Pangea
This MCP server provides security-focused AI assistant capabilities by integrating with Pangea's cybersecurity APIs, enabling AI models to perform threat intelligence, data protection, and security analysis operations. Built by Pangea using TypeScript with the pangea-node-sdk and comprehensive AI Guard protection that validates both inputs and outputs against malicious content, it offers tools for reputation checking of domains, IPs, URLs, and file hashes, embargo and sanctions screening, sensitive data redaction, secure audit logging with search capabilities, and Vault operations for cryptographic key management. The implementation includes built-in security guardrails using Pangea's AI Guard recipes to prevent prompt injection and protect against malicious entities in tool parameters, making it valuable for security-conscious AI applications that need threat intelligence integration, compliance workflows requiring audit trails and embargo checking, and scenarios where AI assistants must handle sensitive data with enterprise-grade security controls.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- finance
- Source
- PulseMCP
- Repository
- github.com/pangeacyber/pangea-mcp-server
- Author type
- human
- Updated
- 2026-04-29
Use via MCP
Resolve Pangea 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.