Ploid provides AI agents access to a living index of over 2 billion people, enabling natural-language people search, verified prospect and candidate list building, decision-maker discovery, and evidence-backed person research. Enrich profiles with professional history, social presence, and source-linked information for recruiting, sales prospecting, and market research.
Claude is Anthropic's AI assistant, available as a desktop app and in Cowork. It supports custom connectors, so it can call MCP servers directly from a chat.
This guide connects Ploid MCP to Claude Desktop through MewCP, so Claude Desktop can use Ploid MCP's 6 tools, like search_people, research_person and find_people, without your Ploid MCP credentials ever reaching the app.
Ploid MCP signs in through managed OAuth. MewCP stores the token encrypted, refreshes it before it expires and injects it only at call time. Your agent never holds it, so it can never leak it.
More apps
Ask your AI to find companies, verify email addresses, and build leads lists with Hunter’s MCP.
Search Apollo's B2B contact and company database, enrich records in bulk, and manage email sequences from your connected Apollo account.
Brevo's marketing and CRM platform — manage contacts, lists and segments, send transactional and campaign email, run SMS and WhatsApp campaigns, and track deals and companies
HubSpot connects AI agents to CRM data and business workflows, enabling them to search and manage contacts, companies, deals, tickets, and engagement records, and access HubSpot tools through its remote MCP server.
Other clients
Ploid MCP works the same way in every client below. Pick yours for its own guide.
Free to start.
Scope access to the exact Ploid MCP tools and accounts you allow, work and personal side by side. Anything outside that scope is refused at call time, even when the model asks for it.
Each call is logged: what ran, on which account, and whether it worked. Failures come back structured, so the agent knows whether to retry instead of guessing.
Every app sits behind one secure MCP URL, and there is no server for you to deploy or keep running. Add an integration in the dashboard and it is live on the next call, with no config to change and no new credentials to wire up. Tools load only when a task needs them, so your agent stays fast and focused however many apps you connect.
In Claude, open Settings → Connectors, then choose Add custom connector.
Name it "mewcp" and paste the URL.
A browser window opens the first time the client connects. Sign in and approve access. No API key needed.
Start a new chat and ask: "List the tools you can use from MewCP." You should see your connected apps.
Find up to 10 matching profiles in Ploid's people index for 1 ACU per completed search, including no matches, without starting research. Failed searches are not charged. Results are bounded, not exhaustive, and indexed details may be stale. Show the candidates and ask the user to choose before research_person, even for a single match. Use company, location or title to narrow a name.
Start source-reviewed deep research on one selected person_id from search_people, or an explicit HTTPS LinkedIn person profile URL. For a name, search and ask the user to choose first. First workspace access costs 25 ACU, including an already-cached profile; rereads within 90 days are free. Not-found and uncertain results are free. Returns a resumable run_id when pending; use get_research_status for the result.
Build a verified list of people from a natural-language sales or research query. Each match is checked against criteria derived from the query. Returns a resumable run_id; use get_research_status for the list.
Build a verified list of likely buyers and influencers at a company for a specific product. Returns a resumable run_id; use get_research_status for the list.
Retrieve a pending or completed research_person, find_people, or find_decision_makers run by run_id, including after reconnecting. Pending runs should be checked no more often than every 5 seconds. Does not start or cancel research.
Stop a research run when the user asks to cancel. Work already completed may still be charged, including people a search admitted before it stopped.
