The Neural Ledger Intelligence
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
Package | Purpose |
| Typed TypeScript client for the TNL |
| Read-only MCP server over stdio or Streamable HTTP |
| Hosted OAuth, tenant policy, quota, and audit MCP gateway |
| Developer credentials, static sample API, and explorer |
| Webhook contracts, signed delivery, and verification helpers |
| Evidence-first skills, orchestration, MCP App, and web UI |
| Shared Cursor and OpenAI workflow contracts and rendering |
| Shared n8n, Pipedream, and Zapier action/trigger contracts |
|
|
| Python SDK and optional point-in-time quant research toolkit |
Related MCP server: Publisher Content MCP Server
Quick Start
Set a member API key in the environment:
export TNL_API_KEY="..."Run the MCP server over stdio:
npx -y @theneuralledger/mcpOr run its localhost Streamable HTTP endpoint:
docker compose up --build
curl http://127.0.0.1:7317/healthzUse 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
127.0.0.1by 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 validatePython development uses the project under python/tnl_intelligence.
Documentation
License
MIT
Available Tools
8 toolstnl_asset_intelligenceAsset intelligenceARead-onlyIdempotent
Return event intelligence linked to an asset ticker. This is not a live trading-price tool.
Inputs: ticker (required), limit, publishedSince. Returns: data
tnl_deep_researchDeep research with Ledger AIBRead-onlyIdempotent
Run a question through TNL Ledger AI research orchestration and return its answer with citations and context.
Inputs: question (required). Returns: data
tnl_entity_intelligenceEntity intelligenceARead-onlyIdempotent
Return recent stories connected to a named TNL entity or entity id.
Inputs: entity (required), limit, publishedSince. Returns: data
tnl_explain_eventExplain an eventARead-onlyIdempotent
Ask Ledger AI to explain a TNL event using its evidence, contradictions, affected assets, and likely impact paths.
Inputs: story (required), focus. Returns: data
tnl_impact_pathImpact-path intelligenceBRead-onlyIdempotent
Return stories associated with a causal or market impact path.
Inputs: impactPath (required), limit, publishedSince. Returns: data
tnl_latest_newsLatest TNL intelligenceARead-onlyIdempotent
Return recent evidence-backed news intelligence, optionally filtered by category or country.
Inputs: limit, country, category, publishedSince. Returns: data
tnl_search_newsSearch TNL intelligenceCRead-onlyIdempotent
Search TNL stories and return structured evidence, impacted assets, entities, and impact paths.
Inputs: query (required), limit, country, category, +1 more. Returns: data
tnl_service_statusTNL service statusARead-onlyIdempotent
Check API access, plan usage, market-context freshness, and current rate-limit headers.
Inputs: no named parameters. Returns: data
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 8 tools
Each tool has a clearly distinct purpose: news retrieval, search, asset/entity intelligence, impact paths, explanation, deep research, and status. There is no overlap or ambiguity.
All tools follow a consistent tnl_verb_noun or tnl_noun_phrase pattern in snake_case, making the naming predictable and easy to navigate.
With 8 tools, the server covers a broad range of intelligence functions without being bloated or too sparse. Each tool earns its place.
The tool set covers core workflows: retrieving news, searching, querying asset/entity intelligence, impact paths, explanations, deep research, and API status. No obvious gaps for the stated domain.
Maintenance
Related MCP Connectors
Financial news for AI agents: search, stories, insider, earnings reads, macro, scored 1-10.
Real-time financial news for AI agents: search by ticker and source, with sentiment and entities.
News search for AI agents: recent news on any topic from outlets worldwide, by country and language.
Licensed, cited financial data for AI agents: news, filings, transcripts, research and tearsheets.
Related MCP Servers
- AlicenseAqualityBmaintenanceReal-time financial news for AI agents and trading bots — AI-enriched stories with per-ticker analysis, a 1–10 relevance score, SEC Form-4 insider transactions, plus trending and "actionable-now" feeds. Free tier, OAuth, no API key to paste.2113MIT
- FlicenseNot gradedqualityDmaintenanceExposes publisher journalism to LLMs and agent frameworks via search, retrieval, source grounding, and consistent citation, enabling accurate content retrieval with attribution and policy enforcement.-
- AlicenseAqualityCmaintenanceEnables AI agents and their users to retrieve scored news sentiment, narratives, historical readings, and cited sources for Bitcoin, gold, and oil, with tamper-evident, time-stamped data for trading decisions.5MIT

ultralayer-v0official
AlicenseNot gradedqualityBmaintenanceRealtime financial context for AI agents: what changed, who is affected, and what to watch next. One suite covering news, events, guidance, filing changes, sentiment, stakeholders, and alerts. Information-efficient responses with evidence for every result. First-class point-in-time safety for backtests. Pairs well with web search and a market-data API. All data is our own.3MIT