identity-service
Verified Safeby agntcy
Overview
Provides currency exchange rate and trading tools via an MCP (Multi-Agent Communication Protocol) server, integrating with an identity service for authentication and authorization.
Installation
docker compose -f samples/docker-compose.yaml up -d currency-exchange-mcp-serverEnvironment Variables
- IDENTITY_SERVICE_GRPC_SERVER_URL
- IDENTITY_SERVICE_API_KEY
- CURRENCY_EXCHANGE_API_URL
Security Notes
The MCP server is built on FastAPI and uses modern HTTP clients (httpx). It delegates authentication and authorization to an external 'AGNTCY Identity Service' via a custom middleware (`IdentityServiceMCPMiddleware`). This middleware ensures that incoming requests are authorized using an API key and are linked to a specific tool or agent. No obvious direct 'eval' or raw system command execution is observed in the truncated sample code for the MCP server itself. Input validation for the `trade_currency_exchange` and `get_currency_exchange_rate` tools is critical but not fully visible in the truncated tool definitions; assuming FastAPI's typing provides some level of validation. A potential risk lies in the `CURRENCY_EXCHANGE_API_URL` environment variable, which, if misconfigured or pointing to a malicious external API, could lead to data integrity issues or SSRF (Server-Side Request Forgery) vulnerabilities. The overall security of this MCP server strongly depends on the robustness and proper configuration of the external Identity Service it relies on, which in development setup uses weak default credentials (e.g., 'postgres' password, 'default' vault token) as noted in the main backend's `env_setup.sh` script.
Similar Servers
mcp-gateway-registry
Provides a programmatic interface to interact with the main MCP Gateway Registry API, enabling tasks like registering/toggling services, managing groups/users, and intelligently discovering tools across registered services using semantic search and access control.
AgentUp
A developer-first framework for building, deploying, and managing AI agents, bringing Docker-like consistency and operational ease to AI agent development.
deepsecure
Provides a zero-trust security control plane for AI agents, enabling cryptographic identity, authenticated ephemeral credentials, fine-grained policy enforcement, secret injection, and secure delegation for AI agent-to-agent interactions.
agent-identity-management
A production-ready identity verification and security platform for AI agents and Model Context Protocol (MCP) servers, providing cryptographic identity, access control, and real-time threat detection.