The GTM MCP Directory
Directory / Data & Enrichment / Dropcontact

Dropcontact

Official MCP Paid, self-serve Data & Enrichment RESEARCHED Checked 2026-09-07
RESEARCHED Facts from public sources with URLs. No usage claims. Nobody has run this tool. The other tier is BENCH-TESTED, which means Andrew personally ran the tool on a stated date and cannot be bought at any price. Across the whole directory that count is 1.

Vendor: dropcontact.com · entry id 01-dropcontact · source 01-data-enrichment.md line 236

What it does
A France-based, GDPR-oriented contact enrichment and email-finding/verification service that takes a name plus company (name, domain, or LinkedIn URL) and returns a verified professional email plus cleaned company data, with batch processing of up to 250 contacts at once.
AI features, separated from automation with an AI label on it
No strong AI claims found; the vendor's own positioning centers on "triple verification" and data-matching/deduplication logic rather than AI/ML. Treat as automation and rules-based verification, not AI-branded.
RevOps role
GDPR-conscious contact enrichment/verification layer for CRM hygiene and list-building; also a widely-used Clay waterfall step (Clay-managed account billed at 2 credits/enriched cell, with a 24h auto-update toggle).
MCP server
Status bucket
Official MCP
Auth
Hosted server at mcp.dropcontact.com/mcp/, supporting OAuth (recommended, browser-based) or a Dropcontact API token/key passed via headers; also usable through the npx mcp-remote bridge for clients without native remote-MCP support
Parsed URLs
2 found in the mcp_url field
Endpoint probe
docs page, not an endpoint
Probed
2026-09-04, HTTP 200

The vendor ships and maintains the server itself. A wrapper built by Zapier, Composio or a similar third party does not count as official. The status was established by hand on 2026-09-07. On 2026-09-04 the recorded URL served a documentation page, not an MCP endpoint. That is where to read about the server, not where to connect to it. An agent needs the second.

mcp_status, verbatim from the file:

official

mcp_url, verbatim from the file:

https://mcp.dropcontact.com/mcp ; https://www.dropcontact.com/mcp-dropcontact

What this server exposes

Not harvested yet. Unmeasured, not empty: nobody has read this server's tool list, so this page says nothing about what it exposes.

141 of the 741 entries that record an official or community MCP server carry a harvested tool list. The other 600 are unmeasured, which is not the same as empty. Harvest last run 2026-09-27. The full roll up is on the tools index.

Command line

No CLI found by the 2026-09-27 harvest across vendor docs, npm, PyPI, Homebrew and GitHub. That is a probe result, not proof of absence.

Access gate
Gate bucket
Paid, self-serve
Can a solo operator reach it
Yes, by paying, no sales call

api_gate, verbatim from the file:

paid

API documentation

No documentation URL recorded.

727 of 1252 entries are in the same position. Blank is legal and it is published as blank.

GitHub health

Not measured. github_url, github_stars, github_last_commit and github_archived are null on every entry in this build.

The refresh rail specced in SPEC section 7.2 has not been run. An unstamped star count is a lie, so nothing is shown rather than something stale.

On GitHub

No GitHub organisation could be tied to dropcontact.com with evidence on 2026-09-08.

Recorded by the harvest: github candidates were seen but none passed the evidence rules.

1 candidate account seen and rejected by the evidence rules: dropcontact-d. A name match alone is never accepted; the account has to point at the vendor domain.

Jobs it can do

A job tag means the vendor says the tool does this. It is not a test result, not proof the capability is reachable through the tool's MCP server, and not proof it is available on the gate this entry records.

Tagged by machine-pass on 2026-08-25 against the closed 56 job vocabulary. 271 of 1,252 entries carry at least one tag; 849 tags are assigned in total.

Sources

9 source URLs. Raw sources field, verbatim:

https://www.dropcontact.com/mcp-dropcontact, https://developer.dropcontact.com, https://www.dropcontact.com/pricing, https://www.clay.com/integrations/data-provider/dropcontact, https://university.clay.com/docs/dropcontact-integration-overview, https://www.dropcontact.com/help/clay-integration, https://support.dropcontact.com/article/237-how-to-use-the-dropcontact-api-key, https://developer.dropcontact.com/, https://mcp.dropcontact.com/mcp

Notes, verbatim from the file
Dropcontact is a clear "official, vendor-built" MCP - it has its own product page and a centrally hosted MCP endpoint at mcp.dropcontact.com, distinct from (and in addition to) its long-standing Clay data-provider integration. API & MCP access is bundled starting at the Starter tier (EUR 79/mo, ~500 credits/mo) and up; there is no persistent free API tier, only a "50 free emails" signup incentive. Pricing model is pay-on-success (1 credit = 1 email found or verified; credit refunded if nothing found). Lower tiers reportedly throttle API requests to ~100/min, which can bottleneck heavy Clay/n8n automation. 2026-09-03: vendor docs state the enrich endpoint (POST /v1/enrich/all) accepts "first_name + last_name + company (or full_name + company)" and its response includes a linkedin field with a linkedin.com/in/ example (https://developer.dropcontact.com/); no MCP tool name is stated there; the docs state a credit is charged only if a verified email is returned. 2026-09-07: https://mcp.dropcontact.com/mcp returned 401 with {"error": "invalid_token", "error_description": "Authentication failed. The provided bearer token is invalid..."} to an MCP initialize POST (https://mcp.dropcontact.com/mcp).
Provenance
Entry id
01-dropcontact
Source file
01-data-enrichment.md
Source line
236
Tier
RESEARCHED
last_checked
2026-09-07
Data baked
2026-09-27

Every field above is rendered from directory.json exactly as the build produced it. Nothing is summarised and nothing is dropped. The one change made at render time is typographic and it is disclosed on the methodology page.