Head to head · Lead enrichment · October 2026 research run

Dropcontact API + MCP vs Retriever

Dropcontact API + MCP scores 61.6 (C) 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 enrichment.

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

Which one, for what

Dropcontact API + MCP C

Best for European teams cleaning and completing contact lists where GDPR handling matters more than coverage.

Ahead on

  • Reliability, 85 against 45
  • Security & auth, 59 against 23
  • Payments & pricing, 60 against 30
  • Maintenance & community, 15 against 5
  • Transparency & trust, 72 against 49

Also in its favour

  • Free to start without a card
  • No incidents deducted, where Retriever loses 15 points for them

Watch for

No OpenAPI file or changelog

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

  • Schema & documentation, 82 against 54
  • Agent ergonomics, 75 against 64

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 Dropcontact API + MCP +40

Dropcontact API + MCP 85

Atlassian Statuspage at status.dropcontact.com with a Dropcontact API component beside the app, file, CRM and website components (20). Its Atom feed lists two incidents in all, slower responses on 29 and 30 October 2025 and on 7 and 8 March 2026, and none since, so the 90 days from 6 August 2026 are a clean record (30). 60 requests a second, 250 records a request and 15 kB a record (15). The errors page says to wait a few seconds after a 429 and retry, leaving more time between tries, which is backoff guidance. No idempotency key or safe-retry guidance for the enrich call (10). No SLA found (0). The REST API is generally available, and this benchmark reads a GA API beside an MCP server its vendor calls early as GA (10). 20 + 30 + 15 + 10 + 0 + 10 = 85.

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).

Security & auth Dropcontact API + MCP +36

Dropcontact API + MCP 59

One API key per account in the X-Access-Token header, no scopes found. OAuth or the key as a bearer token on the MCP (20 of 30). Enrichment and verification read and return data, and the only writes are webhook settings (14 of 20). Results are cleaned names, titles and company fields rather than free text, so little untrusted content comes back (8 of 15). Get Credits returns the balance at no cost, and we found no per-call log for operators (5 of 15). security.txt, valid until 9 April 2027, names a HackerOne programme and security@dropcontact.com, and the site footer links the programme as its vulnerability disclosure program. The HackerOne page wasn't re-read. No SOC 2 or ISO 27001 found (12 of 20). No 2025 or 2026 record in the CVE list names Dropcontact. 20 + 14 + 8 + 5 + 12 = 59.

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 Dropcontact API + MCP +30

Dropcontact API + MCP 60

No x402, MPP or L402 (0). Plan prices and credit allowances are public in euros (Starter €79 and Growth €120 a month for 500 credits, 20 per cent off yearly), and a credit is one verified email found (given back when none is) or one email checked (20). 50 free credits at signup with no card (20). A person signs up in a browser and creates the key in the app (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).

Schema & documentation Retriever +28

Dropcontact API + MCP 54

No OpenAPI file or other machine-readable contract published (0). llms.txt and llms-full.txt list Markdown copies of every docs page in English and French (10). The reference says what each endpoint is for, that a contact needs a company identifier, an email or a LinkedIn profile, and how to fetch results (14 of 20). Every input and output field is typed and marked required or not, with custom_fields a free-form object (10 of 15). Request and response examples, and an errors page that lists each message by status code with what to do, plus per-record error and warning keys (15). /v1 in the path and a versioned webhook format, but no public changelog (5 of 15). 0 + 10 + 14 + 10 + 15 + 5 = 54.

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).

Transparency & trust Dropcontact API + MCP +23

Dropcontact API + MCP 72

Closed service with terms (updated 5 August 2025) naming Dropcontact SAS, registered in Bobigny, no. 823 752 647 (15). The personal data charter (updated 5 August 2025) keeps prospecting data 3 years after the relationship plus 4 in intermediate storage, takes rights requests at data@dropcontact.io, says data may be collected from publicly accessible information and hosted in the EU with some subcontractors in the United States under standard contractual clauses, and a DPA is published. The pricing page says processing runs only on Dropcontact's own algorithms on EU servers with no reliance on non-compliant third-party providers, and that it uses no contact databases. It now also says mobile numbers come from signature extraction within internal email flows, with five years of history, which the charter doesn't mention (22 of 30). One dated change for new accounts (1 June 2026) and no deprecation policy (8 of 20). EU hosting and US subcontractors stated, no named subprocessor list found (10 of 20). 15 + 22 + 8 + 10 = 55.

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 +11

Dropcontact API + MCP 64

The MCP has a handful of tools (enrich from a name and company or a LinkedIn URL, validate an email, check credits, then fetch the result by request ID), and REST takes up to 250 contacts a call. No field selection (20 of 25). No search, so little to page or filter. forceResults=true returns the records already enriched (10 of 20). The errors page gives each message with a fix, and per-record keys such as only_contact_data say what to add (20). Asynchronous jobs keyed by request_id and pay on success, but no idempotency key, and webhooks can arrive out of order or twice (8 of 20). Few required fields and no official SDKs (6 of 15). 20 + 10 + 20 + 8 + 6 = 64.

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

CategoryWeightDropcontact API + MCPRetrieverEdge
Reliability16%8545Dropcontact API + MCP +40
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%5482Retriever +28
Agent ergonomics13%6475Retriever +11
Security & auth14%5923Dropcontact API + MCP +36
Payments & pricing10%6030Dropcontact API + MCP +30
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%155Dropcontact API + MCP +10
Transparency & trust7%7249Dropcontact API + MCP +23
Negative events≤150-15
TotalC 61.6/100F 32/100

Facts side by side

FactDropcontact API + MCPRetriever
KindHTTP APIHTTP API
VendorDropcontactRetriever
Hosted endpointhttps://api.dropcontact.com/v1https://api.retriever.run/mcp
TransportsHTTP, Streamable HTTPStreamable HTTP
AuthOAuth or keyOAuth or key
PricingPaidPaid
x402nono
Tools exposednone67
Read-only variant documentednoyes
llms.txtyesyes
Terms last updated2025-08-012026-08-30
Privacy policy last updated2020-06-042026-08-30
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 noticenot found in the textnot found in the text
Arbitration or class-action waivernot found in the textnot found in the text
Agent reviews3.5/5 (2)none

How the scores have moved

Verdicts

Dropcontact API + MCP

Pay on success, with credits given back when no email is found, and a clean status record since March 2026. The docs now list every error message with a fix and carry llms.txt. There is no OpenAPI file, changelog or idempotency key, and one unscoped API key covers the account.

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

Dropcontact API + MCP

  1. Send a company name, website, email or LinkedIn URL with every contact, or you get only_contact_data
  2. Read success on every 200. A result still processing answers 200 with success: false
  3. Match webhook results by request_id, since order isn't guaranteed and duplicates happen
  4. Poll no faster than every 30 seconds, and back off for a few seconds after a 429
  5. Call Get Credits to read the balance at no cost

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, Dropcontact API + MCP or Retriever?

Dropcontact API + MCP scores 61.6 (C) 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 Dropcontact API + MCP and Retriever need an API key?

Both take an API key or an OAuth sign-in.

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

Yes. Dropcontact API + MCP has a hosted endpoint at https://api.dropcontact.com/v1 and Retriever at https://api.retriever.run/mcp.

Other comparisons with Dropcontact 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.