Conceal
An MCP proxy server that performs pseudo-anonymization of personally identifiable information (PII) before data reaches external AI providers like Claude, ChatGPT, or Gemini. Built in Rust by Gianluca Brigandi, it intercepts MCP communications and uses configurable regex patterns combined with optional Ollama LLM-based detection to identify PII such as emails, phone numbers, SSNs, and IP addresses, then consistently replaces them with realistic fake data while maintaining semantic meaning and data relationships. The implementation includes a SQLite-backed mapping store for consistent anonymization across sessions, supports multiple detection modes (regex-only, LLM-only, or hybrid), and is designed for organizations that need to analyze sensitive data with AI assistants while preserving privacy and regulatory compliance.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-28.
Scan details: Circle-IR · 2026-09-28 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- database
- Source
- PulseMCP
- Repository
- github.com/gbrigandi/mcp-server-conceal
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve Conceal from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.