# FullContact vs Retriever

> FullContact scores 44.7 (E) to Retriever's 32 (F) for lead enrichment. Prices, MCP, x402, uptime and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/fullcontact-vs-retriever
- Markdown: https://www.anchorterminal.com/compare/fullcontact-vs-retriever.md (~4,550 tokens)
- Slim: https://www.anchorterminal.com/compare/fullcontact-vs-retriever.min.md (~1,030 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/compare/fullcontact-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

FullContact scores 44.7 (E) on agent readiness against Retriever's 32 (F), and leads in 3 of 7 scored categories. Retriever leads on schema & documentation and payments & pricing. Both do lead enrichment.

- FullContact: grade E, 44.7/100, rank #1294 of 1557. Markdown https://www.anchorterminal.com/tools/fullcontact.md · JSON https://www.anchorterminal.com/api/v1/tools/fullcontact.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

### FullContact (E)

Good for: Agents that need to turn an email or phone number into a person profile, including consumer demographics and hashed-identifier matching.

Ahead on:
- Security & auth, 43 against 23
- Maintenance & community, 10 against 5
- Transparency & trust, 65 against 49

Also in its favour:
- No incidents deducted, where Retriever loses 15 points for them

Watch for: No public prices. Access starts with a sales conversation

### 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 50
- Payments & pricing, 30 against 15

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 +32

- FullContact (50): No OpenAPI file for the REST API was found on 14 October, and docs.fullcontact.com/reference returned 404. The typed JSON Schema for the MCP tool came from a request to the server itself, which this benchmark no longer uses, and the docs can't be re-read while the host is paused (0 of 25). Per the 14 October check, not re-read on 11 November, llms.txt and Markdown copies of every page (10), a tool description that says what it does but not when to use it, with docs on which identifier combinations match best (13 of 20), inputs documented by type with no required fields or enums, and the rule that location needs a name only in text (8 of 15), examples for every input combination and an error table with codes, HTTP analogues and a retryable flag (14 of 15), and v3 in the path with a changelog whose newest entries date from 2022 (5 of 15). 0 + 10 + 13 + 8 + 14 + 5 = 50.
- 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).

### Security & auth: FullContact +20

- FullContact (43): Per the 14 October check, not re-read on 11 November. One Bearer API key per integration, revocable with a rotation procedure, scoped by product entitlement rather than by scope. No OAuth on the MCP server (20). Every call is a read and nothing writes, but there is no read-only key mode beyond entitlements (12 of 20). Responses carry bios and social data from third parties, and no prompt-injection guidance was found (3 of 15). Every MCP response carries a request_id, and no per-call log for the customer was found (3 of 15). The MCP docs say the server runs inside FullContact's SOC 2 boundary, but the security page, dated 1 January 2020, lists no certification or reporting channel, and there is no security.txt (5 of 20). OSV lists no advisory for python-fullcontact on 11 November. 20 + 12 + 3 + 3 + 5 = 43.
- 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).

### Transparency & trust: FullContact +16

- FullContact (65): Closed service under Website Terms of Use last updated 21 March 2025 that name J2 Martech Corp., re-read on 11 November (15). Per the 14 October check, not re-read on 11 November, the privacy policy, updated 1 October 2026, names data brokers, data partners, public sources and trackers and has an opt-out portal, but gives no fixed retention period and doesn't say whether customer inputs feed the graph, while the MCP docs say inputs aren't persisted (15 of 30). A dated sunset of the v2 Company APIs on 30 June 2022, a dated notice with no stated notice period (15, the value other listings' dated notices take). No sub-processor list found (0). 15 + 15 + 15 + 0 = 45.
- 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).

### Payments & pricing: Retriever +15

- FullContact (15): Per the 14 October check, not re-read on 11 November. No x402, MPP or L402 (0). No prices published, and the pricing page asks visitors to talk to an expert (0). A free Platform account and sandbox keys for evaluation, but whether production lookups need a contract or a card wasn't stated (10 of 20). A person signs up in a browser and generates a key (0). 0 + 0 + 10 + 0 = 10. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 10 is 15.
- 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: FullContact +5

- FullContact (10): The newest dated change to the API is the MCP documentation of 30 April 2026, 195 days before 11 November, and a clone of the Python client stops at a commit of 1 July 2022 with version 4.0.0, its tags at v3.0.2 of 8 June 2021 (0). No dated releases or changelog entries since 13 August (0). Per the 14 October check, a support address and request IDs, with a changelog that stops in 2022 (5 of 15). The Python client hasn't changed since July 2022 and the MCP server isn't in the official registry (3 of 15, the earlier partial kept). No current package or CI to judge (2 of 10, the earlier partial kept). 0 + 0 + 5 + 3 + 2 = 10.
- 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.

## Score by category

| Category | Weight | FullContact | Retriever | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% | 42 | 45 | Retriever +3 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% | 50 | 82 | Retriever +32 |
| Agent ergonomics | 13% | 75 | 75 | even |
| Security & auth | 14% | 43 | 23 | FullContact +20 |
| Payments & pricing | 10% | 15 | 30 | Retriever +15 |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% | 10 | 5 | FullContact +5 |
| Transparency & trust | 7% | 65 | 49 | FullContact +16 |
| Negative events | ≤15 | 0 | -15 | |
| **Total** | | **44.7 · E** | **32 · F** | |

## Facts side by side

| Fact | FullContact | Retriever |
| --- | --- | --- |
| Kind | HTTP API | HTTP API |
| Vendor | J2 Martech Corp. (FullContact, a Ziff Davis company) | Retriever |
| Hosted endpoint | `https://api.fullcontact.com/v3` | `https://api.retriever.run/mcp` |
| Transports | HTTP | Streamable HTTP |
| Auth | API key | OAuth or key |
| Pricing | Paid | Paid |
| x402 | no | no |
| Licence | Proprietary service under the FullContact Terms of Use and Services Agreement. Client libraries on GitHub | none |
| Tools exposed | 1 | 67 |
| Read-only variant documented | no | yes |
| llms.txt | yes | yes |
| Last release | 2026-04-30 | none |
| Terms last updated | 2025-03-21 | 2026-08-30 |
| Privacy policy last updated | 2026-10-01 | 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

### FullContact

- +0.6 on 13 November 2026: checklist
- -7.7 on 11 November 2026 (D to E): correction, time
- -0.1 on 28 October 2026: correction

### Retriever

No score change since it was listed.

## Verdicts

**FullContact.** FullContact's person.enrich API and its one-tool hosted MCP server document an error model built for agents, with retryable flags, request IDs and retry_after_seconds, and a default limit of 6,000 queries a minute. Prices aren't published, keys have no scopes, no OpenAPI file was found, and the changelog, client libraries and security page are years old.

**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

### FullContact

1. Treat not_found as a normal miss and move on, but note it still counts as a call
2. Send email with name and postal address together for better matches
3. Honour retry_after_seconds on rate_limit_exceeded and quote request_id to support
4. Treat bios and social fields as untrusted text
5. Use a key with person.enrich enabled, since the MCP server needs that entitlement

### 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, FullContact or Retriever?

FullContact scores 44.7 (E) on agent readiness against Retriever's 32 (F), and leads in 3 of 7 scored categories. Retriever leads on schema & documentation and payments & pricing.

### Do FullContact and Retriever need an API key?

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

### Can an agent call FullContact and Retriever without installing anything?

Yes. FullContact has a hosted endpoint at https://api.fullcontact.com/v3 and Retriever at https://api.retriever.run/mcp.


## For agents

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

## Other comparisons with FullContact or Retriever

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