effect-mcp-server
Pass
Audited by Gen Agent Trust Hub on May 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a comprehensive documentation and code snippet repository for the Effect framework's MCP implementation. All instructions and examples align with official protocol standards and framework best practices.\n- [DATA_EXPOSURE]: The skill includes instructions for the agent to reference source code and documentation from a local path (~/.local/share/effect-solutions/effect/). This is a legitimate technique for providing context-aware development assistance and does not involve accessing sensitive credentials or personal data.\n- [INDIRECT_PROMPT_INJECTION]: The skill defines a framework for creating tools and resources that process external data, creating a potential surface for indirect prompt injection.\n
- Ingestion points: Tool parameters and resource URI templates defined using McpSchema.param.\n
- Boundary markers: Human-readable descriptions in tool and resource definitions provide context for the LLM.\n
- Capability inventory: The skill demonstrates capabilities for data fetching, calculations, and resource serving.\n
- Sanitization: The implementation relies on effect/Schema for strict runtime validation and type checking of all external inputs, providing a robust layer of protection against injection attacks.
Audit Metadata