mcp.deeprecall.io

Very long descriptions are sometimes used to bury instructions to the AI. Skim it before allowing.

This server isn't on gate's handpicked list. That's not necessarily bad, but there's no third-party signal about it — review its tools carefully.

The tool allows passing an api_key directly as a string argument (in addition to header-based auth). If an agent is instructed to reuse or infer credentials, this could encourage passing sensitive API keys through conversational/tool-call context that may be logged, rather than exclusively via secure header injection. Not malicious by itself, but worth noting as a minor credential-handling risk; recommend header-only auth to reduce exposure of keys in transcripts/logs.