Performs plain-English security scans on AI-built applications and generates fix requests for coding agents.
Also known as contentasoftware/appledger
- Stars
- 0
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- 0.2.5
- Last commit
- Oct 14, 2026
- License
- MIT
What is AppLedger MCP?
AppLedger performs plain-English security scans on AI-built applications and generates fix requests for coding agents.
Summary generated from the project's README
About AppLedger MCP server
AppLedger provides security feedback for applications built using AI tools like Claude Code, Cursor, and Lovable. It scans application folders using independent tools to identify vulnerabilities and translates technical findings into plain English. The service helps developers understand what is wrong, why it matters, and how to fix it. It also generates a specific fix-prompt.md file that can be handed directly back to a coding agent to resolve issues.
Users can choose between a hosted mode or a local mode. In hosted mode, files that Git would commit are zipped and sent via HTTPS to appledger.net for scanning, while sensitive files like .env or SSH keys are strictly excluded. Local mode keeps all code on your machine by using installed versions of Trivy and Opengrep. The system uses Trivy to find leaked keys and outdated libraries, while Opengrep detects dangerous patterns like SQL injection. For those with an existing SonarQube server, local mode can optionally include those scans to check for code quality and security hotspots.
What you can do with it
- 1Generate AI fix requestsCreate a markdown file containing a ready-made instruction set that you can give to a coding agent to repair security flaws.
- 2Audit AI-generated code for vulnerabilitiesScan your application folder to find leaked passwords, outdated libraries, or dangerous patterns like SQL injection.
- 3Automate regular security inspectionsSet up daily or weekly automated scans using system schedulers like cron or Windows Task Scheduler.
Written from the project's README. Every use case is checked against a quote from it.
How to install AppLedger MCP
Formats verified 10 Nov 2026Install AppLedger MCP in Claude Code
$ claude mcp add --env APPLEDGER_KEY=<YOUR_APPLEDGER_KEY> appledger -- uvx appledgerInstall AppLedger MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"appledger": {
"command": "uvx",
"args": [
"appledger"
],
"env": {
"APPLEDGER_KEY": "<YOUR_APPLEDGER_KEY>"
}
}
}
}Install AppLedger MCP in VS Code
.vscode/mcp.json
{
"servers": {
"appledger": {
"type": "stdio",
"command": "uvx",
"args": [
"appledger"
],
"env": {
"APPLEDGER_KEY": "<YOUR_APPLEDGER_KEY>"
}
}
}
}Install AppLedger MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"appledger": {
"command": "uvx",
"args": [
"appledger"
],
"env": {
"APPLEDGER_KEY": "<YOUR_APPLEDGER_KEY>"
}
}
}
}Install AppLedger MCP in Codex
~/.codex/config.toml
[mcp_servers.appledger] command = "uvx" args = ["appledger"] [mcp_servers.appledger.env] APPLEDGER_KEY = "<YOUR_APPLEDGER_KEY>"
Install AppLedger MCP in Gemini CLI
~/.gemini/settings.json
{
"mcpServers": {
"appledger": {
"command": "uvx",
"args": [
"appledger"
],
"env": {
"APPLEDGER_KEY": "<YOUR_APPLEDGER_KEY>"
}
}
}
}Configuration
APPLEDGER_KEYSecretOptional dashboard connection key (al_...). Without it, nothing goes to a dashboard; a hosted check returns a link that saves its result to a free account (the summary is kept up to 24 hours).
APPLEDGER_MODEhosted (default): files Git would commit are sent to appledger.net, scanned and deleted. local: Trivy and Opengrep run on this machine.
| Name | Description | |
|---|---|---|
| APPLEDGER_KEY | Optional dashboard connection key (al_...). Without it, nothing goes to a dashboard; a hosted check returns a link that saves its result to a free account (the summary is kept up to 24 hours). | Secret |
| APPLEDGER_MODE | hosted (default): files Git would commit are sent to appledger.net, scanned and deleted. local: Trivy and Opengrep run on this machine. |
Automated checks
Ran Nov 14, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work
- Source repository linked and reachablecontentasoftware/appledger is public and reachablegithub.com/contentasoftware/appledger ↗Pass
- Package names this repository as its sourceappledger names contentasoftware/appledger as sourcepypi.org/project/appledger/ ↗Pass
- Build provenance (Sigstore attestation)Sigstore attestation for appledgerpypi.org/project/appledger/ ↗Pass
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-10-14github.com/contentasoftware/appledger ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNo popular package one edit away from appledgerPass
- No critical advisory in the package or its dependencies32 resolved dependencies checked; no critical advisoryosv.dev ↗Pass
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubAppLedger honest check
Honest security feedback, in plain language, for apps people build with AI tools such as Claude Code, Codex, Cursor and Lovable.
AppLedger checks your app folder with independent scanners and explains what they find in everyday words: what is wrong, why it matters, and what to do. It also writes a fix request you can hand straight to the AI tool that built the app, then checks again.
What it checks
| Scanner | Finds |
|---|---|
| Trivy | Leaked passwords and keys, outdated libraries with known security problems, risky container setup |
| Opengrep | Dangerous code patterns: SQL injection, command injection, unsafe data loading, debug mode left on |
| SonarQube (optional, local mode) | Code quality and more security hotspots, if you already run a SonarQube server |
Each run produces, in <your-app>/.appledger/:
report.html: a score, who may use the app right now (only you, your team, the whole company), and every problem in plain wordsfix-prompt.md: a ready-made fix request for your coding agentfindings.json: the same findings for tools and dashboards
Two ways to run
| Mode | What you install | Where your code goes |
|---|---|---|
| Hosted (default) | Only this package | Source files Git would commit are zipped, sent over HTTPS to appledger.net, scanned and deleted right after. Secret files are never sent. You confirm before the first upload of each folder |
Local (--local or APPLEDGER_MODE=local) |
Also Trivy, Opengrep and the Opengrep rules | Stays on your computer. With a connection key, only a summary goes to your dashboard (see below); --no-dashboard skips even that |
What gets uploaded in hosted mode
- Sent: files Git would commit (
git ls-files, including new files that aren't ignored). Outside a Git repository,.gitignoreis still honoured. - Never sent:
.envand.env.*(except.env.example,.env.sample,.env.template),*.pem,*.key,*.p12,*.pfx, SSH keys,.npmrc,.pypirc,.netrc,*credentials*.json,service-account*.json,secrets.*, the folderscert,certs,secrets,.sshand.aws,.claude/settings.local.json, Terraform state, password files, Ansible Vault files, Kubernetes/Helm secret manifests, certificates and similar (full list insrc/appledger/uploadpolicy.py). The server drops such files again as a second safety net. - Skipped: dependencies, build output, media, documents and data files (CSV, spreadsheets, slides, SQL, logs, data dumps) and files over 1 MB.
If a secret file is committed to Git or not ignored, the check reports it as a problem by file name. Its content is never read or sent.
See exactly what would be sent, and what is left out and why, without uploading anything:
python -m appledger path/to/your-app --list-files
The first hosted check of a folder asks you to confirm. In scripts and scheduled runs, pass --yes. If the code belongs to your employer or a client, make sure you're allowed to upload it, or use local mode.
Install
Claude Code plugin (recommended: adds the guided check-my-app skill):
claude plugin marketplace add contentasoftware/appledger
claude plugin install appledger@appledger
In the Claude Code desktop app, add the marketplace contentasoftware/appledger in the plugin settings instead. Start a new session, then ask: "Is my app safe to share?" or "Add this app to AppLedger".
MCP server only (needs uv):
claude mcp add appledger -- uvx --from appledger appledger-mcp
Command line:
pip install appledger
python -m appledger path/to/your-app
Step-by-step guide with troubleshooting: https://appledger.net/docs/
Version 0.2.0 (upload preview, consent, secret-file exclusion, scheduling) is being released to PyPI; until then pip install appledger gets 0.1.x.
Company dashboard
Create a free account at appledger.net to keep every app your people check in one ledger: owner, grade, score trend, who may use it and which AI tool built it. Create a connection key under "Connect a computer", then save it on each computer:
python -m appledger --connect al_your_key
Or tell Claude: "Connect AppLedger with this key: al_…". The key is saved in ~/.appledger/key; APPLEDGER_KEY overrides it and --disconnect removes it.
From then on each check also saves a summary to your dashboard: the app's name, score, grade, problem counts, the list of problems found (level and short title, up to 60; never code or file paths), and the scanners used. Never the code.
Not connected yet? From 0.2.3, a hosted check from a computer without a key ends with a save link, also shown in report.html:
Save this result to a free AppLedger ledger (link works for 24 hours): https://appledger.net/app/claim.php?t=...
Open it, create a free account or log in, and the check is in your ledger; the page then offers a key for that computer. Until the link is used, the service keeps only the check's summary (app name, score, the problems' levels and titles; never code), for up to 24 hours. A link works once; --no-dashboard turns it off.
You can also add an app in the web app with Add app: register it without code, or upload a zip to check it in the browser (the zip is scanned and deleted the same way).
Scheduled checks
python -m appledger path/to/your-app --schedule weekly --yes # or daily
python -m appledger --schedules # list
python -m appledger path/to/your-app --schedule off # stop
Uses Windows Task Scheduler on Windows and cron on macOS and Linux. Hosted scheduled checks need the one-time --yes consent; add --local to schedule local checks instead. --quiet prints one line per check.
Local mode setup
- Trivy:
winget install AquaSecurity.Trivy(Windows) orbrew install trivy(Mac) - Opengrep: download from the releases page and put it on your PATH
- Rules:
git clone --depth 1 https://github.com/opengrep/opengrep-rules.git ~/.appledger/opengrep-rules - Check:
python -m appledger --doctor
Repository layout
| Path | What |
|---|---|
src/appledger/scanner.py |
Scanners, plain-language translation, report and fix request |
src/appledger/client.py |
Picks the files to send (honouring .gitignore) and sends them to the hosted service |
src/appledger/uploadpolicy.py |
The full list of secret files that are never uploaded, used by client and server |
src/appledger/service.py |
Server side: unpacks an upload safely and scans it |
src/appledger/server.py |
Local MCP server used by the plugin |
plugin/ |
Claude Code / Codex plugin with the check-my-app skill |
tests/mcp_smoke.py |
Calls every MCP tool like an agent would |
License
MIT. The Opengrep community rules used by the scanner have their own license (Commons Clause); check it before using them in a paid service.
AppLedger MCP questions
How do I add AppLedger MCP to Claude Code?
Run claude mcp add --env APPLEDGER_KEY=<YOUR_APPLEDGER_KEY> appledger -- uvx appledger in your terminal. Add --scope user to make it available in every project.
How do I add AppLedger MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
How can I use the findings to fix my code?
The tool generates a 'fix-prompt.md' file which is a ready-made fix request that you can provide directly to your AI coding agent.