Hunter MCP server for your AI

No. The connect form asks for one thing, an API key, and there is no OAuth app, client secret, or redirect URL to configure. Copy the key from the Hunter dashboard: go to hunter.io, sign in, open your account menu, then API. Paste it and the connection is live.

The MCP server is locked to the single Hunter account that owns the API key you pasted, so the agent sees exactly what that account sees and nothing beyond it. Team context is still readable through hunter_list_team_members, which returns the ids, names, and emails of the people on your team. If you need a different account's data, connect that account's key separately.

Yes. Address lookups, verifications, and enrichment draw on your Hunter account's own monthly allowance, so an agent left to fan out over a large list will consume it the same way you would. The exception is hunter_email_count, which reports how many addresses Hunter holds for a company without consuming a credit, so the agent can gauge coverage before committing to hunter_domain_search. hunter_get_usage breaks the current billing period down by request type, hunter_get_account shows the plan and reset date, and the Search credits running low trigger fires when the remaining searches or verifications fall below your limit.

hunter_domain_search returns the addresses Hunter knows for a company, while hunter_email_finder targets one specific named person at that company. hunter_discover is a different job entirely: it is the prospecting endpoint that finds companies matching a search, not email addresses. hunter_domain_finder runs the other way again, resolving a company name to its most likely web domain, which is the step people usually forget when all they have is a company name.

It works with the campaigns you already have rather than building new ones. There is no create-campaign tool in the catalog, so you set the sequence up in Hunter, then the agent can read it with hunter_list_campaigns, put people into it with hunter_add_campaign_recipients, check sending status with hunter_list_campaign_recipients, and pull people back out with hunter_cancel_campaign_recipients. Adding a recipient queues real mail, which is the write most teams keep behind approval. A Campaign created trigger lets you watch for new sequences someone sets up in the UI.

19 of the 39 operations load up front, which keeps the tool list in your client short enough for a model to choose well from. The rest stay searchable on demand: API key management, custom attribute definitions, connected apps including hunter_push_leads_to_connected_app for syncing leads into a CRM, and leads list housekeeping like renaming, favoriting, and deleting. Flip the full-catalog toggle on the connection if you would rather expose everything at once.

No. PopMCP hosts it and gives you a Streamable HTTP MCP URL. There is nothing to deploy, no callback URL to register, and no infrastructure to keep running or patch.

Any client that supports a remote Streamable HTTP MCP server — Claude Desktop, Claude Web, ChatGPT custom connectors, Codex and the Codex CLI, OpenCode and Z.ai's ZCode, as well as editors such as Cursor, Windsurf and Zed. Your client signs in to PopMCP with OAuth; the provider credential never leaves the server.

Loading 39 tool definitions into every conversation burns context before the work starts. PopMCP loads a curated 19-tool set covering the everyday workflows and keeps the rest searchable, so your AI pulls a specialist tool only when a task needs it. You can switch a connection to the full catalog at any time.

A tool is something your AI calls — there are 39 here. A trigger is something PopMCP watches for you: 9 Hunter events that can start work on the PopMCP side. Triggers never enter your AI client's context, and none of them ask you to paste a callback URL into Hunter.