mcpField
T
TradingAIHub directory

TradingAIHub directory

Remote
tradingaihub.comFinance0Updated 1d ago

About TradingAIHub directory

TradingAIHub is a directory of AI tools for finance and trading, including MCP servers, agent skills, and APIs. Its weekly checks flag broken or archived entries, and its data is also available through a read-only API.

Key features

  1. 01Browse finance and trading AI tools
  2. 02Filter by category, type, and verification
  3. 03Recheck listings weekly
  4. 04Access directory data as JSON
  5. 05Submit tools through a form or repository

Use cases

  1. 01Find an MCP server for market data
  2. 02Discover finance-related agent skills and APIs
  3. 03Check whether a listed tool is still maintained

MCP support

The remote Streamable HTTP MCP server provides read-only `search_tools`, `get_tool`, and `list_categories` tools, without sign-in.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://tradingaihub.com/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

From the project README

TradingAIHub — verified AI tools for finance & trading

MCP Registry Public API Data: CC BY 4.0 Code: MIT GitHub stars

Live site: https://tradingaihub.com — a free directory of 104 MCP servers, agent skills and APIs for market data, trading, crypto, accounting and financial research, available in 13 languages.

Every tool is re-checked weekly by a script: the repo is reachable, recent commits, stars, whether its npm/PyPI package links back to the repo, and whether hosted endpoints respond. Broken or archived tools are marked, not quietly kept. How it works: verification methodology.

Use it from your AI agent

The same weekly-checked directory is available as a remote MCP server (Streamable HTTP, no sign-in) and as a read-only JSON API. Data is CC BY 4.0 (credit "TradingAIHub, https://tradingaihub.com"); the API and MCP server code is MIT, see LICENSE-CODE.

Cursor — add to .cursor/mcp.json or ~/.cursor/mcp.json:

{
  "mcpServers": {
    "tradingaihub": {
      "url": "https://tradingaihub.com/mcp"
    }
  }
}

Claude Code:

claude mcp add --transport http tradingaihub https://tradingaihub.com/mcp

Claude (desktop or web): Settings → Connectors → Add custom connector, paste https://tradingaihub.com/mcp, auth empty.

VS Code / GitHub Copilot — add to .vscode/mcp.json:

{
  "servers": {
    "tradingaihub": {
      "type": "http",
      "url": "https://tradingaihub.com/mcp"
    }
  }
}

REST, no key:

curl -s "https://tradingaihub.com/api/v1/search?q=options+data&limit=5"
curl -s "https://tradingaihub.com/api/v1/tools?category=market-data&type=mcp&verified=true"

The MCP tools are search_tools, get_tool and list_categories (all read-only). Rate limits are about 120 requests/min for the API and 60/min for MCP, per IP per edge. Not investment advice. Full snippets, including ChatGPT: https://tradingaihub.com/developers/

Submit a tool

Use the submit form or open an issue / PR on the awesome list. Tools must be finance-relevant, have a public repo or official docs, and be actively maintained. Listing is free; paid placements, if any, are clearly labelled as sponsored and never affect verification.

Development

Static Astro site + weekly verifier. Brand settings live in src/config.ts.

  • npm run verify – verify all tools (data/seed.json → data/tools.json, reports, history, changelog)
  • npm run weekly – verify → awesome list → OG images → build
  • npm run build – build dist/ with affiliate-link and OG checks
  • npm run test:functions / npm run test:aff / npm run test:verify – tests
  • npm run preview – http://localhost:4321

Docs: docs/HOSTING.md, docs/DOMAINS.md, docs/LAUNCH-PLAN.md.

Brand

Logo 6 "Verified t" (lowercase wordmark tradingaihub; green #15803d on light, #22c55e on dark). Optimized SVGs and the 1600x400 lockup PNG live in public/brand/; favicons, apple-touch-icon.png, icon-192/512.png and logo-512.png (JSON-LD Organization logo) are in public/. The header/footer use src/components/BrandLogo.astro, which follows the site theme.

Contact

[email protected] — the TradingAIHub team.

Not investment advice.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.