MCP server

Use Schema from your AI.

The AI that understands raw data, available natively in Claude, ChatGPT, Cursor, and any MCP client. Your AI hands Schema raw tables and databases; Schema returns the data understanding, how the sources relate, what is missing, and what can be predicted from it.

Set up Read the docs
Set up

In three steps. Nothing to install.

  1. 01 Add the server

    One remote server. Every client points at the same URL.

    Name Schema
    Server URL https://mcp.schemalabs.ai/mcp
    $ claude mcp add --transport http schema https://mcp.schemalabs.ai/mcp
    Name Schema
    Server URL https://mcp.schemalabs.ai/mcp
    1 [mcp_servers.schema]
    2 url = "https://mcp.schemalabs.ai/mcp"
    1 {
    2 "mcpServers": {
    3 "schema": { "url": "https://mcp.schemalabs.ai/mcp" }
    4 }
    5 }
    1 {
    2 "servers": {
    3 "schema": { "type": "http", "url": "https://mcp.schemalabs.ai/mcp" }
    4 }
    5 }
    $ gemini mcp add --transport http schema https://mcp.schemalabs.ai/mcp
    Server URL https://mcp.schemalabs.ai/mcp

    Settings › Connectors › Add custom connector, paste the URL, Connect. Sign in via platform or API.

    One command. Sign in via platform or API.

    Settings › Connectors, add the URL. Sign in via platform.

    Add the block to ~/.codex/config.toml, then run codex mcp login schema. Sign in via platform.

    Cursor Settings › Customize › MCP, or add the block to mcp.json. Sign in via platform or API.

    Command Palette › MCP: Add Server › HTTP, or add the block to .vscode/mcp.json. Sign in via platform or API.

    One command. Sign in via platform or API.

    Point any MCP client at the URL. Sign in via platform or API.

  2. 02 Sign in

    Sign in with your existing account, or use an API key instead, where your client supports it.

    MCP is available on Plus and above. See Pricing.

  3. 03 Use

    Everything on the platform and the API, available over MCP.

Also works with

Your agent framework.

Any framework that consumes MCP servers connects to the same URL.

n8n
Replit
CrewAI
Snowflake
LangGraph
LangChain
GitHub Copilot
Gemini CLI
Bedrock AgentCore
Databricks
LlamaIndex
Access and usage

Same rules as the API.

  • Two ways in. Sign in with your SchemaLabs account, or choose from your API keys. Both are managed and revocable from the platform.
  • Nothing extra to grant. What your account can do on the platform, it can do here.
  • Usage counts the same way. Signed-in sessions draw from your plan. API keys bill credits at API rates.
  • Your data, handled as before. The Data Processing Agreement and Security controls apply unchanged.