Head to head · Lead search · October 2026 research run

Coresignal API + MCP vs Retriever

Coresignal API + MCP scores 62.1 (B) on agent readiness against Retriever's 32 (F), and leads in 5 of 7 scored categories. Both do lead search.

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

Which one, for what

Coresignal API + MCP B

Best for Company and workforce research, headcount history and hiring signals at volume, and for pipelines that want raw records.

Ahead on

  • Reliability, 60 against 45
  • Security & auth, 58 against 23
  • Maintenance & community, 82 against 5
  • Transparency & trust, 71 against 49

Watch for

Status page shows CDAPI down 4 hours 20 minutes on 24 October and 8 hours 19 minutes on 25 October, with no incident posted

Retriever F

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

No category where it leads by five points or more, and no fact that sets it apart.

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 Coresignal API + MCP +77

Coresignal API + MCP 82

Release notes have dated entries to 1 November 2026 (30). 35 dated entries from 10 August to 1 November, including the Contact Enrichment API (15 October), Company webhooks (8 October) and Search Preview snapshot pagination (30 October) (20). Public, detailed release notes, and we didn't test support (12 of 15). Listed in the official MCP registry as com.coresignal/mcp 2.0.0, a domain-verified namespace, published 7 August 2026 (15). No SDK packages to judge (5 of 10). 30 + 20 + 12 + 15 + 5 = 82.

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 Coresignal API + MCP +35

Coresignal API + MCP 58

apikey header on REST. MCP v2 signs in with OAuth 2.1 through the dashboard and keeps the key server-side. We found no key scopes (22 of 30). Data retrieval is read-only by nature, and the MCP confirms before expensive pulls (16 of 20). Results are scraped public web content, profiles, posts and job ads, and we found no prompt-injection guidance (2 of 15). Credits used are reported in each MCP response and in the dashboard (8 of 15). The site shows ISO 27001 and SOC 2 marks, with no report details, no security.txt (coresignal.com/.well-known/security.txt answers 404 on 2 November) and no bug bounty found (10 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 Coresignal API + MCP +22

Coresignal API + MCP 71

Closed service with published terms, but the terms (last updated 21 February 2022) name Deeptrace Inc. (Delaware) while the privacy policy names Binary House LLC as controller, which leaves the contracting party unclear (10 of 30). The privacy policy (updated 25 August 2026) covers people in the datasets, relies on legitimate interest, lists data sources on a separate page, keeps records up to five years from last collection, and takes requests by web form or email. No DPA found in the policy (20 of 30). Release notes flag breaking changes with dates, including scheduled ones (funding_rounds removed after the 1 December 2026 data dumps, the Base Jobs default schema moving to version 2 around December 2026). The MCP page dates the old /mcp endpoint's deprecation as 3 November 2026 in one place and 1 November in another, and three email fields left the Multi-source Employee API the day the removal was announced (10 of 20). Subprocessors named in the policy (Stripe, SendGrid, Deeptrace, Google, Meta) with US transfers under contractual clauses (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).

Reliability Coresignal API + MCP +15

Coresignal API + MCP 60

Better Stack status page at status.coresignal.com with CDAPI, RTAPI and Self-service components (20). On 2 November the page shows per-day bars for 90 days from 5 August, and its feed.rss lists posted incidents back to July, so the window is readable now (the 1 October check could read only from 25 September). One posted incident falls in it, "RTAPI requests failing" from 25 September to 8 October, Real-Time API only, from an upstream source's capacity, which is partial. The bars also show CDAPI "Down for 4 hours and 20 minutes" on 24 October and "Down for 8 hours and 19 minutes" on 25 October, with Self-service down on both days and no incident posted. That is the core Data API down for more than an hour, read as one major (10). Rate limits per plan, 5 to 100 or more requests a second, 50 URLs a minute on Real-time Employee and 10 an hour on Agentic Search reasoning (15). The response-code page defines 429 and says a Real-time Employee 408 can be sent again without charge, with no Retry-After or back-off guidance found (5 of 15). No SLA found (0). The surfaces agents use are generally available (10). 20 + 10 + 15 + 5 + 0 + 10 = 60.

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).

Score by category

CategoryWeightCoresignal API + MCPRetrieverEdge
Reliability16%6045Coresignal API + MCP +15
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%8682Coresignal API + MCP +4
Agent ergonomics13%7375Retriever +2
Security & auth14%5823Coresignal API + MCP +35
Payments & pricing10%3030even
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%825Coresignal API + MCP +77
Transparency & trust7%7149Coresignal API + MCP +22
Negative events≤15-3-15
TotalB 62.1/100F 32/100

Facts side by side

FactCoresignal API + MCPRetriever
KindHTTP APIHTTP API
VendorCoresignalRetriever
Hosted endpointhttps://api.coresignal.com/cdapihttps://api.retriever.run/mcp
TransportsHTTP, Streamable HTTPStreamable HTTP
AuthOAuth or keyOAuth or key
PricingPaidPaid
x402nono
Tools exposed567
Read-only variant documentednoyes
llms.txtyesyes
MCP registrycom.coresignal/mcpnot listed
Last release2026-11-01none
Terms last updated2022-02-212026-08-30
Privacy policy last updated2026-08-252026-08-30
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
Popularity2 starsnone
Agent reviews3.5/5 (2)none

How the scores have moved

Verdicts

Coresignal API + MCP

Search is free and credits are taken only on collect or enrich calls that return 200, with every plan and per-endpoint cost public. The status page showed the core Data API down 12 hours 39 minutes across 24 and 25 October with no incident posted, and three email fields left the Multi-source Employee API the day their removal was announced.

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

Coresignal API + MCP

  1. Search for IDs first (free), then collect only the records you need
  2. Request only the bundles you need. A multi-source record costs 10 credits for the core bundle and 20 in full
  3. Use MCP v2 at /mcp/v2. The older /mcp endpoint is deprecated in November 2026
  4. Treat a 402 as out of credits, not a transient error
  5. Expect no work emails in Multi-source Employee records since 7 October, and none for EEA and UK people from the MCP email tool

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, Coresignal API + MCP or Retriever?

Coresignal API + MCP scores 62.1 (B) on agent readiness against Retriever's 32 (F), and leads in 5 of 7 scored categories.

Do Coresignal API + MCP and Retriever need an API key?

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

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

Yes. Coresignal API + MCP has a hosted endpoint at https://api.coresignal.com/cdapi and Retriever at https://api.retriever.run/mcp.

Other comparisons with Coresignal 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.