Install
$ agentstack add mcp-rumblingb-secret-scanner-mcp ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Secret Scanner MCP Server
Detect leaked API keys, tokens, passwords, and private keys in text, files, or directories — directly via the Model Context Protocol (MCP).
Overview
Secret Scanner is an MCP server that helps AI agents and developers identify accidentally exposed credentials before they cause a breach. With 40+ regex patterns covering major providers, it scans text, files, directories, and git history for leaked secrets.
Tools
| Tool | Description | |------|-------------| | scan_text(text) | Scan any text for API keys, tokens, passwords, private keys | | scan_file(path) | Scan a file for leaked secrets | | scan_directory(path, max_file_size_mb?, include_patterns?) | Recursively scan a directory | | scan_git_history(path, max_commits?) | Scan git commit history for committed secrets | | mask_secrets(text) | Replace all detected secrets with [REDACTED] |
Supported Patterns (40+)
Critical
- Stripe:
sk_live_*,rk_live_* - GitHub:
ghp_*,gho_*,ghu_*,ghr_*,github_pat_* - AWS:
AKIA*, Secret Access Keys - Google:
AIza*API Keys, OAuth Client Secrets - OpenAI:
sk-*,sk-proj-* - Anthropic:
sk-ant-*,sk-ant-api03-* - Slack: Bot tokens (
xoxb-*), User tokens (xoxp-*), Webhooks - Discord: Bot tokens, Webhook URLs
- JWT Tokens
- Private Keys: RSA, EC, OpenSSH, PGP
High
- Databases: PostgreSQL, MySQL, MongoDB, Redis connection strings
- GitLab: Personal tokens (
glpat-*), CI tokens (glci-*) - Square: Access tokens (
sq0atp-*), Secret keys (sq0csp-*) - Twilio: API Keys, Auth Tokens
- Telegram Bot Tokens
- NPM, PyPI, Docker Hub tokens
- SendGrid, Mailgun, Datadog API keys
- Hugging Face tokens (
hf_*)
Medium
- Generic password/secret assignments
- Basic auth in URLs
- Bearer tokens in headers
- Cookie/session secrets
- Cloudflare, SonarQube, Pulumi tokens
Low
- AWS Account IDs
- Internal IP addresses (RFC 1918)
- S3 bucket endpoints
- Email addresses
Installation
pip install -r requirements.txt
Usage
With an MCP Client
Add to your MCP client configuration:
{
"mcpServers": {
"secret-scanner": {
"command": "python",
"args": ["/path/to/secret-scanner-mcp/server.py"]
}
}
}
Direct Invocation
python server.py
Example: scan_text
{
"text": "AWS_KEY=AKIAIOSFODNN7EXAMPLE\npassword=super_secret_123"
}
Returns:
{
"scan_type": "text",
"total_findings": 1,
"summary_by_severity": { "critical": 1, "high": 0, "medium": 0, "low": 0 },
"findings": [
{
"type": "AWS Access Key ID",
"value": "AKIA****AMPLE",
"severity": "critical",
"category": "aws",
"line": 1,
"column": 9,
"context": "AWS_KEY=AKIAIOSFODNN7EXAMPLE"
}
]
}
Example: mask_secrets
{
"text": "My OpenAI key is sk-abc123def456 and my password is secret!"
}
Returns:
{
"original_length": 52,
"masked_length": 52,
"secrets_redacted": 2,
"masked_text": "My OpenAI key is [REDACTED-OpenAI API Key] and my password is [REDACTED-Generic Password Assignment]!"
}
Why Use Secret Scanner?
- Security-first: Catch leaked credentials before they reach production
- CI/CD integration: Run scans as part of your build pipeline
- Git history scanning: Find secrets that were already committed
- AI-ready: Every AI agent developer can use it to check configs, env files, and chat logs for leaked keys
- Comprehensive: 40+ patterns covering Stripe, GitHub, AWS, Google, OpenAI, Anthropic, Slack, Discord, and more
Pricing
$19/month — Single developer license with unlimited scans.
Support development: Buy a license
License
Proprietary — see LICENSE file for details.
Source & license
This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: Rumblingb
- Source: Rumblingb/secret-scanner-mcp
- License: MIT
- Homepage: https://rumblingb.github.io/secret-scanner-mcp/
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.