Skip to main content

DataSignals Events MCP server

Ask an AI assistant about US regulatory filings and have it answer from the filings themselves, with a link back to each one.

This is a small MCP server that runs on your own machine and talks to the DataSignals Events API with your key. Twelve streams in one schema: insider buying clusters, planned insider sales (Form 144), activist stakes (13D/G), institutional holdings (13F), material corporate events (8-K), private capital raises (Form D), FDA actions, biotech trial catalysts, NIH grants, federal contract awards and congressional trades.

There is nothing to sign up for beyond the API key you already have, and nothing is billed twice: a call here spends one thing, the monthly event allowance on your plan.

Install

pip install datasignals-events-mcp

Configure your client

Add this to your MCP client configuration, with your own key. In Claude Desktop the file is claude_desktop_config.json; Cursor, Zed and the others use the same shape.

{
  "mcpServers": {
    "datasignals-events": {
      "command": "datasignals-events-mcp",
      "env": {
        "DATASIGNALS_KEY": "ds_live_your_key_here"
      }
    }
  }
}

Restart the client. Ask it to run check_setup and it will tell you whether the key is configured and whether the feed answers.

No key yet? Two of the tools, list_event_types and feed_health, work without one, so you can see the shape of the data and how fresh it is before you decide. Plans, including a free one, are at https://datasignalslab.com/events-api.html.

What you can ask

The tools are built around questions rather than endpoints:

Tool Answers
search_events "Which FDA actions this week scored above 70?"
company_events "What has been filed on NVDA lately, across all streams?"
get_event "Show me everything on this one event."
list_event_types "Which fields does the Form D stream actually carry?"
feed_health "How current is this data right now?"
usage "How much of my allowance is left, and when does it reset?"
check_setup "Is this thing configured correctly?"

Every record carries the URL of the filing it was parsed from. Where a record has a score, it also carries the terms that score was built from and a flag saying whether those terms were complete; when a term is missing from the published source that flag is false rather than a number being invented.

Honest limits

  • Not real time. Sources refresh once a night, congressional trades weekly and 13F quarterly, because that is how often they are published. The freshest an event can be is this morning's round.
  • Published filings only. The archive holds what was published, not everything a source ever had.
  • Not investment advice. This is data for research and monitoring.

Environment variables

Variable Meaning
DATASIGNALS_KEY Your API key, starting with ds_live_. Required for everything except list_event_types and feed_health.
DATASIGNALS_BASE_URL Override the API base URL. You will not normally need this.

The key is sent as an Authorization header and never as a query parameter, so it does not end up in server logs or browser history. Keep it server-side; anyone holding it can spend your allowance.

Development

python3 -m venv .venv
.venv/bin/pip install -e . pytest
.venv/bin/python -m pytest tests -q

The tests use a mock transport and never touch the network, except for the handshake tests, which start the server for real and speak MCP to it over stdio against a deliberately unreachable endpoint.

Support

support@datasignalslab.com, or the quickstart at https://datasignalslab.com/events-api-quickstart.html.

MIT licensed.

Metadata

Release files for datasignals-lab-events-mcp 1.1.1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for datasignals-lab-events-mcp 1.1.1
File Size Uploaded
datasignals_lab_events_mcp-1.1.1.tar.gz 14.2 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for datasignals-lab-events-mcp 1.1.1
File Interpreter ABI Platform
datasignals_lab_events_mcp-1.1.1-py3-none-any.whl Python 3 none any Details

Total release size: 29.2 kB

Release files / datasignals_lab_events_mcp-1.1.1.tar.gz

Download URL datasignals_lab_events_mcp-1.1.1.tar.gz
Size 14.2 kB
Tags Source
SHA-256 checksum
How to use checksums
9870130d4014d5a20c65309901b7b8703747ea657de72e9b061e8fe72e7e8959
BLAKE2b-256 checksum
How to use checksums
211b1329fea87f9a05291dbfbf0420ec4c25a8dd24ba238fdef07318c199d0a0
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.11.11

Release files / datasignals_lab_events_mcp-1.1.1-py3-none-any.whl

Download URL datasignals_lab_events_mcp-1.1.1-py3-none-any.whl
Size 15.0 kB
Tags Python 3
SHA-256 checksum
How to use checksums
d68e6407ee36a649c034f83549f6c9850eb23f9de46d08179a72341e1966907b
BLAKE2b-256 checksum
How to use checksums
88563aef9ce85d4c61d0a08c4a3ae48387086753d2c69c1ae280417e6bdf1c21
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.11.11

Release history Release notifications | RSS feed

This release

1.1.1 This release

2 release files

1.1.0

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page