Lead Distro AI MCP Server: Connect Claude, Cursor, or Any AI Agent to Your Lead Account

Last Updated: June 10, 2026

Lead Distro AI now has an MCP server that lets Claude and other AI agents connect directly to your lead distribution account and manage it through natural language. Ask "What was my revenue and profit yesterday?" and get a structured answer in seconds. Say "Create a new campaign with round-robin routing across three buyers" and the agent builds the configuration for your review. No logging into a dashboard. No hunting through menus.

There are two ways to connect. The standalone read-only package is available today: install it locally in under five minutes and start pulling analytics through any MCP-compatible client. The hosted full server at mcp.leaddistro.ai is in early access and adds full campaign management, including creating campaigns, adding buyers, configuring delivery, and running test leads. Both options work with Claude Code, Claude Desktop, Cursor, Windsurf, and any client that implements the open Model Context Protocol standard.

According to Anthropic, which introduced the Model Context Protocol in November 2024, MCP-connected agents retrieve accurate, real-time data instead of relying on static training knowledge, which is the difference between an agent that tells you general facts about lead distribution and one that tells you your specific campaign's profit margin this morning. For a deeper look at how lead distribution platforms handle AI-native workflows, see our guide on what is lead distribution software.

Key Takeaways

• Lead Distro AI has an MCP server that lets any MCP-compatible AI agent read your analytics and manage your campaigns through natural language commands.
• Two connection options exist: a locally installed read-only package available now, and a hosted full server at mcp.leaddistro.ai available to early access users.
• Three permission scopes control access: read (analytics only), campaigns:write (full campaign management), and leads:write (test lead submission only).
• 31 tools are available across all scopes, covering campaigns, buyers, suppliers, performance data, ping-post configuration, automations, and buyer portals.
• Billing, payment, and subscription data are intentionally excluded from the MCP, and agents cannot submit real production leads.
• Setup takes under five minutes and requires only a Lead Distro AI account, an API key from your dashboard settings, and Node.js 18 or later.
• Claude Code, Claude Desktop, Cursor, and Windsurf all work out of the box with either connection method.

How the Lead Distro AI MCP Server Works

MCP stands for Model Context Protocol, an open standard that lets AI agents call software tools through a consistent interface. Think of it as a universal connector: instead of every AI client needing a custom integration for every piece of software, MCP lets any compliant client talk to any compliant server using the same handshake.

When Claude is connected to Lead Distro AI via MCP, the agent has access to a defined set of tools, each one backed by a real API call to your account. When you ask "What's my campaign performance this week?", the agent calls get_campaign_performance, retrieves your actual P&L data, and answers from real numbers. When you say "Add a new buyer to my home services campaign," the agent calls create_buyer and add_buyer_to_campaign in sequence, then shows you what it built before anything is saved.

The key distinction from a general chatbot is that every response is grounded in your live account data, not a language model's training. For more context on how Lead Distro AI connects with external platforms, read our overview of Lead Distro AI integrations.

Option 1: Install the Read-Only MCP Package

The standalone package runs locally on your machine and exposes the nine read-scope tools. No early access required. You can query analytics, review campaign configurations, and pull performance data through any MCP client today.

Prerequisites

• Node.js 18 or later
• A Lead Distro AI account (start your 7-day free trial if you don't have one yet, credit card required)
• An API key from Settings > API Keys in your dashboard, scoped to read

Build and Register with Claude Code

# 1. Build the package
cd mcp-server
npm install && npm run build
 
# 2. Register with Claude Code
claude mcp add leaddistro \
  --env LEADDISTRO_API_KEY=your_api_key_here \
  --env LEADDISTRO_BASE_URL=https://www.leaddistro.ai \
  -- node /absolute/path/to/mcp-server/dist/index.js
 
# 3. Restart Claude Code

Claude Desktop Configuration

If you are using Claude Desktop instead of Claude Code, add the following block to your claude_desktop_config.json file under mcpServers:

{
  "mcpServers": {
    "leaddistro": {
      "command": "node",
      "args": ["/absolute/path/to/mcp-server/dist/index.js"],
      "env": {
        "LEADDISTRO_API_KEY": "your_api_key_here",
        "LEADDISTRO_BASE_URL": "https://www.leaddistro.ai"
      }
    }
  }
}

Replace /absolute/path/to/mcp-server/dist/index.js with the actual path on your machine. Restart Claude Desktop after saving.

Test the Connection

Once restarted, open a new conversation and ask: "List my campaigns." If the server is connected correctly, Claude returns your live campaign list with status and settings pulled directly from your account.

For a technical reference on posting leads programmatically, see the Lead Distro AI API guide.

Option 2: Connect via the Hosted Server (Early Access)

The hosted server at mcp.leaddistro.ai/mcp removes the need to install or build anything locally. It exposes all 31 tools across all three permission scopes, including full campaign creation and management.

Authentication Options

API key: Generate a key from Settings > API Keys in your dashboard. Scope it to campaigns:write for full management access or read for analytics only.

OAuth keyless (recommended for Claude Code): Run the following command, which opens a branded Lead Distro AI consent screen in your browser. No API key needs to be stored on your machine.

claude mcp add leaddistro --auth oauth

Request Early Access

The hosted server is available to beta users. Sign up for Lead Distro AI and contact the team to request access. Early access users get all 31 tools, priority support for MCP-related issues, and input on the tool roadmap.

MCP Tool Reference: What Your AI Agent Can Do

Tools are grouped into three permission scopes. Scope a key to the minimum access level your workflow needs. If you are only pulling reports, use read. If you are managing campaigns, use campaigns:write. The leads:write scope covers test lead submission only.

The leads:write scope covers only test leads. Real production lead submission goes through the Lead Distro AI API, not the MCP server.

What AI Agents Cannot Access

Transparency about scope limits builds trust, so here is what the MCP server intentionally excludes.

Billing and payment data are not accessible through any tool or scope. The agent cannot view invoices, payment methods, subscription tiers, or billing history. Those actions require logging into the dashboard directly.

Real production leads cannot be submitted through the MCP. The send_test_lead tool exists solely to verify that a campaign's routing and delivery configuration is working correctly. It fires a synthetic lead through the pipeline so you can confirm the buyer receives the right fields, without touching your live lead volume or buyer caps.

Subscription changes are also excluded. The agent cannot upgrade or downgrade your plan, cancel your account, or modify any payment-related settings.

This scope design means you can give a campaigns:write key to an AI agent workflow without worrying that it will touch your financials. The agent manages distribution logic; you manage billing.

3 Real-World Use Cases for PPL Agencies

Morning Performance Brief

Connect your read-scoped key to Claude and start every morning with a one-question briefing. Ask: "What was my total revenue, cost, and profit yesterday across all campaigns? Which buyer had the lowest accept rate?"

Claude calls get_lead_stats for the aggregate numbers and get_campaign_performance for per-buyer breakdowns, then returns a plain-language summary you can share with your team or act on immediately. No dashboard login required, no report to pull manually.

New Campaign Setup

When onboarding a new vertical or lead type, walk Claude through the configuration in plain language. Say: "Create a new home services campaign with round-robin routing, cap it at 50 leads per day, and add three buyers: Buyer A with a $25 CPL and webhook delivery, Buyer B with a $20 CPL and email delivery, and Buyer C with $30 CPL and GoHighLevel delivery."

Claude sequences the create_campaign, create_buyer, add_buyer_to_campaign, and set_buyer_delivery calls, shows you every step before executing, and finishes by running send_test_lead so you can confirm the routing before going live. What used to take 20 minutes of clicking through menus takes under three minutes of conversation. For a deeper look at how AI agents are reshaping lead distribution, see our full breakdown.

Buyer Onboarding Check

When a new buyer signs up, track their progress without logging in. Ask: "Which of my buyers are not fully onboarded? What steps are they missing?"

Claude calls get_onboarding_status for each buyer and returns a checklist of incomplete steps, whether that is a missing webhook URL, an unsigned agreement, or a delivery method not yet configured. You know exactly what to follow up on before the buyer's first lead is supposed to arrive. For reference on how different distribution models compare, read our guide on lead distribution software for AI agents.

Frequently Asked Questions

Is the MCP server available on all Lead Distro AI plans?

The read-only standalone package is available to all Lead Distro AI subscribers, including those on the 7-day free trial (credit card required to start). The hosted full server at mcp.leaddistro.ai with all 31 tools is currently in early access. Sign up and contact the team to request access. There is no additional per-seat charge for MCP access; it is included in your plan subscription.

Does connecting an AI agent give it access to my buyers' personal contact information?

The read-scope tools return buyer configuration data: delivery settings, cap limits, pricing, and onboarding status. They do not expose your buyers' personal contact details, payment information, or private portal credentials. Billing and payment data are excluded from all scopes by design. If you want to restrict access further, scope your API key to read only and the agent cannot modify any account settings.

What happens if the AI agent tries to do something outside its allowed scope?

The MCP server enforces scope at the API layer, not just at the tool definition level. If an agent holding a read-scoped key attempts to call create_campaign or any other campaigns:write tool, the server returns a permission error and the agent reports the failure rather than silently skipping the step. Scope enforcement is server-side and cannot be bypassed by the agent.

Can I use this with ChatGPT or other AI tools?

The Lead Distro AI MCP server works with any client that implements the Model Context Protocol standard. Currently, MCP support is available in Claude Code, Claude Desktop, Cursor, and Windsurf. ChatGPT does not yet support MCP natively as of June 2026, but any client that adds MCP support will work with Lead Distro AI's server without any changes on our end.

Is there a rate limit on MCP tool calls?

MCP tool calls count against the same API rate limits as direct API requests, which are determined by your plan tier. Read-scope tools are lightweight and are unlikely to approach limits in normal conversational use. If you are running automated workflows that call tools in a tight loop (for example, a script that checks performance every few minutes), structure the workflow with appropriate pauses between calls. Contact the team if you need higher rate limits for a specific workflow.

Conclusion

MCP turns Lead Distro AI from a platform you log into into a platform you converse with. Instead of navigating dashboards to pull a report or configure a campaign, you describe what you need and the agent handles the execution, grounded in your live account data at every step.

The read-only package is available today. Clone the repo, run npm install && npm run build, register it with Claude Code or Claude Desktop, and ask your first question in under five minutes. For the full 31-tool hosted server with campaign management, sign up and request early access.