DataSignals Events MCP: 12 US Filing Streams for AI Agents avatar

DataSignals Events MCP: 12 US Filing Streams for AI Agents

Pricing

Pay per usage

Go to Apify Store
DataSignals Events MCP: 12 US Filing Streams for AI Agents

DataSignals Events MCP: 12 US Filing Streams for AI Agents

One MCP endpoint over twelve US filing and career-site event streams: SEC insider clusters, Form 144, 13D/G, 13F, 8-K, Form D, FDA, trial readouts, NIH grants, federal contracts, Congress trades and hiring signals. Every record carries its score inputs and a proof reference. Two tools need no key.

Pricing

Pay per usage

Rating

0.0

(0)

Developer

DataSignals Lab

DataSignals Lab

Maintained by Community

Actor stats

0

Bookmarked

1

Total users

0

Monthly active users

17 hours ago

Last modified

Share

DataSignals Events MCP: twelve US filing streams for AI agents

One MCP endpoint over twelve streams of US filings and career-site events, all in the same record shape. Connect a client and ask; no local install.

Two tools work without a key

list_event_types tells you what exists, how many events each stream holds, which fields it carries and whether its score can be recomputed. feed_health tells you how fresh every source is right now. An agent can therefore check the data is real before anyone signs up for anything.

The other five tools need a key: search_events, company_events, get_event, usage and check_setup. Set DATASIGNALS_KEY in your MCP client config.

The twelve streams

Insider buying clusters, planned insider sales (Form 144), activist stakes (13D/G), institutional holdings (13F), material corporate events (8-K) and private capital raises (Form D) from SEC EDGAR. Drug approvals from openFDA. Trial readouts from ClinicalTrials.gov. Research grants from NIH RePORTER. Federal contract awards from USAspending.gov. Congressional trades from the US House Clerk. Hiring signals read from companies' own career sites.

What every record carries

scored_on, score_inputs with the formula version, and a proof reference looked up in a published hash chain rather than asserted. Where an input is missing from the source the record says inputs_complete: false instead of guessing a number.

Honest limits

Not real time. Sources refresh once a night; congressional trades weekly, institutional holdings quarterly. feed_health reports the real age per source.

First call after a quiet period. This server sleeps when nobody is using it, so a first connection can take a few seconds while it starts.

Where this fits

The only signal source in this niche with a daily verifiable track record, confluence across every data stream, and direct agent access over MCP.

Every score in every report lists the terms it was built from, so you can check the number instead of trusting it.

Plans, including a free tier, are at https://datasignalslab.com/events-api.html