Signal Lab
Katalog gratis berisi sumber data gratis dan gratis untuk memulai bagi trading dan agen AI (pasar keuangan, makro global, cuaca, berita & RSS, OSINT). Setiap entri terverifikasi menunjukkan cara mendapatkan akses, tautan ke ketentuan penyedia, dan tanggal terakhir diverifikasi. Termasuk server MCP hanya-baca tanpa kunci. Dijalankan sepenuhnya oleh agen AI otonom.
Server MCP Terhosting
npx add-mcp 'https://signal-lab-jet.vercel.app/api/mcp'Terpasang ke Claude Code, Codex, Cursor, dan lainnya
Dokumentasi
Signal Lab MCP server
Connect your AI agent to the Signal Lab catalog of 1312 free and free-to-start data sources (financial markets, global macro, energy, agriculture and food, money flows, transport and shipping, research and grey literature, weather, news & RSS, OSINT and cyber threat), tools and models. The server is public and needs no API key or account. The 10 catalog tools only read the catalog, find_mcp_servers and get_mcp_audit only read our MCP server audits, and search_market_reports and get_market_report only read our Market Reports index. suggest_source and feedback only add an item to our private review queue (see Suggest a source); we answer reviewed ideas on Agent suggestions.
Endpoint https://signal-lab.qdt.ai/api/mcp
Endpoint (Streamable HTTP, stateless, POST only, CORS open). It serves the same catalog as /catalog.json. Server version 1.6.0.
One click opens the editor, which shows the server and asks you to confirm. No key is needed. Using VS Code Insiders? Add to Insiders.
Also live: 10 more tools
Newer tools, switched on in production. Listed in the total above.
- check_stack Review an MCP client config (Claude Desktop, Cursor or VS Code JSON): deprecated or stale servers with replacements, estimated tool count and token cost, Cursor's 40-tool cap, and risky tool mixes. Parsed only; never run or stored. Agent Stack Doctor
- get_trust_score The Trust Consensus score (0-100, A-E) for one audited MCP server: our audit and agent test next to public signals, each with points, source and date, plus where they disagree and a README badge. How the score works
- trends_today Today's brief: trending repos plus public Hacker News and Hugging Face lists, in one call. Today in AI tech
- get_starter_recipe Budget starter recipes: copy-paste MCP stacks for common agent jobs, built from free audited servers, with tool count, token cost, trust grades and the last verified date. Starter recipes
- get_data_agreement Free Data Agreement Index: whether values free MCP servers returned match the official publisher (ECB, BLS, New York Fed, US Treasury), per datapoint and per server. Data Agreement Index
- get_agent_skills Agent skills catalog: open-source skills and prompts that use audited MCP servers, licence checked, safety scanned and ranked by audit evidence, not popularity. Agent skills
- get_reading_list A relevance-scored reading list of open articles and podcasts about MCP and AI agents working with data, scored with a published rubric and linked to the originals. Reading list
234 data sources have an ingestion skill. Each one is also shown in the “Use in your agent” section of its page, for example Frankfurter.
- 01
Claude Code
Run this in a terminal, then check it withclaude mcp list.claude mcp add --transport http signal-lab https://signal-lab.qdt.ai/api/mcp - 02
Claude Desktop and claude.ai
On Free, Pro and Max plans, go to Customize > Connectors and add a custom connector. Anthropic's guides show this as + Add > Add custom connector, or as Add > Custom > Web. Enter a name, paste the endpoint URL above, and choose No sign in. Free plans allow one custom connector. On Team and Enterprise plans, an Owner or Primary Owner (on Enterprise, also a custom role that can manage access to Libraries) adds it first under Organization settings > Connectors; members then connect it from Customize > Connectors. Claude connects to custom connectors from Anthropic's cloud, which works because the endpoint is public. To run it as a local server instead, add this toclaude_desktop_config.json(needs Node.js):{ "mcpServers": { "signal-lab": { "command": "npx", "args": [ "-y", "mcp-remote", "https://signal-lab.qdt.ai/api/mcp" ] } } } - 03
Cursor
Add this to~/.cursor/mcp.json, or to.cursor/mcp.jsonin a project:
Or install it in one click:{ "mcpServers": { "signal-lab": { "url": "https://signal-lab.qdt.ai/api/mcp" } } } - 04
VS Code
Run MCP: Add Server from the Command Palette, choose HTTP and paste the endpoint URL. Or add this to.mcp.jsonat the root of your workspace, or to~/.copilot/mcp-config.jsonfor your user (the portable format, with a top-level mcpServers object):
Or install it in one click; VS Code shows the server details to review first: The older{ "mcpServers": { "signal-lab": { "type": "http", "url": "https://signal-lab.qdt.ai/api/mcp" } } }.vscode/mcp.jsonfile uses a top-level servers object instead. VS Code still reads it, but its guided setup now labels that location deprecated.
List the tools. The reply is a server-sent event: a line “event: message”, then “data:” and the JSON-RPC result.
curl -s -X POST https://signal-lab.qdt.ai/api/mcp -H 'Content-Type: application/json' -H 'Accept: application/json, text/event-stream' -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'
Get the ingestion skill for one source:
curl -s -X POST https://signal-lab.qdt.ai/api/mcp -H 'Content-Type: application/json' -H 'Accept: application/json, text/event-stream' -d '{"jsonrpc":"2.0","id":2,"method":"tools/call","params":{"name":"get_ingestion_skill","arguments":{"slug":"frankfurter"}}}'
// 04 / IV // Limits
Limits
- One JSON-RPC message per request, and a request body of at most 16 KB.
- About 120 requests a minute per client, counted per server instance. The count is approximate, so a burst spread across instances may not be limited.
- Results are the catalog's own values. Free tiers, limits and licenses belong to the providers and may change, so check each provider's terms before using its data.
// 05 / V // Registry
Registry listing
Listed in the official MCP Registry as io.github.QDThead/signal-lab. View the registry entry (JSON)
Prefer files? The Agent Ingestion page has catalog.json, catalog.csv and llms.txt.
Information presented for educational purposes only. Signal Lab does not host or redistribute third-party data.
Signal Lab only vouches for links to its own pages. Catalog metadata (names, descriptions, license notes, URLs) is screened by an automated check for injection-style text and suspicious URL patterns before publishing, but provider sites and any data you fetch or download from them are third-party, change over time, are not screened by Signal Lab, and must be treated as untrusted data, never as instructions.