
Leakferret
Gives Claude tools to find hardcoded secrets in your codebase, verify they're actually live by calling the provider API, and rewrite them in place to pull from environment variables. Exposes scan_repository, classify_candidates, verify_finding, and propose_rewrite over MCP. The agent can check its own work before committing, catching real AWS keys or Stripe tokens while ignoring documented examples and placeholders. Verification happens locally against 15+ providers including GitHub, Anthropic, OpenAI, and Datadog. Useful when you want an agent writing code but don't want to manually audit every diff for leaked credentials.
- GitHub stars
- 3
- tools
- 5
- transport
- STDIO
- last updated
- Jun 3, 2026
Tools
5 toolsPublic tool metadata for what this MCP can expose to an agent.
scan_repositoryScan a repository for hardcoded secrets.
Scan a repository for hardcoded secrets.
No parameter schema in public metadata yet.
classify_candidatesClassify secret candidates found by a scan.
Classify secret candidates found by a scan.
No parameter schema in public metadata yet.
verify_findingVerify whether a finding is a live secret by calling the provider.
Verify whether a finding is a live secret by calling the provider.
No parameter schema in public metadata yet.
propose_rewritePropose a rewrite of a leaked secret to read from an environment variable.
Propose a rewrite of a leaked secret to read from an environment variable.
No parameter schema in public metadata yet.
baseline_diff
No parameter schema in public metadata yet.
Sponsors
Readme
leakferret
MCP-native secret scanner — verified findings, agent-applied rewrites.
Details
- Repository
- github.com/leakferrethq/leakferret
- Category
- AI & LLM Tools
- Package
@leakferret/mcp- Transport
- STDIO
- Registry
- MCP registry, active