Back to Browse

V3 MCP Server

Developer ToolsLow Risk10.0MCP RegistryLocal
Free

Server data from the Official MCP Registry

Person and company profiles, company search and logos, work emails and email checks

About

Person and company profiles, company search and logos, work emails and email checks

Security Report

10.0
Low Risk10.0Low Risk

Valid MCP server (3 strong, 3 medium validity signals). No known CVEs in dependencies. Package registry verified. Imported from the Official MCP Registry.

12 files analyzed · 1 issue found

Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.

Permissions Required

This plugin requests these system permissions. Most are normal for its category.

HTTP Network Access

Connects to external APIs or services over the internet.

file_system

Check that this permission is expected for this type of plugin.

env_vars

Check that this permission is expected for this type of plugin.

What You'll Need

Set these up before or after installing:

Enrich Layer API key from enrichlayer.com/dashboardRequired

Environment variable: ENRICHLAYER_API_KEY

How to Install

Add this to your MCP configuration file:

{
  "mcpServers": {
    "mcp-server-v3": {
      "command": "npx",
      "args": [
        "-y",
        "@enrichlayer/mcp-server-v3@0.2.2"
      ],
      "env": {
        "ENRICHLAYER_API_KEY": "your-enrichlayer-api-key-here"
      }
    }
  }
}

Some servers take additional arguments. See the repository for details.

Documentation

View on GitHub

From the project's GitHub README.

Enrich Layer v3 MCP server

An MCP server for the Enrich Layer v3 API on api.enrichlayer.com. It gives an AI agent six tools: person and company profiles, company search, company logos, work email search and email validation.

This is a separate server from the v2 one (@enrichlayer/mcp-server), which keeps working as before.

Requirements

  • Node.js 20.3 or later.
  • An Enrich Layer API key.

API key, account and credits

  • Get a key: log in at enrichlayer.com/dashboard, open the API Key tab and copy the key.
  • Whose credits: the server works under the account whose key is set in ENRICHLAYER_API_KEY. Every successful call is charged to that account; the result shows the credits charged in creditCost. Calls that end in an error are not charged.
  • A separate account for an agent: a person creates an Enrich Layer account on the website, tops it up, copies its API key and puts the key into the agent's MCP config. The person owns the account and its credits.
  • Rate limit: the limit is counted per account. New accounts have a very small limit until their first payment.

Install

Most clients keep the key in their config file, so keep that file private. VS Code asks for the key instead and stores it for you.

Cursor

Add Enrich Layer v3 to Cursor

The button opens Cursor's install link (cursor://anysphere.cursor-deeplink/mcp/install?...). The link carries no key: after the server is added, replace <your API key> with your key in Cursor's MCP settings.

To add it by hand, put this block into ~/.cursor/mcp.json (all projects) or .cursor/mcp.json (one project):

{
  "mcpServers": {
    "enrichlayer-v3": {
      "command": "npx",
      "args": ["-y", "@enrichlayer/mcp-server-v3"],
      "env": { "ENRICHLAYER_API_KEY": "<your API key>" }
    }
  }
}

VS Code

Install Enrich Layer v3 in VS Code

The link opens VS Code's install link (vscode:mcp/install?...). VS Code asks for the API key when the server first starts.

To add it by hand, put this into .vscode/mcp.json in the workspace, or into the MCP configuration of your user profile:

{
  "inputs": [
    { "type": "promptString", "id": "enrichlayer-api-key", "description": "Enrich Layer API key", "password": true }
  ],
  "servers": {
    "enrichlayer-v3": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@enrichlayer/mcp-server-v3"],
      "env": { "ENRICHLAYER_API_KEY": "${input:enrichlayer-api-key}" }
    }
  }
}

Claude Desktop

Edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows) and add the same mcpServers block as for Cursor. Quit and reopen Claude Desktop. Server logs are in ~/Library/Logs/Claude/mcp-server-enrichlayer-v3.log on macOS.

Claude Code

claude mcp add --env ENRICHLAYER_API_KEY=<your API key> --transport stdio enrichlayer-v3 -- npx -y @enrichlayer/mcp-server-v3

Codex

codex mcp add enrichlayer-v3 --env ENRICHLAYER_API_KEY=<your API key> -- npx -y @enrichlayer/mcp-server-v3

Codex stops a tool call after 60 seconds by default. Raise the limit in ~/.codex/config.toml:

[mcp_servers.enrichlayer-v3]
command = "npx"
args = ["-y", "@enrichlayer/mcp-server-v3"]
env = { ENRICHLAYER_API_KEY = "<your API key>" }
tool_timeout_sec = 310

Windsurf

Add the same mcpServers block as for Cursor to the MCP config file named in the Windsurf MCP docs: ~/.config/devin/mcp_config.json on macOS and Linux, %AppData%/devin/mcp_config.json on Windows. Cascade opens this file with its "Open MCP config file" action. Instead of the key itself you can write ${env:ENRICHLAYER_API_KEY} there and keep the key in your environment.

Antigravity

Open the … menu of the agent panel → MCP Servers → Manage MCP Servers → View raw config, or edit ~/.gemini/config/mcp_config.json (.agents/mcp_config.json for one workspace). Add the same mcpServers block as for Cursor, with a longer tool call limit — Antigravity's default is 180 seconds:

{
  "mcpServers": {
    "enrichlayer-v3": {
      "command": "npx",
      "args": ["-y", "@enrichlayer/mcp-server-v3"],
      "env": { "ENRICHLAYER_API_KEY": "<your API key>" },
      "timeoutSeconds": 310
    }
  }
}

Tools

Toolv3 endpointWhat it does
get_person_profileGET /v3/personOne person by exactly one identifier: profile (LinkedIn URL or username), email, twitter, facebook or github. Optional sections: socialLink, phoneNumber, personalEmail, workEmail, careerInsight, developerProfile, activities.
get_company_profileGET /v3/companyOne company by its LinkedIn company or showcase page url. Optional sections: fundingData, exitData, acquisitions, extra, activities.
search_companiesGET /v3/company/searchCompanies matching a name (q), up to 10.
search_company_logosGET /v3/company/logoCompanies matching a name or domain (q), with logo URLs.
find_work_emailsGET /v3/email/prospectWork email candidates for full_name, or first_name and/or last_name, at a company domain.
validate_emailGET /v3/email/validateWhether one email address is deliverable.

The input schemas are generated from the published v3 OpenAPI spec, so parameter names and allowed values are the ones v3 accepts.

Ask only for the sections you need. A full person profile can be long: Claude Code warns above 10,000 tokens of tool output and cuts it at 25,000 by default (raise MAX_MCP_OUTPUT_TOKENS if you need more).

Email addresses

  • get_person_profile with personalEmail or workEmail returns only addresses validated as deliverable. To find someone's work email from a profile URL, pass profile and workEmail: "include"; if contactInformation.emails.work is empty, find_work_emails with the person's name and company domain may still find candidates.
  • find_work_emails returns candidates, each with a validation verdict in validity; only valid is confirmed deliverable.
  • validate_email returns the verdict in emailStatus.

What a call returns

  • data — the full v3 answer, unchanged.
  • creditCost — credits charged for the call, from the X-EnrichLayer-Credit-Cost header.
  • requestId — the X-Request-Id of the call; quote it to support.

The result comes as MCP structured content and as the same JSON in a text block.

Errors come back as tool errors with a readable message, creditCost, requestId and the next step to take: invalid parameters (400), an invalid or missing key (401), not enough credits or no access (403), not found (404), no copy fresh enough (409, with the age of the newest cached copy), rate limit (429) and service errors (5xx). The server retries 429 and 5xx twice before it reports them.

Freshness and long calls

get_person_profile and get_company_profile take maxAgeSeconds: the oldest cached copy you accept. By default it is 30 days, and the answer usually comes in seconds. A small value starts a live lookup, which is slower and costs more: it can take up to 5 minutes, and the server waits about 300 seconds for the answer.

MCP clients limit how long a tool call may run. Set the limit to at least 310 seconds where the client allows it:

  • Claude Code: nothing to set. It cuts off a call only after 5 minutes without an answer or a progress notification (30 minutes for a server it starts itself), and this server sends a progress notification every 15 seconds while it waits.
  • Codex: tool_timeout_sec, 60 seconds by default.
  • Antigravity: timeoutSeconds, 180 seconds by default.
  • Claude Desktop, Cursor, VS Code and Windsurf do not document a setting for this, and a long call can be cut off by the client.

A call cut off before the answer arrives may still be charged. To get the copy that was saved in the meantime, call again without maxAgeSeconds; do not repeat a live lookup right away.

Environment variables

VariableRequiredDefault
ENRICHLAYER_API_KEYyes—
ENRICHLAYER_API_BASE_URLnohttps://api.enrichlayer.com

Hosted connector

The same tools are served over HTTP at https://mcp.enrichlayer.com/v3/mcp. Add that address as a remote MCP server in your client; the client opens the Enrich Layer sign-in page, where you paste your API key. Calls then spend that account's credits, as with the local server.

The server behind that address is the enrichlayer-mcp-v3-http command of this package. It serves Streamable HTTP without sessions, so any instance can answer any request:

PathWhat it does
POST /v3/mcpMCP requests; needs a Bearer access token from the sign-in service
GET /.well-known/oauth-protected-resource/v3/mcpTells the client where to sign in
GET /v3/health{"status":"ok","version":"<version>"}
VariableRequiredDefault
MCP_BASE_URLyes— (the public origin; access tokens must be issued by it and for it)
AUTH_JWT_SECRETyes— (the secret the sign-in service signs access tokens with)
PORTno3000
ENRICHLAYER_API_BASE_URLnohttps://api.enrichlayer.com
SENTRY_DSN, SENTRY_ENVIRONMENTnoerrors are not reported
AUTH_ISSUERno— (the sign-in service whose ES256 tokens are accepted, e.g. https://auth.enrichlayer.com)
AUTH_MCP_AUDIENCEno— (the aud its access tokens carry for this server)
AUTH_API_AUDIENCEno— (the audience requested for the token the REST API accepts)
AUTH_MCP_CLIENT_ID, AUTH_MCP_CLIENT_SECRETno— (this server's client registration, used for the token exchange)

ES256 access tokens

Set all five AUTH_* settings above, or none of them. With none, the server accepts only the HS256 tokens signed with AUTH_JWT_SECRET, and the resource metadata names MCP_BASE_URL as the authorization server. With a partial set the server refuses to start, and so it does when AUTH_ISSUER ends in a slash: it must equal the iss of the tokens exactly.

With all five, the server also accepts ES256 access tokens from AUTH_ISSUER, and the resource metadata names AUTH_ISSUER as the authorization server. HS256 tokens keep working beside them. The token header picks the check; any other algorithm, none included, gets 401. An ES256 token must have typ: at+jwt and a kid, be signed by a key in <AUTH_ISSUER>/.well-known/jwks.json, carry iss = AUTH_ISSUER exactly, have AUTH_MCP_AUDIENCE in aud, and carry sub, client_id, grant_id, scope, exp, iat and jti. If the signing keys cannot be fetched, or the answer is not 200 with a key set, the answer is 500, not 401, so clients keep their tokens.

An ES256 token never reaches the REST API and never stands for an API key. For each call the server exchanges it at <AUTH_ISSUER>/token (RFC 8693 token exchange, client credentials over HTTP Basic, audience = AUTH_API_AUDIENCE, no redirects followed) and calls the API with the token it gets back. That token is reused until 30 s before it expires, separately for every incoming token and grant, and is asked for again on every retry; a token that comes without expires_in serves only its own call. A 401 from the API drops it, so the next call exchanges again and a revoked grant is refused at once. The wait for the exchange counts against the call's time limit and ends when the client cancels the call; the exchange itself goes on for other calls that share it. If the exchange fails, the tool call fails. Only an invalid_grant refusal, such as a revoked grant, tells the user to sign in again; any other refusal, an answer that cannot be read and an exchange that does not finish within the call's time limit are the server's to fix: the user is told to try again later and the error is reported. API refusals tell a signed-in user to sign in again rather than to fix an API key they do not have.

Each tool call writes one JSON line to stdout with the tool, the API status, creditCost, requestId, the time it took and the client name; keys, tokens and parameters are never logged.

A tag v<version> also builds the image ghcr.io/enrichlayer/mcp:<version>. To build and run it locally:

docker build -t enrichlayer-mcp-v3 .
docker run --rm -p 3000:3000 -e MCP_BASE_URL=http://localhost:3000 -e AUTH_JWT_SECRET=<secret> enrichlayer-mcp-v3
curl http://localhost:3000/v3/health

Development

npm ci
npm test            # build, then unit and conformance tests
npm run update-spec # refresh spec/v3-openapi.json from the published spec
npm run gen:params  # regenerate src/generated/v3-params.ts from the spec copy

CI checks the types and runs the tests on Node 20, 22 and 24, and fails when the published v3 spec differs from spec/v3-openapi.json.

server.json describes the server for the official MCP registry. Its name, version and package must match package.json; a test checks this.

To release, set the version in package.json and server.json and push the tag v<version>. The tag runs the same checks and stages the version on npm; the package owner publishes it from Staged Packages on npmjs.com. Then run the Registry workflow by hand from the Actions tab to publish server.json to the MCP registry. The registry takes each version only once, so running the workflow again for the same version fails.

License

MIT

Reviews

No reviews yet

Be the first to review this server!