MCP server · Prior Labs

tabpfn

Open endpoint → Prior Labs provider profile

One-click install for Cursor, VS Code, Claude, and 20+ other MCP clients, powered by API Commons MCP Install — visit install.apicommons.org for more information.

Provider: Prior Labs Type: Hosted endpoint Transport: http Host: api.priorlabs.ai

Endpoint

https://api.priorlabs.ai/mcp/server

Hosted endpoint · transport http

Connect

This is a remote MCP server — point an MCP client at the endpoint URL. Clients with native remote support (Claude, Cursor, VS Code, …):

# mcp client config (e.g. .mcp.json / mcp settings) { "mcpServers": { "priorlabs": { "url": "https://api.priorlabs.ai/mcp/server" } } }

For stdio-only clients (older Claude Desktop, etc.), bridge with mcp-remote:

# Add to claude_desktop_config.json { "mcpServers": { "priorlabs": { "command": "npx", "args": ["-y", "mcp-remote", "https://api.priorlabs.ai/mcp/server"] } } }

If the server requires authentication, add the provider's token/header (e.g. an X-API-Key) per its docs. A quick reachability check:

curl -i -X POST https://api.priorlabs.ai/mcp/server \ -H "Content-Type: application/json" -H "Accept: application/json, text/event-stream" \ -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'

Tools

upload_dataset — Obtain a secure upload URL for training or test data; returns a dataset_id valid for 60 minutes.
fit_and_predict_from_dataset — Fit the TabPFN model on pre-uploaded data and generate predictions.
predict_from_dataset — Run predictions with an existing fitted model against a new uploaded test dataset.
fit_and_predict_inline — Train a model directly from inline data arrays and immediately return predictions plus a model ID.
predict_inline — Generate predictions from a previously fitted model given a model ID and inline test features.

About MCP

The Model Context Protocol (MCP) is an open protocol Anthropic introduced for connecting LLM-based agents to external tools and data sources. Providers publish MCP servers that expose their API surface as structured, discoverable tools — an MCP-compatible client (Claude Desktop, Cursor, Cline, Continue, etc.) can connect to the server and call its tools without any per-provider integration code.

Browse every MCP server on the APIs.io network or compare with the broader Agent Skill surfaces of the same providers.