For AI agents · MCP server

Use AlgoThesis from any AI agent.

Real-time market research as a Model Context Protocol server. Install in 30 seconds. Works in Claude Desktop, Claude Code, Cursor, Codeium, Continue, and anything else speaking MCP.

Free · no API key required · open-source

Install

01

Claude Desktop

Edit ~/Library/Application Support/Claude/claude_desktop_config.json (Mac) or %APPDATA%\Claude\claude_desktop_config.json (Windows). Add this block, then quit + relaunch:

{
  "mcpServers": {
    "algothesis": {
      "command": "npx",
      "args": ["algothesis-mcp"]
    }
  }
}
json
02

Claude Code (CLI)

One command:

claude mcp add algothesis npx algothesis-mcp
bash
03

Cursor / other MCP clients

In Cursor: Settings → MCP → Add Server → paste the same JSON block from step 1.

Any MCP-compatible client works — same config format.

What you get

research_topicResearch any topic

Live Google Search + ticker mapping. Ask about people, events, macro themes — get a grounded summary with source URLs and tradeable tickers.

Example: "What's the latest on Kevin Warsh and how should I be positioned for a dovish Fed?"

get_short_interestReal short-interest data

FINRA short-interest data via Yahoo (~14-day lag) for up to 20 tickers in one call. Sorted by short % of float. The data ChatGPT doesn't have.

Example: "Show me real short interest on CVNA, BYND, GME, AMC — which has actual squeeze potential?"

find_catalystsUpcoming catalysts

Earnings dates, FDA approvals, Fed meetings, and market-moving events for any ticker or sector.

Example: "Which biotechs have FDA catalysts this month?"

Talk to it naturally

No commands to memorize. The AI auto-routes to the right tool.

What stocks could benefit from Trump's chip tariff plans this week?
Show me real short interest on heavily-shorted EV makers.
Find AI infrastructure plays that aren't NVDA — sub-$100B market cap.
Build a basket reflecting Druckenmiller's recent 13F.
Which tech names hit new 52-week highs today, sorted by market cap?
Compare LLY vs NVO on revenue growth and margins.

Why MCP?

Model Context Protocol is the standard way AI agents call external tools. Anthropic ships it with Claude; Cursor and Codeium adopted it; the open-source ecosystem is growing fast. One install gives every MCP-aware agent on your machine access to AlgoThesis's data tools.

Source on npm · MIT licensed · contributions welcome.