# Explorium AgentSource (slim)

> Explorium's AgentSource is a B2B data service for matching, searching and enriching companies and prospects, with event signals and AI research tasks. Agents reach it through a REST API (v2) and a hosted MCP server.

- Full: https://www.anchorterminal.com/tools/explorium-agentsource.md (~8,350 tokens) · this version ~1,730 tokens · JSON https://www.anchorterminal.com/tools/explorium-agentsource.json · canonical https://www.anchorterminal.com/tools/explorium-agentsource
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-10

**D · 48.1/100 · rank #821 of 950 · #14 in Lead & company data · not agent-ready · confidence medium**


Assessment: AgentSource v2 has a public OpenAPI 3.1 file, Markdown docs, a 200 queries a minute limit with `Retry-After`, public credit prices and a 100-credit trial. No status page or published SLA was found, each company shares one API key with no scopes, and the vendor's two published price tables disagree.

## Facts

- Kind: HTTP API · vendor: Explorium Ltd. · category: Lead & company data · legal entity: Explorium Ltd. · provenance 68/100
- Endpoint: `https://api.explorium.ai` (HTTP, Streamable HTTP, SSE (legacy))
- Auth: API key · pricing: Pay per use · x402: no · licence: Proprietary service under the Explorium Terms of Use. The `mcp-explorium` repository of connection files is MIT
- Probe metrics: not measured yet (probes haven't run)
- Modes: Lead search (fetch businesses and prospects by filter, 1 credit a result), enrichment (17 business and 3 prospect enrichments, 1 to 5 credits) and contact lookup (professional email 2 credits, email and phone 5). No standalone email verifier
- API: REST at https://api.explorium.ai, 74 operations under `/v2` and 67 under `/v1` in the OpenAPI 3.1 file (version 0.3.32). Every enrichment has a sync `/enrich` (up to 50 IDs) and an async `/job` (up to 10,000 records, 24 hours)
- MCP server: Hosted at https://mcp-v2.explorium.ai/mcp (Streamable HTTP) and `/sse`, 11 tools, API key as bearer token. The v1 server at mcp.explorium.ai uses OAuth and is deprecated with v1
- Free tier: Free trial of 100 credits valid 90 days. No standing free tier
- Rate limits: 200 queries a minute per API key over a 60-second sliding window. Each entity in a batch counts as one query. Enterprise plans can buy more
- Errors: JSON errors with `details` and a `correlation_id`. 422 lists the failing fields, 403 signals no credits, 429 carries `Retry-After`
- Pagination: `page` and `page_size` up to 500 a page and 60,000 records, or a `next_cursor` token with no limit
- Webhooks: Up to 10 per tenant, each with its own rotatable HMAC secret. Deliveries are signed over the timestamp and payload in `X-Signature`
- Research: `/v2/businesses/research` and `/v2/prospects/research` run an LLM task per entity with optional web search and scraping, and a caller-defined output schema
- Credit visibility: `GET /v2/credits` returns the balance, `/v2/credits/aggregation` returns usage over time, and the `credit-usage: true` header adds the credits spent to each response
- Certifications: SOC 2, ISO 27001 and ISO 27701 per the privacy policy. No report or certificate was read
- Open source: No. The `mcp-explorium` repository holds connection files for the v1 MCP server under MIT
- Prices: Lite credit pack $0.06 per credit; Starter credit pack $0.03 per credit; Growth credit pack $0.025 per credit; Scale credit pack $0.015 per credit; Fetched business or prospect $0.03 per record; Contact enrichment, email and phone $0.15 per record

- Scores: Reliability 42, Performance pending, Schema & documentation 76, Agent ergonomics 63, Security & auth 37, Payments & pricing 40, Task success pending, Maintenance & community 28, Transparency & trust 59 · negative events -2 · total over the 7 assessed categories
- Why: Reliability, Hosted lines. · Schema & documentation, Public OpenAPI 3.1 file with 74 v2 and 67 v1 operations (25). · Agent ergonomics, The MCP v2 server has 11 tools (15), and the statistics tools are free for sizing an audience before a paid fetch (2 added back), 17 of 25… · Security & auth, The docs say each company gets a single API key shared by all its users, sent in a header. · Payments & pricing, No x402, MPP or L402 (0). · Maintenance & community, The last dated API change found is v2 general availability on 2 September 2026, 37 days before the check (20 of 30). · Transparency & trust, Closed service.
- Sources: 30, open questions: 10, both in the full twin
- Capabilities: lead.search, lead.enrichment, email.finder, data.company, data.person
- JSON: https://www.anchorterminal.com/api/v1/tools/explorium-agentsource.json
- Verify (for the vendor): the badge `https://www.anchorterminal.com/badges/explorium-agentsource.svg` or a link to https://www.anchorterminal.com/tools/explorium-agentsource from a page on explorium.ai or one of its subdomains, or the README of github.com/explorium-ai/mcp-explorium, then `POST https://www.anchorterminal.com/api/v1/verify` `{"slug", "url"}` or `verify_listing` at /mcp; re-checked weekly, no effect on the grade. Snippets in the full twin.

## Before you call it

1. Send the key in the `api_key` header to `https://api.explorium.ai` and use `/v2` paths. v1 is deprecated
2. Point MCP clients at `https://mcp-v2.explorium.ai/mcp`. The site's agent files still name the v1 server at `mcp.explorium.ai`
3. Count each entity in a batch as one query against the 200 a minute limit, so 50 IDs in one call spend 50
4. Call the statistics endpoint first to size an audience for free. Fetch costs 1 credit a result, or 2 with the Bombora intent filter
5. Call `/v2/autocomplete` before filtering on category, tech stack or job title, and never mix two category types in one request

## Connect

```bash
curl --request POST --url https://api.explorium.ai/v1/prospects --header 'accept: application/json' --header 'api_key: YOUR_API_KEY' --header 'content-type: application/json' --data '{"mode": "full", "page": 1}'
```
Full config and headless snippets are in the full page. Through letme (picks today, calling later): https://letme.dev/explorium-agentsource

## Similar tools

| Tool | Grade | Score | Shared capabilities | Slim |
| --- | --- | --- | --- | --- |
| Apollo API + MCP | B | 63.3 | lead.search, lead.enrichment, email.finder, data.company, data.person | https://www.anchorterminal.com/tools/apollo.min.md |
| Coresignal API + MCP | B | 62.9 | lead.search, lead.enrichment, email.finder, data.company, data.person | https://www.anchorterminal.com/tools/coresignal.min.md |
| Lusha API + MCP | B | 62.3 | lead.search, lead.enrichment, email.finder, data.person, data.company | https://www.anchorterminal.com/tools/lusha.min.md |
| LeadMagic API + MCP | C | 60.2 | lead.search, lead.enrichment, email.finder, data.person, data.company | https://www.anchorterminal.com/tools/leadmagic.min.md |
| FullEnrich API + MCP | C | 59.6 | lead.search, lead.enrichment, email.finder, data.person, data.company | https://www.anchorterminal.com/tools/fullenrich.min.md |


## Panel reviews (0, desk reviews from public material, no calls made)