The Neural Ledger Intelligence

Read-only global event and evidence intelligence with entities, assets, and impact paths.

OtherTypeScriptv0.1.0

TNL Intelligence

Open-source developer tools for The Neural Ledger intelligence API.

TNL Intelligence gives AI agents and quantitative research systems structured, source-linked global event intelligence. It is an evidence and research layer, not a broker, an order router, or a source of trading-grade prices.

Packages

PackagePurpose
@theneuralledger/sdkTyped TypeScript client for the TNL /v1 API
@theneuralledger/mcpRead-only MCP server over stdio or Streamable HTTP
@theneuralledger/gatewayHosted OAuth, tenant policy, quota, and audit MCP gateway
@theneuralledger/onboardingDeveloper credentials, static sample API, and explorer
@theneuralledger/eventsWebhook contracts, signed delivery, and verification helpers
@theneuralledger/researchEvidence-first skills, orchestration, MCP App, and web UI
@theneuralledger/adaptersShared Cursor and OpenAI workflow contracts and rendering
@theneuralledger/connectorsShared n8n, Pipedream, and Zapier action/trigger contracts
@theneuralledger/clitnl CLI, watch command, local cache, and foreground daemon
tnl-intelligencePython SDK and optional point-in-time quant research toolkit

Quick Start

Set a member API key in the environment:

export TNL_API_KEY="..."

Run the MCP server over stdio:

npx -y @theneuralledger/mcp

Or run its localhost Streamable HTTP endpoint:

docker compose up --build
curl http://127.0.0.1:7317/healthz

Use the CLI:

npx -y @theneuralledger/cli latest
npx -y @theneuralledger/cli search "Federal Reserve"

Use the TypeScript SDK:

import { TnlClient } from '@theneuralledger/sdk';

const client = new TnlClient({ apiKey: process.env.TNL_API_KEY! });
const page = await client.listNews({ sort: 'pipeline', pageSize: 20 });

Use the Python SDK:

from tnl_intelligence import TnlClient

with TnlClient(api_key="...") as client:
    page = client.list_news(sort="pipeline", page_size=20)

Security

  • API keys are never accepted as visible command-line arguments.
  • MCP tools are read-only and do not place trades.
  • Streamable HTTP binds to 127.0.0.1 by default.
  • Local daemon events never contain the API key.
  • Hosted deployments use the separate gateway, TLS ingress, OAuth validation, tenant policy, short-lived upstream capabilities, and distributed quotas.

See SECURITY.md and the build plan. Research deployment boundaries and staged rollout are documented in Research operations.

Development

npm install
npm run openapi:sync
npm run validate

Python development uses the project under python/tnl_intelligence.

Documentation

License

MIT

Installation

Source-derived launch command. Check the maintainer’s required arguments and credentials before running:

bash
npx -y @theneuralledger/mcp

Set up in your AI client

Merge this template into ~/Library/Application Support/Claude/claude_desktop_config.json. Keep existing servers. Add any arguments, credentials, and permissions required by the maintainer; this template has not been install-tested.

json
{
  "mcpServers": {
    "com-theneuralledger-intelligence": {
      "command": "npx",
      "args": [
        "-y",
        "@theneuralledger/mcp"
      ]
    }
  }
}

Restart Claude Desktop completely for changes to take effect. Confirm the server appears connected in the client’s tool list, then try a read-only example from its documentation.

Claude Desktop setup reference

Package

@theneuralledger/mcpnpm

Compatible MCP Clients

The Neural Ledger Intelligence works with any MCP-compatible client. Copy the config snippet from the Configuration section above and add it to the file shown for your client, then restart the application.

  • Claude Desktop~/Library/Application Support/Claude/claude_desktop_config.jsonRestart Claude Desktop completely for changes to take effect.
  • Cursor~/.cursor/mcp.jsonRestart Cursor for changes to take effect.
  • VS Code.vscode/mcp.jsonReload VS Code window for changes to take effect.
  • Windsurf~/.codeium/windsurf/mcp_config.jsonRestart Windsurf for changes to take effect.
  • Claude Code.mcp.jsonSave at the project root, then start Claude Code in that project and review the MCP server approval prompt. Keep real credentials out of shared files.

Learn More