Pytheum MCP
OfficialClick on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Pytheum MCP Which markets does the Trump indictment news move?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
pytheum-mcp
MCP server for the pytheum prediction-market context API.
On PyPI as
pytheum-mcp. Source: github.com/pytheum/pytheum-mcp. Docs: github.com/pytheum/pytheum-doc.
Wraps the four public endpoints on api.pytheum.com as MCP tools so AI agents (Claude Desktop, Cursor, anything that speaks MCP over stdio) can ask "which markets does this news article move?" without writing their own retrieval layer.
Install
Two install paths — both run the same Python code. Pick whichever your MCP client makes easier:
Via npm (recommended for Claude Desktop)
# no install needed — npx runs it
npx -y @pytheum/mcpClaude Desktop ships a Node.js runtime but not Python, so npx is the path of least resistance there. The npm package is a small shim that runs uvx pytheum-mcp under the hood; uv is still required (see the npm README for the install one-liner).
Via PyPI (Python-native)
uvx pytheum-mcp # one-shot
uv tool install pytheum-mcp # permanentRequires Python 3.11+ and uv.
Configure
Claude Desktop
Edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"pytheum": {
"command": "npx",
"args": ["-y", "@pytheum/mcp"],
"env": {
"PYTHEUM_API_BASE": "https://api.pytheum.com"
}
}
}
}Restart Claude Desktop. The hammer icon in the composer should list pytheum's tools.
Cursor / Windsurf / others
Same config under ~/.cursor/mcp.json (or the client's equivalent). If you already have uv on PATH, you can swap npx -y @pytheum/mcp for uvx pytheum-mcp to skip the Node shim entirely:
{
"mcpServers": {
"pytheum": {
"command": "uvx",
"args": ["pytheum-mcp"],
"env": {
"PYTHEUM_API_BASE": "https://api.pytheum.com"
}
}
}
}Tools
Tool | Endpoint | Description |
|
| Find markets matching free-text |
|
| Events paired with a market |
|
| Events paired with any market in a bundle |
|
| Markets related to a firehose event |
Configuration
Env var | Default | Purpose |
|
| Override to hit staging or a local stub |
Reference
Endpoint schemas, response shapes, errors, and rate limits live in pytheum/pytheum-doc. The machine-readable OpenAPI spec is at openapi.yaml.
License
MIT
Available Tools
4 toolst_bundle_contextC
Events paired with any market inside a bundle, deduplicated by event_id.
Inputs: bundle_ref (required), limit.
t_find_marketsC
Find prediction markets matching a free-form text query (article body / news headline / question).
Inputs: query (required), limit, group_by.
t_market_contextC
Events (news/social/macro) paired with a specific market. market_ref accepts venue-prefixed id, slug, or URL.
Inputs: market_ref (required), limit.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
Each tool targets a distinct purpose: bundle context, event-related markets, free-text search, and market context. No overlap in functionality.
All tools use a consistent 't_' prefix and snake_case, but not all follow a strict verb_noun pattern (e.g., 'bundle_context' is noun-like). Still highly uniform.
Four tools is an ideal size for this domain—each tool serves a clear, non-redundant purpose without being too few or too many.
The tool set covers the core operations for retrieving prediction market data: search, context, and event linking. No obvious gaps for a read-oriented server.
Related MCP Connectors
Pay-per-use tool marketplace for AI agents. Search, price-check, and call APIs via MCP.
Connect AI agents to primary sources - markets, macro, news, earth, network, entities and research.
16 Bitcoin, business, data, text, and developer tools for AI agents over one MCP endpoint.
Real SEC, 13F, insider, congress & macro data your AI agent can cite. Hosted MCP, 24 tools.