MCP server for ClassiFinder — secret scanning tools for AI agents
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"classifinder-mcp","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# ClassiFinder MCP Server An [MCP](https://modelcontextprotocol.io) server that gives AI agents the ability to scan text for leaked secrets and redact them before they reach an LLM. ## Installation ```bash pip install classifinder-mcp ``` ## Setup Get a free API key at [classifinder.ai](https://classifinder.ai), then add to your agent config: ### Claude Code ```json { "mcpServers": { "classifinder": { "command": "classifinder-mcp", "env": { "CLASSIFINDER_API_KEY": "ss_live_your_key_here" } } } } ``` ### Cursor Add to `.cursor/mcp.json` in your project: ```json { "mcpServers": { "classifinder": { "command": "classifinder-mcp", "env": { "CLASSIFINDER_API_KEY": "ss_live_your_key_here" } } } } ``` ## Tools ### `classifinder_scan` Scan text for leaked secrets and credentials. Returns findings with type, severity, confidence, and remediation guidance. ``` Agent: "Check this config for secrets" → classifinder_scan(text="AWS_ACCESS_KEY_ID=AKIAJGKJHSKLDJFH3284") → Found 1 secret: aws_access_key (critical, confidence 0.95) ``` ### `classifinder_redact` Replace all detected secrets with safe placeholders. Returns clean text safe to forward to any LLM. ``` Agent: "Clean this before sending to the model" → classifinder_redact(text="key=sk_live_EXAMPLE_KEY_HERE") → "key=[STRIPE_LIVE_SECRET_KEY_REDACTED]" ``` ## What It Detects **178 detection patterns:** - **164 secret types** across 10 categories: cloud/infra keys (AWS, GCP, Azure, Vercel including the 2024+ prefixed taxonomy vcp_/vci_/vca_/vcr_/vck_, Fly.io, Doppler, HashiCorp Vault, Cloudflare, Dropbox, JFrog/Artifactory and more); payment (Stripe, PayPal, Shopify with 4 token types, credit cards Luhn-validated, Square); VCS (GitHub, GitLab with 10 token types covering deploy/feed/runner/SCIM/k8s-agent/OAuth/feature-flag, Bitbucket); comms/SaaS (Slack including config/session/legacy variants, Twilio, SendGrid, Mailgun, Datadog, Sen…
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.