Agents
What is MCP?
MCP, the Model Context Protocol, is a standard way for models and editors to call tools and read resources from a server.
Updated
How it works
- A server advertises tools and resources.
- The model or IDE calls a tool.
- The tool reads or writes your system and returns a result.
What it is not
It is not an agent framework, and it is not a database API that was never exposed as MCP.
MCP: this, and the thing it is confused with
| This | Not this | |
|---|---|---|
| Is | A protocol for tools | The agent loop itself |
| Carries | Tool calls and resources | Your whole database |
| Needs underneath | Something the tool can actually query | Nothing |
Where Pixeltable fits
Pixeltable is an MCP client: pxt.mcp_udfs(url) turns a server's tools into functions an LLM column can call, and each call and its result land in a row. The library has no API that turns your own tables and queries into an MCP server. Its own MCP servers are for coding agents: the developer server inspects schemas, queries tables and runs a REPL against a local or Cloud catalog, and the hosted Cloud MCP at /mcp/cloud reads and operates a signed-in Cloud organization after AuthKit consent; ?read_only=true leaves only the read tools.
Questions
How does MCP work?
What is MCP often confused with?
Next step
Install the Pixeltable skill, or sign up for Cloud and run the same file on a hosted database.