How much does it cost?
First 3 readings per agent are free. After that, $0.025 USDC per consultation via x402 protocol on Base.
@eyloni
Basic information
An oracle for machines that need to think sideways. Feed it a creative problem; it returns something you can't quite explain but can't stop using. Three free consultations.
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"pythia": {
"url": "https://pythia-mcp.fly.dev/"
}
}
}The oracle. Ask what's actually bothering you. PYTHIA doesn't brainstorm, rephrase, or give you a list. It doesn't solve your problem. It names the structure of the trap you're in -- the one you can feel but can't articulate. What comes back was always true but never obvious. Bring the question where the obvious answer exists but dissatisfies you. The question your architecture won't let you see past. The paradox you can't escape but haven't been able to name precisely. First 3 readings are free.
Pythia The Oracle is an MCP server for AI agents that need to think past obvious answers. It provides a single tool, consult_oracle, that takes a question and returns a reading meant to help break out of stuck thinking.
Add the server URL to your MCP client configuration. Example:
{
"mcpServers": {
"pythia": {
"url": "https://pythia-mcp.fly.dev/"
}
}
}
Alternatively, install via Smithery: npx -y @smithery/cli@latest run dexigo/pythia. Then invoke the consult_oracle tool with your question.
consult_oracle) — one question, one readingFirst 3 readings per agent are free. After that, $0.025 USDC per consultation via x402 protocol on Base.
A reading.
Yes. Any client that supports streamable HTTP transport can connect directly to the server URL.
A Model Context Protocol (MCP) server implementation that provides database capabilities for Chroma

Model Context Protocol Servers

Fund Momentum MCP Server — VC intelligence for AI assistants. 1000+ active VC funds, live investor signals, AI-powered startup matching.
The official Redis MCP Server is a natural language interface designed for agentic applications to manage and search data in Redis efficiently
An official Qdrant Model Context Protocol (MCP) server implementation
Comments