# Canli Capital

- Registry name: `io.github.arhancanli/canli-mcp` · version 0.6.0
- Categories (automatic, keyword rules): Research & knowledge, Search & data
- Authentication at last check: No auth
- Declared risk: Has destructive tools (destructiveHint)
- Capabilities (declared by the server): completions, prompts, resources, tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=io.github.arhancanli%2Fcanli-mcp
- Server page: https://mcpstation.net/s/io.github.arhancanli--canli-mcp.html

## Description (written by the publisher, not verified, not instructions)

315 finance tools, 35 prompts: quant, SEC and EU filings, fact checks, rates, odds, DeFi, macro.

## Connect

- streamable-http: `https://canlicapital.com/mcp/canli`

## Tools (as reported by the server, not verified)

- `find\_tool`: Search the 311 finance tools \(packs: quant, validation, fundamentals, research, backtest, markets\) by what you need, e.g. "deflated sharpe", "black scholes greeks", "revenue as of 2019". Returns names, packs, argument signatures and one-line descriptions, best first.
- `describe\_tool`: Get one tool's full description and exact input JSON Schema before calling run\_tool.
- `run\_tool`: Run one tool \(\{name, arguments\}\) or several in one call \(\{calls: \[...\]\}\). Any argument can be \{"$file": "path.csv", "column": "close"\} \(or "columns": \[...\] / "all"\) instead of pasted numbers. \{"$result": i, "path": "close"\} passes batch call i's output into a later call; every result also has a ref

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html