Side-by-side comparison of two Model Context Protocol servers — install paths, tools, quality signals, and directory engagement so you can pick the right one for Claude, Cursor, and other MCP clients.
The graded MCP registry: live-probes every remote server in the official registry (initialize, tools/list, schema quality, latency, provenance) and publishes evidence-backed grades — searchable by agents via its own MCP endpoint at mcpqueen.com.
MCP server for DeepSeek AI with chat, reasoning, multi-turn sessions, function calling, thinking mode, and cost tracking.
Quality signal
41/100 (Fair)
49/100 (Fair)
Install path
npx · low
npx · high
Engagement
0 0 0 0
2 0 0 17
Tools
Not listed yet
Supports DeepSeek V4 flash and pro models with 1M-token contextMulti-turn session management preserving conversation stateOpenAI-compatible function calling with up to 128 toolsSchema-validated JSON output with bounded repair retriesCost tracking with cache-aware breakdownRemote HTTP and local stdio transport options