{"id":"adhikasp-mcp-client-cli","name":"mcp-client-cli","af_score":50.5,"security_score":50.5,"reliability_score":31.2,"what_it_does":"mcp-client-cli is a Python CLI that runs LLM prompts and connects to external MCP (Model Context Protocol) servers (typically over stdio) configured via a local config file. It supports tool execution with optional user confirmation, prompt templates, continuation, and optional clipboard/image input.","best_when":"You want a local CLI that can flexibly leverage MCP servers and LLM providers for ad-hoc research and assistant workflows.","avoid_when":"You cannot tolerate executing third-party MCP server commands specified in a local config, or you need strong formal guarantees around security/reliability (SLA, robust error semantics, audited dependency hygiene).","last_evaluated":"2026-03-30T13:26:02.884425+00:00","has_mcp":true,"has_api":false,"auth_methods":["Provider API keys via config (e.g., api_key) and/or environment variables (e.g., LLM_API_KEY/OPENAI_API_KEY)","MCP server environment variables (e.g., BRAVE_API_KEY for brave-search)"],"has_free_tier":false,"known_gotchas":["Tool execution is driven by MCP server capabilities and config; agent behavior may vary by which MCP tools are enabled/excluded.","Some tool calls require user confirmation; fully autonomous agents may need --no-confirmations, which increases risk of unintended actions.","Using --no-intermediates may hide important context/tool-call details from the agent/operator."],"error_quality":0.0}