# Explorium AgentSource vs Retriever

> Explorium AgentSource scores 44 (E) to Retriever's 32 (F) for lead search. Prices, MCP, x402, uptime and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/explorium-agentsource-vs-retriever
- Markdown: https://www.anchorterminal.com/compare/explorium-agentsource-vs-retriever.md (~5,400 tokens)
- Slim: https://www.anchorterminal.com/compare/explorium-agentsource-vs-retriever.min.md (~1,180 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/compare/explorium-agentsource-vs-retriever.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (the key docs and every listing in one file, at most 16 MB, about 4 million tokens: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- MCP: https://www.anchorterminal.com/mcp (the whole catalogue as tools, no key)
- DNS: dig +short TXT <slug>.grade.anchorterminal.com (the grade as a DNS TXT record, for a sandbox with no HTTP where names still resolve; also top., best.<category>. and <a>.vs.<b>. under the zone, and the same under grade.letme.dev)
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)
- Updated: 2026-11-18

Explorium AgentSource scores 44 (E) on agent readiness against Retriever's 32 (F), and leads in 4 of 7 scored categories. Retriever leads on schema & documentation and agent ergonomics. Both do lead search.

- Explorium AgentSource: grade E, 44/100, rank #1315 of 1557. Markdown https://www.anchorterminal.com/tools/explorium-agentsource.md · JSON https://www.anchorterminal.com/api/v1/tools/explorium-agentsource.json
- Retriever: grade F, 32/100, rank #1455 of 1557. Markdown https://www.anchorterminal.com/tools/retriever.md · JSON https://www.anchorterminal.com/api/v1/tools/retriever.json
- Best lead, contact and company data APIs for AI agents: https://www.anchorterminal.com/best/lead-data/index.md
- All 253 leads comparisons: https://www.anchorterminal.com/compare/lead-data/index.md

## Which one, for what

### Explorium AgentSource (E)

Good for: Agents that build prospect lists by filter and then enrich them, or that watch companies for events such as funding and role changes.

Ahead on:
- Security & auth, 32 against 23
- Payments & pricing, 60 against 30
- Maintenance & community, 28 against 5
- Transparency & trust, 61 against 49

Watch for: No status page was found, and no SLA is published

### Retriever (F)

Good for: A sales team that wants an agent to build qualified lead tables and run outreach from Claude, Cursor or Codex.

Ahead on:
- Schema & documentation, 82 against 40
- Agent ergonomics, 75 against 63

Watch for: Its sequences send LinkedIn invitations, messages, visits and likes from connected accounts automatically, which LinkedIn forbids, so customers' accounts can be restricted


## Why the edge

### Schema & documentation: Retriever +42

- Explorium AgentSource (40): Explorium's terms bar robots and automated collection on its website, so only the terms were re-read on 4 November and other readings are per the 9 October check. The OpenAPI 3.1 file read on 9 October has no recorded visible link from a docs page, and the host can't be re-read to find one, so it no longer counts as a published contract (0 of 25). llms.txt and a Markdown twin of every docs page (10). The docs pages and the 11 MCP tool descriptions say what each call is for and what to call first (12 of 20). The typed schemas, enums and item limits were read from that file, so they no longer count (0 of 15). Docs pages have request and response examples, and the error guide lists Partner ID header messages that don't match the `api_key` scheme (10 of 15). Versions live in the path with a migration guide and a full v2 change list. No dated changelog was found (8 of 15). 0+10+12+0+10+8 = 40.
- Retriever (82): OpenAPI 3.1 file, version 1.0.0, about 51 paths, linked from llms.txt (25). llms.txt and a Markdown copy of every docs page (10). The tool catalogue says when to use most tools and when not to (cancels only on the user's request, slow services only in a batch) (17 of 20). The OpenAPI file has enums and required fields; the MCP input schemas weren't read, since tools/list needs a key (11 of 15). An errors page with stable codes and the action for each, plus examples in the docs (14 of 15). Routes are versioned under /v1 but there's no public changelog (5 of 15).

### Payments & pricing: Explorium AgentSource +30

- Explorium AgentSource (60): Explorium's terms bar robots and automated collection on its website, so only the terms were re-read on 4 November and other readings are per the 9 October check. No x402, MPP or L402 (0). Credit pack prices and per-operation credit costs are public without a login (20). The pricing page and the site's own `pricing.md` disagree on two packs, which is recorded as a deduction and not here. Free trial of 100 credits for 90 days. No page read asks for a card at sign-up, and the auto-refill guide treats a payment method as something added later (20). The vendor's `auth.md` says registration needs a person and there is no client-registration endpoint (0). Total 40. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 40 is 60.
- Retriever (30): No x402, MPP or L402 (0). Credits per action and the dollar price per credit ($0.0134 on Starter) are public without a login (30). No free tier or trial without a card found; the terms say only that free tiers may be offered (0). Access needs a browser signup and a subscription, so an agent can't onboard itself (0).

### Maintenance & community: Explorium AgentSource +23

- Explorium AgentSource (28): Explorium's terms bar robots and automated collection on its website, so only the terms were re-read on 4 November and other readings are per the 9 October check. The last dated API change found is v2 general availability on 2 September 2026, 63 days before 4 November (20 of 30). No dated changelog, so three entries in 90 days could not be shown (0). Support by email and by a shared Slack channel for customers that have one, with no public changelog or forum (5 of 15). No official REST SDK found. The repository's `server.json` names `ai.explorium/mcp-explorium`, but no registry page could be read (0). The `mcp-explorium` repository is MIT, with its last commit on 22 January 2026 and only a publishing workflow, no CI (3 of 10). 20+0+5+0+3 = 28.
- Retriever (5): No changelog, release notes or dated API change found, and the docs carry no dates; the blog's posts are marketing articles, not release notes (0 and 0). Support is an email address and a demo booking, with no public changelog or community channel that answers (5 of 25). Not in the official MCP registry and no official SDK (0). No package to check (0). The domain dates from 7 April 2026.

### Agent ergonomics: Retriever +12

- Explorium AgentSource (63): Explorium's terms bar robots and automated collection on its website, so only the terms were re-read on 4 November and other readings are per the 9 October check. 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. `page` and `page_size` up to 500, a `next_cursor` mode with no limit, and filters with autocomplete (20). Errors carry a `correlation_id`, 422 names the failing field, and Research returns failed rows with an `_error` field. Error bodies have no stable code (15 of 20). No idempotency keys. Retry guidance covers 429 and 500. MCP tool annotations were not read because we did not connect (6 of 20). No official REST SDK found in the docs index. Enrichment needs a match or fetch call first, and five filters need an autocomplete call first (5 of 15). 17+20+15+6+5 = 63.
- Retriever (75): 67 tools in the catalogue (5), with 5 back because the outreach tools are a toolset shown only when the organisation has a sender and switchable in settings (10 of 25). Limit, offset and cursor pagination, up to 1,000 rows a call, and the first 20 rows returned with a finished run (18 of 20). Stable error codes with the action to take (20). Idempotency-Key on run creation, and readOnlyHint, destructiveHint and idempotentHint on the tools (20). Few required parameters (a run needs only a prompt), but no official SDK, only a Node client in a recipe (7 of 15).

### Transparency & trust: Explorium AgentSource +12

- Explorium AgentSource (61): Explorium's terms bar robots and automated collection on its website, so only the terms were re-read on 4 November and other readings are per the 9 October check. Closed service. The Explorium Terms of Use (updated 14 June 2026, re-read) cover the Platform, API and data, and let Explorium change or end the service without notice (14 of 30). The privacy policy (updated 28 June 2026) sets out controller and processor roles, publishes 2025 request counts and links an opt-out page. Retention has no periods, and no DPA was found on the pages read (16 of 30). The v1 timeline gives end of support about six months and retirement about twelve months after 2 September 2026, marked indicative, and website traffic enrichment is slated for removal with no date. Dated notices take 15 as settled in this run (15 of 20). Processing in Israel, the United States and the EU is stated. No sub-processor list was found (6 of 20). 14+16+15+6 = 51.
- Retriever (49): Closed source with clear terms, last updated 30 August 2026 (15). The privacy policy states retention (deletion within 30 days of closing an account) and names some subprocessors, but says nothing about the LinkedIn and email accounts customers connect, the people in lead tables or the data providers named on the pricing page (12 of 30). The terms say the service may be changed or removed "with reasonable notice" and material changes to the terms get 15 days' notice; no deprecation dates found (8 of 20). Subprocessors are given as examples (Vercel, Railway, Supabase, Anthropic, OpenAI) with no data locations, beyond Standard Contractual Clauses for transfers (8 of 20).

### Security & auth: Explorium AgentSource +9

- Explorium AgentSource (32): Explorium's terms bar robots and automated collection on its website, so only the terms were re-read on 4 November and other readings are per the 9 October check. The docs say each company gets a single API key shared by all its users, sent in a header. The site's `auth.md` says a key can be deleted in the console, and the key page says to ask an administrator for a reset. No scopes (12 of 30). No read-only mode or per-key limits. The API mostly reads, writes are limited to webhooks and event enrolments, and auto-refill has an optional cap (5 of 20). Research scrapes web pages and the LinkedIn post enrichments return third-party text. No prompt-injection guidance was found in the docs (2 of 15). Balance and aggregation endpoints, per-call credit reporting, correlation IDs and last-active times for users. No per-call log was found (8 of 15). The privacy policy states SOC 2, ISO 27001 and ISO 27701, with no report, security.txt, disclosure policy or bug bounty found. A certification claim with no report or reporting route takes 5, as settled in this run (5 of 20). No GitHub-reviewed advisory names Explorium in the 12 months to 4 November. 12+5+2+8+5 = 32.
- Retriever (23): The MCP server's OAuth 2.1 issues an ordinary API key, and keys have no scopes or expiry and work as their creator in that organisation: plain revocable keys (20), less 10 because the MCP docs offer the key in the URL as `?api_key=` (10 of 30). No read-only mode; destructive hints and explicit-request instructions on cancels and deletes, and the outreach toolset can be switched off (8 of 20). The tools return scraped pages, social posts and inbox replies, with no prompt-injection guidance found (0). Credit charges per run and a credits ledger by source, but no audit log documented (5 of 15). No security.txt (404), disclosure policy, bug bounty or certification found (0).

## Score by category

| Category | Weight | Explorium AgentSource | Retriever | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% | 42 | 45 | Retriever +3 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% | 40 | 82 | Retriever +42 |
| Agent ergonomics | 13% | 63 | 75 | Retriever +12 |
| Security & auth | 14% | 32 | 23 | Explorium AgentSource +9 |
| Payments & pricing | 10% | 60 | 30 | Explorium AgentSource +30 |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% | 28 | 5 | Explorium AgentSource +23 |
| Transparency & trust | 7% | 61 | 49 | Explorium AgentSource +12 |
| Negative events | ≤15 | -2 | -15 | |
| **Total** | | **44 · E** | **32 · F** | |

## Facts side by side

| Fact | Explorium AgentSource | Retriever |
| --- | --- | --- |
| Kind | HTTP API | HTTP API |
| Vendor | Explorium Ltd. | Retriever |
| Hosted endpoint | `https://api.explorium.ai` | `https://api.retriever.run/mcp` |
| Transports | HTTP, Streamable HTTP, SSE (legacy) | Streamable HTTP |
| Auth | API key | OAuth or key |
| Pricing | Pay per use | Paid |
| x402 | no | no |
| Licence | Proprietary service under the Explorium Terms of Use. The `mcp-explorium` repository of connection files is MIT | none |
| Tools exposed | 11 | 67 |
| Read-only variant documented | no | yes |
| llms.txt | yes | yes |
| Last release | 2026-09-02 | none |
| Terms last updated | 2026-06-14 | 2026-08-30 |
| Privacy policy last updated | 2026-06-28 | 2026-08-30 |
| Customer content may train models | not found in the text | not found in the text |
| Terms restrict automated access | yes | yes |
| Terms restrict benchmarking | yes | not found in the text |
| Terms or service can change without notice | yes | not found in the text |
| Arbitration or class-action waiver | not found in the text | not found in the text |

## How the scores have moved

### Explorium AgentSource

- +2.5 on 13 November 2026: checklist
- -6.7 on 4 November 2026 (D to E): new evidence, correction
- -0.1 on 28 October 2026: correction

### Retriever

No score change since it was listed.

## Verdicts

**Explorium AgentSource.** AgentSource v2 has 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, no specification file is linked from the docs, and the vendor's two published price tables disagree.

**Retriever.** Retriever automates outreach from customers' LinkedIn accounts, which LinkedIn's rules forbid. For agents it has an OAuth MCP server, an OpenAPI file, idempotency keys, stable error codes and published credit prices, but no status page, changelog, security contact, free tier or named company behind it.

## Before you call either

### Explorium AgentSource

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

### Retriever

1. Don't enrol leads in a sequence with LinkedIn steps without the user knowing LinkedIn forbids automated activity and can restrict their account
2. Send an `Idempotency-Key` with each run and replay with the same key after a timeout, so a retry doesn't start a second billed run
3. Run `getEmail`, `getPhoneNumber` and `webResearch` through `service_batch_execute`, even for one person; `service_execute` refuses them
4. Check `credits` before a paid run, and call `service_inspect` for a service's `thingsToKnow` and credit cost before executing it
5. On 429 wait for Retry-After; at most 5 runs execute per organisation, so a queued run starts on its own and shouldn't be created again

## Questions

### Which is better for AI agents, Explorium AgentSource or Retriever?

Explorium AgentSource scores 44 (E) on agent readiness against Retriever's 32 (F), and leads in 4 of 7 scored categories. Retriever leads on schema & documentation and agent ergonomics.

### Do Explorium AgentSource and Retriever need an API key?

Explorium AgentSource needs an API key. Retriever takes an API key or an OAuth sign-in.

### Can an agent call Explorium AgentSource and Retriever without installing anything?

Yes. Explorium AgentSource has a hosted endpoint at https://api.explorium.ai and Retriever at https://api.retriever.run/mcp.


## For agents

- This comparison as JSON: https://www.anchorterminal.com/compare/explorium-agentsource-vs-retriever.json, and with the fewest tokens: https://www.anchorterminal.com/compare/explorium-agentsource-vs-retriever.min.md
- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {"a": "explorium-agentsource", "b": "retriever"}`. From a terminal: `anchor compare explorium-agentsource retriever`
- Each listing in full: https://www.anchorterminal.com/api/v1/tools/explorium-agentsource.json and https://www.anchorterminal.com/api/v1/tools/retriever.json

## Other comparisons with Explorium AgentSource or Retriever

- [Apollo API + MCP vs Explorium AgentSource](https://www.anchorterminal.com/compare/apollo-vs-explorium-agentsource.md)
- [Apollo API + MCP vs Retriever](https://www.anchorterminal.com/compare/apollo-vs-retriever.md)
- [Clay vs Explorium AgentSource](https://www.anchorterminal.com/compare/clay-vs-explorium-agentsource.md)
- [Clay vs Retriever](https://www.anchorterminal.com/compare/clay-vs-retriever.md)
- [Coresignal API + MCP vs Explorium AgentSource](https://www.anchorterminal.com/compare/coresignal-vs-explorium-agentsource.md)
- [Coresignal API + MCP vs Retriever](https://www.anchorterminal.com/compare/coresignal-vs-retriever.md)
- [Crustdata API + MCP vs Explorium AgentSource](https://www.anchorterminal.com/compare/crustdata-vs-explorium-agentsource.md)
- [Crustdata API + MCP vs Retriever](https://www.anchorterminal.com/compare/crustdata-vs-retriever.md)
- [Dievio vs Explorium AgentSource](https://www.anchorterminal.com/compare/dievio-vs-explorium-agentsource.md)
- [Dievio vs Retriever](https://www.anchorterminal.com/compare/dievio-vs-retriever.md)
- [Enrich Layer API + MCP vs Explorium AgentSource](https://www.anchorterminal.com/compare/enrich-layer-vs-explorium-agentsource.md)
- [Enrich Layer API + MCP vs Retriever](https://www.anchorterminal.com/compare/enrich-layer-vs-retriever.md)
- [Explorium AgentSource vs FullEnrich API + MCP](https://www.anchorterminal.com/compare/explorium-agentsource-vs-fullenrich.md)
- [Explorium AgentSource vs Fuse MCP](https://www.anchorterminal.com/compare/explorium-agentsource-vs-fuse-mcp.md)
- [Explorium AgentSource vs Gojiberry](https://www.anchorterminal.com/compare/explorium-agentsource-vs-gojiberry.md)
- [Explorium AgentSource vs Hunter API + MCP](https://www.anchorterminal.com/compare/explorium-agentsource-vs-hunter.md)
- [Explorium AgentSource vs LeadMagic API + MCP](https://www.anchorterminal.com/compare/explorium-agentsource-vs-leadmagic.md)
- [Explorium AgentSource vs Lusha API + MCP](https://www.anchorterminal.com/compare/explorium-agentsource-vs-lusha.md)
- [Explorium AgentSource vs People Data Labs](https://www.anchorterminal.com/compare/explorium-agentsource-vs-people-data-labs.md)
- [Explorium AgentSource vs Prospeo API + MCP](https://www.anchorterminal.com/compare/explorium-agentsource-vs-prospeo.md)
- [Explorium AgentSource vs RocketReach API](https://www.anchorterminal.com/compare/explorium-agentsource-vs-rocketreach.md)
- [Explorium AgentSource vs ZoomInfo API + MCP](https://www.anchorterminal.com/compare/explorium-agentsource-vs-zoominfo.md)
- [FullEnrich API + MCP vs Retriever](https://www.anchorterminal.com/compare/fullenrich-vs-retriever.md)
- [Fuse MCP vs Retriever](https://www.anchorterminal.com/compare/fuse-mcp-vs-retriever.md)
- [Gojiberry vs Retriever](https://www.anchorterminal.com/compare/gojiberry-vs-retriever.md)
- [LeadMagic API + MCP vs Retriever](https://www.anchorterminal.com/compare/leadmagic-vs-retriever.md)
- [Lusha API + MCP vs Retriever](https://www.anchorterminal.com/compare/lusha-vs-retriever.md)
- [People Data Labs vs Retriever](https://www.anchorterminal.com/compare/people-data-labs-vs-retriever.md)
- [Prospeo API + MCP vs Retriever](https://www.anchorterminal.com/compare/prospeo-vs-retriever.md)
- [Retriever vs RocketReach API](https://www.anchorterminal.com/compare/retriever-vs-rocketreach.md)
- [Retriever vs ZoomInfo API + MCP](https://www.anchorterminal.com/compare/retriever-vs-zoominfo.md)
- [Clearbit vs Explorium AgentSource](https://www.anchorterminal.com/compare/clearbit-vs-explorium-agentsource.md)
- [Clearbit vs Retriever](https://www.anchorterminal.com/compare/clearbit-vs-retriever.md)
- [Databar vs Explorium AgentSource](https://www.anchorterminal.com/compare/databar-vs-explorium-agentsource.md)
- [Databar vs Retriever](https://www.anchorterminal.com/compare/databar-vs-retriever.md)
- [Dropcontact API + MCP vs Explorium AgentSource](https://www.anchorterminal.com/compare/dropcontact-vs-explorium-agentsource.md)
- [Dropcontact API + MCP vs Retriever](https://www.anchorterminal.com/compare/dropcontact-vs-retriever.md)
- [Explorium AgentSource vs FullContact](https://www.anchorterminal.com/compare/explorium-agentsource-vs-fullcontact.md)
- [Explorium AgentSource vs ZeroBounce](https://www.anchorterminal.com/compare/explorium-agentsource-vs-zerobounce.md)
- [FullContact vs Retriever](https://www.anchorterminal.com/compare/fullcontact-vs-retriever.md)
- [Retriever vs ZeroBounce](https://www.anchorterminal.com/compare/retriever-vs-zerobounce.md)
- [Hunter API + MCP vs Retriever](https://www.anchorterminal.com/compare/hunter-vs-retriever.md)

---

Query this catalogue directly over MCP: https://www.anchorterminal.com/mcp (Streamable HTTP, no key). How: https://www.anchorterminal.com/agents/#mcp
