AI Bridge
Secure MCP server by fakoli that bridges Claude Code with OpenAI and Google Gemini APIs, featuring multi-layer security protection including prompt injection detection, content filtering, input sanitization, and configurable rate limiting. The implementation provides granular security controls with basic/moderate/strict modes, supports all major OpenAI models (GPT-4o, o1, o3-mini) and Gemini variants (1.5 Pro/Flash), and includes performance optimizations like pattern caching and early termination for fast validation. Built with comprehensive error handling, structured logging, and extensive test coverage, it serves developers who need secure AI API access with enterprise-grade protection against malicious prompts, content policy violations, and API abuse while maintaining flexibility for legitimate use cases.
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
- ai-ml
- Source
- PulseMCP
- Repository
- github.com/fakoli/mcp-ai-bridge
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve AI Bridge 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.