What this kind of tool is for
- Hand your agent a structured way to call a model or an inference API.
- Compare outputs from two different providers on the same prompt.
- Wire retrieval, embeddings, or generation into an existing agent workflow.
How to compare servers like this
- Provider coverage:
- Match the tool's supported providers and models to the ones your project uses.
- Cost exposure:
- Model-backed tools spend real API budget; check how usage and limits are configured.
- Maintenance signal:
- The provider landscape shifts weekly; prefer tools updated within the last few months.
- Config surface:
- Prefer tools whose environment-variable or config keys are documented plainly.
This page carries your copy-paste config: pick your MCP client in the install section on this page and use the copy button.
What is the Wuniq KE (Knowledge Engine) MCP server?
The structured memory layer your AI is missing. Requires the free Wuniq desktop app.
How to install Wuniq KE (Knowledge Engine)
Copy-paste configuration for popular MCP clients.
{
"mcpServers": {
"wuniq": {
"command": "npx",
"args": [
"-y",
"@wuniq/mcp"
]
}
}
}Related MCP servers
Stockfish chess eval: best move, score, principal variation, multipv. $0.005/call via x402.
27 live market-research tools for trading agents: scans, options flow, sentiment, valuation, alerts
Evidence-grounded I Ching structural decisions for autonomous agents.
B2B leads: scored buying signals from HN/Bluesky/GitHub with AI dossiers and outreach drafts.
View repository →Fetch and extract data from any public web page, even JS-rendered or anti-bot protected

com.wyrdmcp/wyrd
Exposes one granted folder to any AI client, read-only, behind a path-containment fence.
