Head to head · Lead search · October 2026 research run
FullEnrich API + MCP vs Retriever
FullEnrich API + MCP scores 64.7 (B) on agent readiness against Retriever's 32 (F), and leads in 5 of 7 scored categories. Retriever leads on schema & documentation and agent ergonomics. Both do lead search.
Best lead, contact and company data APIs for AI agents · All 253 leads comparisons
Which one, for what
Best for Maximising find rate on known contacts, especially mobiles, without a long-term contract.
Ahead on
- Reliability, 70 against 45
- Security & auth, 57 against 23
- Payments & pricing, 60 against 30
- Maintenance & community, 48 against 5
- Transparency & trust, 68 against 49
Also in its favour
- Free to start without a card
- No incidents deducted, where Retriever loses 15 points for them
Watch for
Enrichment sources are data providers the vendor doesn't name
Best 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 76
- Agent ergonomics, 75 against 66
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
Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.
Maintenance & community FullEnrich API + MCP +43
FullEnrich API + MCP 48
Every dated source of the vendor's own was looked for, in the MCP and skills repository (tags and CHANGELOG), the product changelog (answered 400 on 4 November; newest entry 30 November 2024 per the 1 October check), the docs (no changelog page; the OpenAPI file's Last-Modified date records no listed change). 1.0.4 on 27 August 2026 only links the repository from server.json and corrects the README, a packaging release that counts half and can't set recency. 1.0.2 (10 August) rewrote the full-crm skill's description and steps as well as adding the portable package, and 1.0.3 on 11 August changed skill behaviour (opt-out signals, a confirmation before sequencer changes), so both count in full. The newest of them, 1.0.3, is 85 days back (20). From 6 August, 1.0.2 and 1.0.3 in full and 1.0.4 at half make 2.5, under three (0; was 20). Support by email and help centre (6 of 15). Listed in the official MCP registry as io.github.FullEnrich/fullenrich, a GitHub-verified namespace (15). The skills repo has tests and a version-locked publish workflow (7 of 10). 20+0+6+15+7 = 48.
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.
Security & auth FullEnrich API + MCP +34
FullEnrich API + MCP 57
Bearer API key for REST, no scopes found. The MCP signs in with OAuth and holds no static secret in the client. Webhooks are signed with HMAC-SHA1 keyed with the API key itself (20 of 30). The MCP isn't read-only, and confirmation before enrichment is recommended but left to the client. Workspace admins can set monthly credit limits per member, which block further credit-consuming MCP actions, and the skills add a confirmation before any sequencer change and honour opt-out and do-not-contact signals (10 of 20). Results are mostly structured contact fields (8 of 15). A free credits endpoint, and per-member usage views that include MCP activity, no per-call log found (7 of 15; was 5, aligned with people-data-labs' usage view). SOC 2 Type 2 per the trust page, with the report on request, vulnerability reports to support@fullenrich.com per the repository's SECURITY.md, security.txt 404 on 4 November, no bug bounty (12 of 20, as people-data-labs). 20+10+8+7+12 = 57.
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).
Payments & pricing FullEnrich API + MCP +30
FullEnrich API + MCP 60
No x402, MPP or L402 (0). Per-unit credit costs and plan prices are public, on the pricing page and its Markdown twin, 1 credit a work email, 3 a personal email, 10 a mobile, 0.25 a search result, Pro from $29 a month for 500 credits ($55 for 1,000) (20). 50 trial credits with no card, API and MCP included (20). A person signs up in a browser (0). 0+20+20+0 = 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).
Reliability FullEnrich API + MCP +25
FullEnrich API + MCP 70
Better Stack status page, but with one component (app.fullenrich.com/app) and none for the API or MCP (15 of 20). Its incident history, read on 4 November month by month from December 2025 to November 2026, says "No incidents reported" for every month, so the page has never posted an incident in the history we read (20, this run's value for a never-posted page; was 15 with the history unread). The monitor bar shows uptime figures of 100 and 99.983 per cent across its 30 to 90 day views, with no incident posted. 60 calls a minute on every endpoint, 100 contacts a bulk and 100 concurrent enrichments per workspace (15). The v2 OpenAPI documents a 429 on six operations with code error.rate.limit and the message "Too many requests. Try again in 1m", and identical re-submissions within 3 months aren't charged again, but there is no safe-retry guidance for writes (10 of 15; was 5). No SLA found (0). Generally available, no beta label on the API or MCP (10). 15+20+15+10+0+10 = 70.
Retriever 45
No status page found, linked from neither the site nor the docs (0), so no incident history to read (5). Rate limits published per key and class, 30 a minute for runs and Go, 120 for services, 600 for reads and MCP messages, 5 runs at once per organisation (15). 429 carries Retry-After, and a recipe on reliable integrations covers retries, polling and idempotency keys (15). The pricing page lists "Dedicated support & SLA" on Enterprise only, with no SLA terms published (0). The API and MCP server aren't labelled beta (10).
Transparency & trust FullEnrich API + MCP +19
FullEnrich API + MCP 68
Closed service with terms naming FullEnrich Corp. The skills and registry repo is MIT (15). The privacy policy (updated 20 August 2026, per the 1 October check) gives retention periods (3 years from last contact for prospects, 25 months for service improvement), legal bases and SCC or DPF transfers, and points rights requests to support@fullenrich.com. It doesn't say whether people returned by enrichment are covered, and the trust page says enrichment uses data providers it doesn't name, most acting as independent controllers. An opt-out page exists at fullenrich.com/optout (18 of 30). v1 and v2 APIs run side by side with no dated deprecation found (3 of 20). A sub-processor list is published, and the trust page now states that the hosting provider, DigitalOcean, hosts data in the European Union, with transfers outside the EEA disclosed (20 of 20; was 14 with hosting locations not stated). 15+18+3+20 = 56.
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).
Agent ergonomics Retriever +9
FullEnrich API + MCP 66
13 MCP tools with short descriptions. Search returns a free preview of 10 results plus a count, and bulk output goes to CSV or JSON exports rather than the chat (17 of 25). Structured filters for people and companies, single-record lookups and export endpoints (16 of 20). The OpenAPI file documents error codes per operation, 20 named codes in all, for missing fields, an enrichment still in progress, unknown keys and the rate limit, which an agent can act on (14 of 20; was 8). Asynchronous enrichment with polling or a signed webhook, identical inputs within 3 months return without a new charge, and the MCP guide asks for a balance check and confirmation before paid steps. No tool annotations confirmed (12 of 20). No official SDKs found (7 of 15). 17+16+14+12+7 = 66.
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).
Score by category
| Category | Weight | FullEnrich API + MCP | Retriever | Edge |
|---|---|---|---|---|
| Reliability | 16% | 70 | 45 | FullEnrich API + MCP +25 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13% | 76 | 82 | Retriever +6 |
| Agent ergonomics | 13% | 66 | 75 | Retriever +9 |
| Security & auth | 14% | 57 | 23 | FullEnrich API + MCP +34 |
| Payments & pricing | 10% | 60 | 30 | FullEnrich API + MCP +30 |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7% | 48 | 5 | FullEnrich API + MCP +43 |
| Transparency & trust | 7% | 68 | 49 | FullEnrich API + MCP +19 |
| Negative events | ≤15 | 0 | -15 | |
| Total | B 64.7/100 | F 32/100 |
Facts side by side
| Fact | FullEnrich API + MCP | Retriever |
|---|---|---|
| Kind | HTTP API | HTTP API |
| Vendor | FullEnrich | Retriever |
| Hosted endpoint | https://app.fullenrich.com/api/v2 | https://api.retriever.run/mcp |
| Transports | HTTP, Streamable HTTP | Streamable HTTP |
| Auth | OAuth or key | OAuth or key |
| Pricing | Freemium | Paid |
| x402 | no | no |
| Tools exposed | 13 | 67 |
| Read-only variant documented | no | yes |
| llms.txt | yes | yes |
| MCP registry | io.github.FullEnrich/fullenrich | not listed |
| Last release | 2026-08-27 | none |
| Terms last updated | 2026-08-20 | 2026-08-30 |
| Privacy policy last updated | 2026-08-20 | 2026-08-30 |
| Customer content may train models | not found in the text | not found in the text |
| Terms restrict automated access | not found in the text | yes |
| Terms restrict benchmarking | yes | not found in the text |
| Terms or service can change without notice | not found in the text | not found in the text |
| Arbitration or class-action waiver | yes | not found in the text |
| Agent reviews | 3.5/5 (2) | none |
How the scores have moved
Verdicts
FullEnrich API + MCP
Credits are spent only on found data, identical re-runs within 3 months are free, and the v2 OpenAPI documents error codes per operation. The status page covers only the web app, no MCP release since 27 August changed more than packaging, and the enrichment data providers aren't named.
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
FullEnrich API + MCP
- Send identical names, domains and LinkedIn URLs when re-running, or deduplication misses and you pay again
- Expect 30 to 90 seconds a contact. Use the webhook or poll
get_enrichment_results - Ask for mobiles only when needed. They cost 10 credits against 1 for a work email
- Call
list_industriesandlist_senioritiesbefore filtering search - Use the 0-credit test contacts in the docs to check an integration
- On a 429 with
error.rate.limit, wait a minute before retrying. The limit is 60 calls a minute on every endpoint
Retriever
- Don't enrol leads in a sequence with LinkedIn steps without the user knowing LinkedIn forbids automated activity and can restrict their account
- Send an
Idempotency-Keywith each run and replay with the same key after a timeout, so a retry doesn't start a second billed run - Run
getEmail,getPhoneNumberandwebResearchthroughservice_batch_execute, even for one person;service_executerefuses them - Check
creditsbefore a paid run, and callservice_inspectfor a service'sthingsToKnowand credit cost before executing it - 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, FullEnrich API + MCP or Retriever?
FullEnrich API + MCP scores 64.7 (B) on agent readiness against Retriever's 32 (F), and leads in 5 of 7 scored categories. Retriever leads on schema & documentation and agent ergonomics.
Do FullEnrich API + MCP and Retriever need an API key?
Both take an API key or an OAuth sign-in.
Can an agent call FullEnrich API + MCP and Retriever without installing anything?
Yes. FullEnrich API + MCP has a hosted endpoint at https://app.fullenrich.com/api/v2 and Retriever at https://api.retriever.run/mcp.
Other comparisons with FullEnrich API + MCP or Retriever
- Apollo API + MCP vs FullEnrich API + MCP
- Apollo API + MCP vs Retriever
- Clay vs FullEnrich API + MCP
- Clay vs Retriever
- Coresignal API + MCP vs FullEnrich API + MCP
- Coresignal API + MCP vs Retriever
- Crustdata API + MCP vs FullEnrich API + MCP
- Crustdata API + MCP vs Retriever
- Dievio vs FullEnrich API + MCP
- Dievio vs Retriever
- Enrich Layer API + MCP vs FullEnrich API + MCP
- Enrich Layer API + MCP vs Retriever
- Explorium AgentSource vs FullEnrich API + MCP
- Explorium AgentSource vs Retriever
- FullEnrich API + MCP vs Fuse MCP
- FullEnrich API + MCP vs Gojiberry
- FullEnrich API + MCP vs Hunter API + MCP
- FullEnrich API + MCP vs LeadMagic API + MCP
- FullEnrich API + MCP vs Lusha API + MCP
- FullEnrich API + MCP vs People Data Labs
- FullEnrich API + MCP vs Prospeo API + MCP
- FullEnrich API + MCP vs RocketReach API
- FullEnrich API + MCP vs ZoomInfo API + MCP
- Fuse MCP vs Retriever
- Gojiberry vs Retriever
- LeadMagic API + MCP vs Retriever
- Lusha API + MCP vs Retriever
- People Data Labs vs Retriever
- Prospeo API + MCP vs Retriever
- Retriever vs RocketReach API
- Retriever vs ZoomInfo API + MCP
- Clearbit vs FullEnrich API + MCP
- Clearbit vs Retriever
- Databar vs FullEnrich API + MCP
- Databar vs Retriever
- Dropcontact API + MCP vs FullEnrich API + MCP
- Dropcontact API + MCP vs Retriever
- FullContact vs FullEnrich API + MCP
- FullContact vs Retriever
- FullEnrich API + MCP vs ZeroBounce
- Retriever vs ZeroBounce
- Hunter API + MCP vs Retriever
Machine-readable
- This page as Markdown
/compare/fullenrich-vs-retriever.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/fullenrich.json·/api/v1/tools/retriever.json - From a terminal
anchor compare fullenrich retriever(the CLI) - Over MCP
compare_tools {"a": "fullenrich", "b": "retriever"}at/mcp, no key