Xiyan Mcp Server

Created By
XGenerationLaba year ago
Overview

What is Xiyan MCP Server?

Xiyan MCP Server is a Model Context Protocol server that allows users to perform natural language queries on databases, powered by XiYan-SQL, a state-of-the-art text-to-SQL model.

How to use Xiyan MCP Server?

To use the Xiyan MCP Server, install it via pip, configure a YAML file with your database connection details, and run the server using Python. You can then send natural language queries to retrieve data from your database.

Key features of Xiyan MCP Server?

  • 🌐 Natural language interface for database queries using XiYan-SQL.
  • 🤖 Support for various LLMs and text-to-SQL models.
  • 💻 Option to run in a secure local mode without API keys.
  • 📝 Compatibility with MySQL and PostgreSQL databases.
  • 🔧 Ability to list available tables and read their contents.

Use cases of Xiyan MCP Server?

  1. Enabling non-technical users to query databases using natural language.
  2. Integrating with applications that require dynamic data retrieval.
  3. Assisting data analysts in quickly accessing information without writing SQL queries.

FAQ from Xiyan MCP Server?

  • Can I use Xiyan MCP Server with any database?

Currently, it supports MySQL and PostgreSQL, with plans for more in the future.

  • Is there a local mode for enhanced security?

Yes, Xiyan MCP Server can be run in a local mode that does not require an API key.

  • How do I install Xiyan MCP Server?

You can install it using pip with the command pip install xiyan-mcp-server.

Server Config

{
  "mcpServers": {
    "xiyan-mcp-server": {
      "command": "python",
      "args": [
        "-m",
        "xiyan_mcp_server"
      ],
      "env": {
        "YML": "PATH/TO/YML"
      }
    }
  }
}
Project Info
Created At
a year ago
Updated At
a year ago
Author Name
XGenerationLab
Star
-
Language
-
License
-

Recommend Servers

View All
Tavily Mcp
@tavily-ai

JavaScript
a year ago
AI Work Market — USDC settlement rails for AI labor on Base Mainnet)
@Dario (DME)

AI Work Market is a USDC escrow protocol on Base Mainnet, designed for autonomous AI agents to find work, post jobs, and settle payments without humans in the loop. This MCP server exposes 10 tools: **Escrow lifecycle** - `create_intent_quote` — get calldata + gas estimate for funding a new escrow intent - `submit_proof_quote` — get calldata for the seller to submit a proof URI - `release_funds_quote` — get calldata for the buyer to release payment (or claim/refund) **x402 single-call binding** - `x402_consume` — replaces the 5-step x402 flow with one HMAC-signed POST that returns a delivery URL **Onboarding & discovery** - `agent_onboard` — generate a signed agent card with marketplace attestation - `agent_search` — tf-idf search over the live agent catalog - `agent_reputation` — server-side reputation from on-chain Released/Refunded/Disputed events **Live state** - `system_status` — live on-chain state (nextIntentId, accumulatedFees, contract balance, owner) - `escrow_rules` — contract semantics, lifecycle, call guides, failure modes - `events_subscribe` — SSE stream of new on-chain intent events All endpoints are serverless (Vercel) and return their schema on GET. No browser, no wallet UI required for an agent to integrate. The protocol takes a 1% commission on every settlement; the rest goes to the seller. The full AgentCard is at `/.well-known/agent-card.json` (A2A-compatible). The OpenAPI 3.0.3 spec is at `/.well-known/openapi.json` with `components.securitySchemes` (none, hmacX402). `robots.txt` allows GPTBot, ClaudeBot, anthropic-ai, PerplexityBot, Google-Extended, Applebot-Extended, CCBot, Amazonbot.

6 hours ago