Ask Claude for 10 VPs of Sales. Get them back with verified emails.

An MCP server for sales data is a service that exposes a B2B contact database or enrichment engine as tools an AI assistant can call directly. MCP is the Model Context Protocol, described on modelcontextprotocol.io as an open-source standard for connecting AI applications to external systems, supported by Claude, ChatGPT, VS Code and Cursor among others. In practice it means an assistant can run a people search, pull a verified email or push a record to your CRM without you opening another tab. Cleanlist runs one at mcp.cleanlist.ai, and Apollo and ZoomInfo each publish one as well.

Open Claude, go to Settings, then Connectors, add https://mcp.cleanlist.ai/v1/mcp as a custom connector and sign in with OAuth. Cleanlist is not in Anthropic's connector directory, so you add it by URL. There is no API key to paste and nothing to install: it is a remote MCP server, and the OAuth grant links Claude to your Cleanlist organization. Revoke it from the same Connectors screen and Claude loses access to your data and your credits at once.

Yes. The Cleanlist MCP server works with any MCP client that supports remote servers over HTTP with OAuth, including ChatGPT, because mcp.cleanlist.ai speaks the standard protocol. Claude is the client Cleanlist supports and tests first, and the connector installs from Claude Settings, then Connectors. Cleanlist does not ship a first-party ChatGPT app or a Perplexity connector today, so in those clients you add it as a generic remote MCP server. Outside Claude, the Cleanlist REST API v2 covers the same jobs with a clapi_ Bearer key.

The Cleanlist MCP server exposes 30+ tools that map one to one onto the roughly 30 endpoints of Cleanlist REST API v2. The groups: people search, company search and find-similar-companies; person, company and bulk enrichment through the 25+ provider waterfall; research and qualification skills that score each lead against your ICP; lead lists with CSV import; CRM sync to HubSpot and Salesforce, plus sequencer sync to Lemlist; CSV and JSON export; and account tools for identity, credit balance, credit estimates and usage.

Cleanlist charges MCP tool calls in credits at the same rates as the app and the REST API: 1 credit for a verified email, 10 for a phone number, 11 for a full contact record, 1 for a company enrichment, 0.5 to save a newly added lead to a list, 0.2 per lead for CRM or sequencer sync, and 5 per lead for AI research or qualification. People search and company search cost 0 credits, and so do reading lists and checking your balance. There is no separate MCP subscription, and credits come from one shared organization wallet.

Cleanlist enforces 60 requests per minute per organization, 30 requests per minute per API key, and a hard cap of 60 People Searches per UTC day per API key. Those limits sit on the REST API v2 endpoints, and MCP tool calls run against the same endpoints inside the same organization, so the per-organization ceiling and the daily search cap apply to agent traffic too. The 30-per-minute figure is scoped to a clapi_ API key rather than to an OAuth connector. The daily search cap is the one that bites in agent workflows, so batch filters into fewer, broader searches and page through the results. Cleanlist publishes no uptime SLA and the MCP server is in beta.

The Cleanlist MCP server is in beta and included from the Starter plan; the Free plan does not include it. Programmatic REST API access starts on Pro, or an AppSumo Tier 5+ license. Self-serve pricing is Free at $0 with 50 credits a month, Starter at $49 per seat a month with 750 credits per seat, and Pro at $89 per seat a month with 1,500 credits per seat. Enterprise is custom. Annual billing takes 25% off.

Server-side MCP means the MCP server runs remotely on the vendor infrastructure and the client connects to it over HTTP with OAuth. In-context MCP means the server runs locally beside the client, usually over stdio, with the process and credentials on your own machine and every tool definition loaded into the model context window. Cleanlist is server-side only: mcp.cleanlist.ai is a hosted remote endpoint, so there is nothing to install and credentials live in an OAuth grant instead of a local config file. There is no published Cleanlist package on npm today, so the in-context path is not a supported install.

No. Cleanlist gates every paid operation behind a signed quote. The agent must first call the credit-estimate tool, which returns an HMAC-signed quote_id with a five-minute TTL, and the server rejects the paid call if the real cost would exceed the quote or the quote has expired. Your credit balance is also a hard ceiling: the wallet is shared across the app, the REST API and MCP, so the most an agent can consume is the balance you already hold.

Cleanlist limits what an agent can touch in three ways: OAuth scoped to your organization across 14 scopes, so you never paste a raw key into a chat client; a one-way sync tool, which pushes enriched leads out to HubSpot, Salesforce or Lemlist; and revocation from Claude Settings, then Connectors, at any moment. What Cleanlist does not claim: there is no published SOC 2 report, no uptime SLA, and no read-only key mode, because scopes are granted per user. The MCP server is in beta.

The Cleanlist MCP server and Cleanlist REST API v2 cover the same jobs and differ in who does the calling. MCP is for an AI client: Claude connects over OAuth, discovers 30+ tools and decides which to call from your prompt. The REST API is for your code: you authenticate with a clapi_ Bearer key, call the roughly 30 endpoints yourself and poll async workflows. Credits, rate limits and the signed-quote model are identical. REST API access starts on Pro and MCP is included from Starter. REST API v2 has no webhooks, so both surfaces poll for async enrichment results.

Yes. Claude reads your plain-English request and calls the Cleanlist search_people tool with structured filters, so Claude does the translating. Ask for VPs of Sales at US SaaS companies with 201 to 500 employees and Claude maps that onto the title, seniority, country and headcount fields. Cleanlist exposes about 24 filter fields, covering title, seniority, years in role, location, skills, education, past titles and companies, industry and headcount. There are no revenue, funding-stage, technographic or intent filters.