New · MCP Server

Your AI agent can run your outreach end-to-end

Sellvance is the first B2B outreach platform with a native Model Context Protocol server. Connect Claude, ChatGPT, Cursor or any MCP-aware agent and hand off the whole pipeline in plain language.

Claude ChatGPT Gemini Cursor VS Code OpenAI API
Sellvance MCP server — one tool per API endpoint

One platform, end-to-end — that's the whole point

An agent is only as good as the surface it can act on. Most outreach stacks are six disconnected tools, so agents hit a wall the moment a workflow crosses a boundary. Sellvance covers the entire pipeline in one product.

Discover prospects

“Find 200 founders of pre-seed SaaS companies in Berlin hiring their first AE.” The agent queries the database and imports the matches.

Segment & organize

Create segments, attach automated filters, and let the agent sort new leads into the right buckets as they arrive.

Enrich & qualify

Fill missing fields, score leads against your ICP, and drop the unqualified — through enrichment profiles the agent configures.

Write sequences

“Draft a 4-touch sequence, opener under 60 words, no fake personalization.” Sequence, steps and spintax, ready to review.

Launch campaigns

Bind a sequence to a segment, attach mailboxes, preview messages against real leads, and activate — all conversationally.

Monitor & iterate

Ask for campaign health, reply rates or bounce audits. The agent reads live stats and suggests fixes.

Built on the open MCP standard, secured by scoped keys

The server auto-generates one tool per public API endpoint, so any capability the UI has, your agent has too. Authentication uses the same scoped API keys as the REST API.

  • Streamable HTTP transport. The modern MCP spec — no stdio shims.
  • Workspace-scoped URLs. Mount at /mcp/ws/<workspace>/ to sandbox an agent.
  • Scope filtering. outreach:read, leads:write and friends enforced on every call.
  • Hundreds of tools auto-generated from the OpenAPI schema — one per endpoint, always in sync with the platform.

Two-minute quickstart

  1. Create a scoped API key in Workspace Settings → API Keys.
  2. Copy the MCP URL from Settings → MCP.
  3. Paste it into your agent's config.
  4. Ask: “Find 50 B2B SaaS CTOs in the UK and draft a cold-outreach sequence.”
{
  "mcpServers": {
    "sellvance": {
      "url": "https://sellvance.com/mcp/ws/<workspace>/",
      "headers": {
        "Authorization": "Bearer <api_key>"
      }
    }
  }
}

No SDK, no webhooks, no scripts. The agent reads the tool list the moment it connects.

Why Sellvance plus agents is a step change

End-to-end in one session

Data, leads, sequences, sending and analytics live together — no tool boundaries mid-workflow.

Delegate the tedious parts

Segmenting, filtering, qualifying, drafting, QA — a sales week becomes a paragraph in a chat.

Always in sync

New API endpoint ships, new MCP tool appears. No integration to update, no SDK to upgrade.

Granular, scoped access

Read-only eyes on one workspace, or write access to a single resource — your key's scopes decide.

Works with any MCP client

Claude, ChatGPT, Cursor, VS Code, Gemini, or your own in-house agent.

Pay for outcomes, not seats

Giving an agent the keys doesn't multiply a per-seat subscription — you pay for the work it does.

Hand the reins to your AI agent

Create a free workspace, generate an API key, and let Claude or ChatGPT build your next campaign while you watch.