Skip to content
MCP server

Canli Quant

235 finance calculation tools behind three search-and-run tools, with no network calls

Runs locallyStatus and history
Install
Pricing
Open source
Platforms
CLI
Runs
Locally
Version
0.4.0
Listing updated
3 days ago

About Canli Quant

Canli Quant is an open-source MCP server for finance and payments. It runs locally on your machine and is started by your AI client.

Listing hundreds of tools in a model's context is expensive, so this server exposes three by default: find_tool, describe_tool and run_tool. The model searches the catalogue in plain words, reads one tool's schema, then runs it. The README measures the saving at 680 tokens against 83,944 for listing 238 tools directly, and reports the right tool ranked first 94% of the time on 110 test requests.

Behind those three sit 236 quant tools covering performance and risk, options and exotics, fixed income, portfolio construction, econometrics, technical indicators, execution and sizing, crypto and FX, valuation, strategy backtests and data checks, plus a library of 399 strategy sleeves. Tools compute on the data you send; the README says nothing leaves your machine and that results are checked in tests against QuantLib, statsmodels, arch, TA-Lib and others (465 reference cases).

NaN and Infinity results are refused with an error naming the fields, rather than returned as silent nulls. Set CANLI_TOOLSETS to list some toolsets directly instead of through the search tools.

Install

Run in a terminal

claude mcp add canli-quant-mcp -- npx -y canli-quant-mcp

Add to claude_desktop_config.json

{
  "mcpServers": {
    "canli-quant-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "canli-quant-mcp"
      ]
    }
  }
}
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "canli-quant-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "canli-quant-mcp"
      ]
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "canli-quant-mcp": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "canli-quant-mcp"
      ]
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "canli-quant-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "canli-quant-mcp"
      ]
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "canli-quant-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "canli-quant-mcp"
      ]
    }
  }
}

Configuration

  • CANLI_TOOLSETSToolsets to list directly (comma-separated, or all). Default: three discovery tools that reach every tool.

Tools this server provides (3)

Taken from the project documentation; the running server may differ.

find_tool
Search the tool catalogue in plain words.
describe_tool
One tool's description and exact input schema.
run_tool
Run any tool by name, optionally with a calculation receipt.

What it does

Three-tool discovery
find_tool, describe_tool and run_tool reach the whole catalogue with a small context footprint.
Strategy sleeve library
Includes 399 strategy sleeves that can be run in tournaments over your price data.
Checked calculations
Tests compare results with QuantLib, statsmodels, arch, TA-Lib, scipy and other references.
Local only
Runs over stdio with no key, no account and no network calls.
Calculation receipts
run_tool can add a receipt, and a digits setting trims output tokens.
Toolset selection
CANLI_TOOLSETS lists chosen toolsets directly or all of them.

Good for

  • Check whether a strategy's edge survives many variant trials
  • Price barrier or vanilla options and compare them
  • Run ADF, KPSS and variance-ratio tests on a spread
  • Screen an option chain for arbitrage before fitting a surface
  • Compare strategy sleeves on ETF prices

Pricing

Open source

Free, MIT-licensed

Prices change. Check canlicapital.com before you buy.

Canli Quant FAQ

Does my data leave my machine?

The README says every tool computes on the data you send, with no network calls, and tests enforce this.

How many tools are there?

236 quant tools are reported, with 235 behind the three discovery tools by default, plus 399 strategy sleeves.

How accurate is tool search?

On 110 test requests, the right tool came first 94% of the time and in the top three 99%.

How do I install it?

Run npx -y canli-quant-mcp or add it with claude mcp add canli-quant.

Is Canli Quant free?

Yes. Canli Quant is open source, so you can use and self-host it for free.

How do I add Canli Quant to Claude Code?

Run this command in your terminal: claude mcp add canli-quant-mcp -- npx -y canli-quant-mcp

What are the best alternatives to Canli Quant?

The closest alternatives to Canli Quant are Agent-Native Analytics, Google Ads + Meta Ads + SEO/GEO MCP, Solana MCP by Vybe, Tapetide - Indian Stock Market MCP and World Monitor.

Alternatives to Canli Quant

  1. Open-source analytics app where an AI agent builds charts and dashboards from your data

    • Remote
    • Open source
    • 7.7K GitHub stars
    • Analytics and data
  2. Hosted MCP connector for managing Google Ads, Meta Ads, GA4 and Search Console from chat

    • 8 tools
    • Remote
    • Freemium
    • 8.1K GitHub stars
    • Marketing and SEO
  3. Remote MCP server exposing the Vybe Solana API to AI clients and code editors

    • 44 tools
    • Remote
    • 2.8K GitHub stars
    • Finance and payments
  4. Indian NSE and BSE stock market data for AI assistants through 48 MCP tools

    • 17 tools
    • Remote
    • Freemium
    • 150 GitHub stars
    • Finance and payments
  5. World Monitor

    MCP server

    Live geopolitical intelligence dashboard with an API and MCP server for agents

    • Remote
    • Freemium
    • Analytics and data
  6. Budget Tracker

    MCP server

    Local MCP expense ledger that logs receipts and mileage, splits VAT and prepares rebilling

    • 14 tools
    • Remote
    • Freemium
    • 2 GitHub stars
    • Finance and payments