About Hunter MCP
Hunter MCP connects MCP clients to Hunter.io for prospecting and email research. It combines domain and company discovery, contact finding and verification, enrichment, and lead management, with only lead creation changing data.
Key features
- 01Search emails by domain
- 02Find and verify professional emails
- 03Enrich people and companies
- 04Discover companies with filters
- 05Review and create leads
- 06Check account credits and usage
Use cases
- 01Find contacts at a target company
- 02Verify a prospect email before outreach
- 03Enrich a person or company record
- 04Review or add leads in Hunter
MCP support
Exposes 11 Hunter.io tools to MCP clients for searching, verification, enrichment, discovery, and lead operations. Ten tools are read-only; create_lead writes to the Hunter leads list.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
11Saved tool list · updated 3w ago
This tool takes no parameters.
Details
From the project READMEHunter MCP
Hunter.io MCP server. 11 tools cover domain search, email finding and verification, enrichment, company discovery, and lead management.
Install
Claude Code:
claude mcp add hunter -e HUNTER_API_KEY=your-key -- npx -y @scalably-io/hunter-mcp
Codex:
codex mcp add hunter --env HUNTER_API_KEY=your-key -- npx -y @scalably-io/hunter-mcp
Claude Desktop: download hunter-mcp.mcpb from the latest GitHub release and open it.
Setup
- Create an API key at hunter.io/api-keys.
create_leadwrites to your Hunter leads list and is the only non-read tool; the other 10 tools are read-only.
Tools (11)
| Tool | What it does |
|---|---|
account_info | Read the Hunter v2 account plan and exact current credit usage, including remaining unified or per-type balances |
domain_search | Search Hunter v2 emails for one domain/company with current people, verification, location, job-title, decision-maker, aggregation, and offset filters |
email_finder | Find and automatically verify the most likely professional email from a company/domain plus name, or directly from a LinkedIn handle |
email_verifier | Verify one email address with Hunter v2 and return exact deliverability, score, SMTP/MX, accept-all, webmail, disposable, and source evidence |
email_count | Count Hunter email coverage for a domain/company, optionally limited to personal or generic addresses, without returning addresses |
email_enrichment | Enrich a person from an email address or LinkedIn handle using Hunter v2, optionally in Clearbit-compatible format |
company_enrichment | Enrich a company from its domain using Hunter v2, optionally in Clearbit-compatible format |
combined_enrichment | Enrich both a person and their company from one email using Hunter v2, optionally in Clearbit-compatible format |
discover | Use Hunter Discover v2 to find companies from current natural-language or structured organization, location, industry, headcount, type, year, keyword, technology, and funding filters |
create_lead | Create one Hunter lead from a required email and optional current lead fields, list placement, and custom attributes. This is a single-attempt mutation |
list_leads | List Hunter leads with current list, identity, company, status, verification, activity/date, location, tag, campaign, user, confidence, custom-attribute, query, and offset filters |
Configuration
| Variable | Required | Purpose |
|---|---|---|
HUNTER_API_KEY | yes | Hunter.io API key from hunter.io/api-keys |
HUNTER_API_BASE | no | Override the Hunter API base URL (default https://api.hunter.io/v2) |
HUNTER_TIMEOUT_MS | no | Per-request timeout in milliseconds (default 30000) |
HUNTER_RETRY_BASE_MS | no | Base delay in milliseconds for the GET retry backoff (default 500) |
Reply shape
Every tool returns plain JSON with status (succeeded, partial, no_op), operation, summary, target, result, proof, warnings, recovery. Failures throw a plain error string: <code>: <message> <hint>.
Limits
Hunter's per-plan request quotas surface in account_info.
Verify
Each release lists the package version, the .mcpb sha256 and the production commit it was derived from in CHANGELOG.md. CI runs the tests and a clean install of the packed tarball on every push.
Privacy Policy
This server runs locally, on your machine, under your own credentials. It collects no personal data, contains no telemetry, stores nothing persistently, and talks only to the vendor API it wraps. No third party, including Scalably, receives your data. Contact: [email protected]. Canonical copy: https://scalably.io/connector-privacy.html
License
MIT. Copyright Scalably.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.