keel\.venv\Scripts\python.exe" "D:\path\to\keel\keel_server.py"
Or paste the block from mcp_config.example.json into your client's config (Cline: cline_mcp_settings.json).
Two things that will save you a debugging session:
mcp__keel__*), or the agent's first keel call hangs waiting on an authorization prompt that doesn't always surface.keel-guard hook loads from the current directory's .claude/settings.json with no parent fallback — it's active when Claude Code runs from where the project lives.keel has two parts, and they have different reach.
The 12 MCP tools are standard MCP — they work with any MCP-capable coding agent: Claude Code, Codex, Cursor, Cline, Windsurf, Zed, VS Code + Copilot, Continue, Goose, and the Cline forks (Roo Code, Kilo Code). Memory, checkpoints, the anti-tamper verify, attestation, decision logging, cost tracking, and route_task all run anywhere MCP runs.
The `keel-guard` hook (layer 2) is Claude Code–specific. It's a PreToolUse hook in .claude/settings.json — a Claude Code mechanism that no other client implements today. So:
| Client | MCP tools (layers 1 & 3) | Mechanical guard (layer 2) |
|---|---|---|
| Claude Code | ✅ Full | ✅ Yes — the keel-guard hook installs and fires |
| Codex, Cursor, Cline, Windsurf, Zed, Copilot, Continue, Goose | ✅ Full | ⚠️ Not installed — no hook system |
On a non–Claude Code client you still get the persuasion layer (the injected rules) and, crucially, the attestation layer: a checkpoint that skipped verify still comes out uncertified in stats and report. You lose the mechanical block on direct test runs, but you don't lose visibility — the bypass is still recorded. That's the proof-regime design paying off: the guarantee that *matters* (you can always tell whether a milestone was verified) doesn't depend on any one client's hook system.
Claude Code is where keel is fullest and where it's developed and hardened. Other clients are first-class for everything except layer 2.
init_project: creates .keel/, writes the architecture and immutable constraints, locks your test files, initializes git, installs the keel-guard hook, and injects the autonomy rules into CLAUDE.md.load_context at the start of every session, save_progress + checkpoint after each step, verify to validate, log_usage after each model call, record_decision at each architectural choice, report at the end.You come back at milestones, not at every line.
| Tool | Role | Guards against |
|---|---|---|
init_project | Lays the harness (architecture, constraints, test lock, git, hook, CLAUDE.md) | — |
load_context | Resumption briefing at session start | Context loss |
save_progress | Writes done / doing / todo to disk | Context loss |
record_decision | Append-only log of architectural choices | Architectural drift |
checkpoint | Git commit of the step, with certification | File loss |
verify | Runs the locked tests, detects tampering | Cheating (reward hacking) |
lock_tests | Re-locks the tests (human action) | — |
check_drift | Recalls constraints, flags unsaved work | Drift |
route_task | Most cost-effective model for a subtask | Cost / data sovereignty |
log_usage | Records real spend of a model call | Cost observability |
stats | Aggregated metrics (cost, cheating, certification, velocity) | Steering |
report | Markdown milestone report for the human | Steering |
Every tool emits an event to .keel/events.jsonl (local, private to your repo). From that trace, keel continuously derives: sessions, checkpoints, certified vs. uncertified milestones, verify pass rate, cheating alerts, real cost per model, and velocity. That trace is what makes an agentic run legible — and it's the raw material for the funded layer below.
keel is one product in two pieces. This repo — the local sensor — is free and MIT, forever. It runs entirely on your machine: it watches your agent, catches tampering, tracks waste and cost, and writes everything to a local events.jsonl that never leaves your repo. A solo developer needs nothing else.
The funded piece is a cloud dashboard for engineering teams (*by TokenDrift*), planned, on top of the same sensor. Where the free tier answers *"how is my agent doing?"*, the team dashboard answers *"how is my whole team doing, over time?"* — by aggregating the sensors of every developer on the team: total agent spend and recoverable waste, the share of milestones that were honestly certified (not just green), real-time alerts when a budget or a cheat-rate spikes, and anonymized benchmarking against other teams (*"your agents tamper 3× more than the median"*).
The split is deliberate: the sensor is free because a local binary is cloneable and can't be sold — its job is to be useful and to spread. The paid value lives in the team-level network and aggregated data, which a single local install structurally can't produce. Same model as Langfuse, PostHog, and Sentry: free and complete for the individual; paid when you become a team that needs the collective view.
Privacy is built into the split: the sensor sends metadata only — never your code or prompts. Cheat detection runs locally; only the verdict (certified / suspect) would ever leave the machine.
route_task and pricesThe model prices (keel_core.py, MODELS constant) are June 2026 estimates — replace them with your real rates. route_task accounts for agentic burn (cost = tokens × iterations × inefficiency) and excludes non-EU clouds when sensitive=True, which is why a sensitive subtask in the run above was routed to an EU-hosted model.