Skip to main content
4 min read

The CLI

The map for talking to abm.dev from code, from an agent, and from your terminal. One request in. Eighty-nine fields and forty signals back, each one cited. No subscription. No per-source bill. A value is either sourced or it is not returned.

The shape of it

abm.dev is an enrichment API. You send one identifier — an email, a LinkedIn URL, or a company domain — and abm.dev resolves it across ten data sources (LinkedIn, Companies House, Perplexity, Tavily, Hunter, and others) into a single response.

Every value in that response carries three things: its source (which provider it came from), a confidence score from 0 to 1, and a selection_reason— why that value was chosen. Higher confidence means more agreement across sources. Nothing is invented. If abm.dev can’t cite a value, it doesn’t return one.

There are three ways to reach it.

  • From an agent — connect the MCP server, or point the agent at the docs.
  • From the terminal or a script — call the REST API directly.
  • From a browser — try it in the playground, free.

Get a key

Sign up, then create a key from your dashboard. Every request authenticates with that key.

Note

Send your key as either an x-api-key header (the form used below) or Authorization: Bearer on POST /api/v2/enrichments. The full, live contract is at the API reference.

Call it from a script

Two endpoints. Submit an enrichment, then read it back.

Submit

Bash
curl -X POST https://api.abm.dev/api/v2/enrichments \
  -H "x-api-key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"targets":[{"type":"person","email":"[email protected]"}]}'

Each target also accepts a LinkedIn URL or a company domain instead of an email.

Retrieve

Bash
curl https://api.abm.dev/api/v2/enrichments/{id} \
  -H "x-api-key: YOUR_API_KEY"

That’s the whole surface for direct calls. For the full request and response schema — field lists, types, and the exact response envelope — read the enrichment reference. For batch jobs, see the jobs reference.

Connect an agent

Claude

Add the MCP server and abm.dev’s enrichment tools appear inside Claude.

  1. Settings → Connectors → Custom.
  2. Paste the URL:
Text
https://mcp.abm.dev/mcp

The server exposes abm.dev’s enrichment tools to the agent. The exact tool list isn’t documented here — see /for-agents. Setup walkthrough: Claude connector.

Cursor, Claude Code, Windsurf

No connector UI. Hand the agent a prompt instead — tell it to:

  1. Read https://abm.dev/llms.txt.
  2. Request an API key.
  3. Save the key to a .env file.
  4. Run one test enrichment.
  5. Report back with citations.

The agent reads the spec, wires itself up, and verifies the connection before it touches your data. More at /for-agents.

Live results and batches

For agent loops that need answers as they arrive, abm.dev streams results in real time over SSE. For batch jobs, a webhook fires when the job finishes. The configuration details for both live in the jobs reference — webhook setup is documented there, not invented here.

The CLI

abm.dev publishes a command-line client for terminal-first workflows. The binary, install method, commands, and flags are documented in one place and may change — treat /docs/cli as the source of truth rather than anything memorised. If you only need to submit and read enrichments, the two REST calls above are the whole story.

What you pay

Per enrichment. No subscription. Credits never expire, and every data source is included in the price — no per-source bills, no per-field charges. Pricing starts at about €0.29 per enrichment.

Packs:

PackPrice
30€2.89
100€9.29
500 (best value)€36.99
2,000€119.99

The playground is free. New accounts get free launch credits — use code LAUNCHCODES. Full breakdown at pricing.

Where to go next

abm.dev is operated by Foxley Farm Operations Ltd (UK Company No. 16392009), Oakham, United Kingdom. GDPR-compliant. Questions the docs don’t answer? Open a ticket.