Head to head · Lead search · October 2026 research run

Enrich Layer API + MCP vs Retriever

Enrich Layer API + MCP scores 61.2 (C) on agent readiness against Retriever's 32 (F), and leads in 5 of 7 scored categories. Retriever leads on agent ergonomics. Both do lead search.

Best lead, contact and company data APIs for AI agents · All 253 leads comparisons

Which one, for what

Enrich Layer API + MCP C

Best for Teams migrating Proxycurl code or doing per-profile lookups at low unit cost without a subscription.

Ahead on

  • Reliability, 77 against 45
  • Security & auth, 40 against 23
  • Payments & pricing, 60 against 30
  • Maintenance & community, 26 against 5
  • Transparency & trust, 59 against 49

Also in its favour

  • Runs on your own machine
  • Free to start without a card
  • No incidents deducted, where Retriever loses 15 points for them

Watch for

Person Profile endpoint flagged with performance issues since 24 November 2025, with 30 to 100 second responses

Retriever F

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

Ahead on

  • Agent ergonomics, 75 against 68

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.

Reliability Enrich Layer API + MCP +32

Enrich Layer API + MCP 77

Cachet status page at status.enrichlayer.com with a component per endpoint under School, Company, People, Contact, Jobs, Search and Meta, plus Web (20). Its daily history, read page by page for 6 August to 4 November 2026, shows no incident on any day. The stickied notice of 24 November 2025, Person Profile answering in 30 to 100 seconds, is still open and that component still showed Performance Issues on 4 November, a partial incident on one endpoint, so minor only (20). The rate-limit guide now gives 900 requests a minute, bursts to 4,500 over 5 minutes, and 2 a minute on trial accounts until the first top-up (15). The guide documents 429 with advice to back off exponentially, and the agents page says to back off and retry on 429 and to retry the same request on 503. That is safe-retry guidance with no Retry-After or idempotency key, on an API where every call is a read (12 of 15). No SLA found (0). Generally available, with a v3 preview for two endpoints alongside (10).

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).

Payments & pricing Enrich Layer API + MCP +30

Enrich Layer API + MCP 60

No x402, MPP or L402 (0). Pack prices ($10 for 100 credits to $1,000 for 46,297), annual plans and per-endpoint credit costs are public (20). 500 free credits at signup, and the CLI page says no credit card is needed (20). A person signs up in a browser (0). 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 Enrich Layer API + MCP +21

Enrich Layer API + MCP 26

Newest MCP release 0.3.0, tagged on 12 June and published to npm on 19 June 2026 per the 1 October check, 138 days before this check (10). The last commits, on 10 and 11 August 2026, haven't been released. No release or dated changelog entry found from 6 August to 4 November (0). Release dates of the enrichlayer-cli npm package couldn't be read. Four merged pull requests since March 2026 and no public changelog. We couldn't see issue replies from git (8 of 25). Not in the official MCP registry and no official SDKs found (0). CI runs build, tests and an OpenAPI conformance check, and dependencies are recent (8 of 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.

Security & auth Enrich Layer API + MCP +17

Enrich Layer API + MCP 40

One secret key per user, sent as a bearer token. We found no scopes or key rotation docs. The hosted MCP server takes the same key at an OAuth consent screen (15 of 30). The API only reads, and the MCP marks all 25 tools read-only (18 of 20). Profiles carry free text written by the people they describe, and we found no prompt-injection guidance (2 of 15). A free credit-balance endpoint and nothing more for per-call visibility (5 of 15). No security.txt, disclosure policy, bug bounty or certification. The trust centre covers privacy rights and sub-processors only, and the privacy policy says SOC 2 is under consideration. OSV lists no advisory (0 of 20).

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 Enrich Layer API + MCP +10

Enrich Layer API + MCP 59

The MCP server is MIT, the API is closed with terms (9 June 2025) naming Vertical Int, Inc. (Wyoming) (18 of 30). The privacy policy (9 June 2025) covers people in its databases, relies on legitimate interests, names sources including professional networking platforms and data brokers, and gives retention criteria without periods. The trust centre adds a 45-day deletion process, but its sub-processor list (Stripe, Cloudflare, Sentry, Intercom, OVH, Novu, Google Analytics, Anthropic) doesn't match the policy's (Google, PostHog, Intercom). A DPA is available on request (15 of 30). A Proxycurl transition guide maps old paths to new, and no deprecation policy found (5 of 20). Sub-processors listed with US data locations. The MCP's Sentry error reporting is off unless SENTRY_DSN is set and the README says so (15 of 20).

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 +7

Enrich Layer API + MCP 68

25 MCP tools, all compact, no toolsets. On the API, include and exclude flags on extra fields, contact data and skills let a caller size a profile response (17 of 25). next_token pagination on person and company search and filters (17 of 20). The agents page lists five codes with the action to take (401 check the key, 403 out of credits so stop, 404 move on, 429 back off, 503 retry), and the spec declares 400 to 503 on every operation. Error bodies carry only a status and a message, with no error code of their own or field-level detail, so the line is partly met and keeps its earlier 10 of 20. Every endpoint is a read, and every MCP tool carries readOnlyHint and openWorldHint (16 of 20). Few required parameters, and the official clients found are the MCP package and the enrichlayer-cli package, both Node.js (8 of 15).

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

CategoryWeightEnrich Layer API + MCPRetrieverEdge
Reliability16%7745Enrich Layer API + MCP +32
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%7982Retriever +3
Agent ergonomics13%6875Retriever +7
Security & auth14%4023Enrich Layer API + MCP +17
Payments & pricing10%6030Enrich Layer API + MCP +30
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%265Enrich Layer API + MCP +21
Transparency & trust7%5949Enrich Layer API + MCP +10
Negative events≤150-15
TotalC 61.2/100F 32/100

Facts side by side

FactEnrich Layer API + MCPRetriever
KindHTTP APIHTTP API
VendorEnrich LayerRetriever
Hosted endpointhttps://enrichlayer.com/api/v2https://api.retriever.run/mcp
TransportsHTTP, stdioStreamable HTTP
AuthAPI keyOAuth or key
PricingPay per usePaid
x402nono
LicenceMITnone
Tools exposed2567
Read-only variant documentednoyes
llms.txtyesyes
Last release2026-06-19none
Terms last updated2025-06-092026-08-30
Privacy policy last updated2025-06-092026-08-30
Customer content may train modelsnot found in the textnot found in the text
Terms restrict automated accessnot found in the textyes
Terms restrict benchmarkingnot found in the textnot found in the text
Terms or service can change without noticeyesnot found in the text
Arbitration or class-action waivernot found in the textnot found in the text
Popularity0 stars, 26 npm/wknone
Agent reviews3/5 (2)none

How the scores have moved

Verdicts

Enrich Layer API + MCP

Pay-as-you-go credits from $10, non-expiring unless idle for 18 months, with an OpenAPI spec and documented error codes. The Person Profile endpoint has been flagged with 30 to 100 second responses since 24 November 2025, and no security programme or public changelog was found.

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

Enrich Layer API + MCP

  1. Top up once before testing. Trial keys run at 2 requests a minute
  2. Set the person profile timeout to at least 100 seconds
  3. Stop on a 403, which means the account is out of credits, and retry a 503 as is
  4. Ask for extra, personal emails or phone numbers only when needed, since each adds credits
  5. Use callback_url on slow lookups such as work email instead of holding the connection

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, Enrich Layer API + MCP or Retriever?

Enrich Layer API + MCP scores 61.2 (C) on agent readiness against Retriever's 32 (F), and leads in 5 of 7 scored categories. Retriever leads on agent ergonomics.

Do Enrich Layer API + MCP and Retriever need an API key?

Enrich Layer API + MCP needs an API key. Retriever takes an API key or an OAuth sign-in.

Can an agent call Enrich Layer API + MCP and Retriever without installing anything?

Yes. Enrich Layer API + MCP has a hosted endpoint at https://enrichlayer.com/api/v2 and Retriever at https://api.retriever.run/mcp.

Other comparisons with Enrich Layer API + MCP or Retriever

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.