About Lead Intelligence
An MCP server for sales teams that evaluates conversion likelihood, pipeline risk, and channel contribution from CRM or CSV lead records, then creates a daily follow-up queue. For pipelines over 500 leads, it can generate a Python script to score records locally.
Key features
- 01Estimate conversion probability and time
- 02Assess pipeline risk and stage outlook
- 03Analyze multi-touch channel attribution
- 04Create a daily CALL / NURTURE / VERIFY queue
- 05Generate local scoring scripts for larger pipelines
Use cases
- 01Choose which prospects sales reps should contact today
- 02Find cooling leads and associated pipeline value at risk
- 03Compare channels by contribution to conversions
MCP support
Provides lead pipeline scoring tools to MCP clients over Streamable HTTP and uses OAuth 2.1 for sign-in. Larger pipelines can be scored locally with a generated Python script.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://lead-scoring-mcp.saifs.ai/mcpclaude mcp add --transport http ai-saifs-lead-intelligence https://lead-scoring-mcp.saifs.ai/mcp{"mcpServers":{"ai-saifs-lead-intelligence":{"type":"http","url":"https://lead-scoring-mcp.saifs.ai/mcp"}}}Open in Cursor{"servers":{"ai-saifs-lead-intelligence":{"type":"http","url":"https://lead-scoring-mcp.saifs.ai/mcp"}}}Open in VS Code{"mcpServers":{"ai-saifs-lead-intelligence":{"type":"http","url":"https://lead-scoring-mcp.saifs.ai/mcp"}}}{"mcpServers":{"ai-saifs-lead-intelligence":{"serverUrl":"https://lead-scoring-mcp.saifs.ai/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
Details
From the project READMELead Intelligence
Scores an open sales pipeline from lead records: probability and expected time to convert, money at risk and the value of one contact, a funnel-stage outlook, multi-touch channel credit (Shapley attribution), and a daily CALL / NURTURE / VERIFY queue for SDRs and sales managers. Works from any CRM or CSV export with a lead id and a created date.
| Registry name | ai.saifs/lead-intelligence |
| Endpoint | https://lead-scoring-mcp.saifs.ai/mcp |
| Transport | Streamable HTTP (remote, nothing to install) |
| Auth | OAuth 2.1 — PKCE (S256) and dynamic client registration; your client opens a sign-in page on first use |
| Publisher | SAIFS AI |
Install
VS Code / GitHub Copilot
Add to .vscode/mcp.json (workspace) or your user mcp.json:
{
"servers": {
"saifs-lead-intelligence": {
"type": "http",
"url": "https://lead-scoring-mcp.saifs.ai/mcp"
}
}
}
Then start the server from the MCP view and sign in when prompted.
Claude (claude.ai, Desktop)
Settings → Connectors → Add custom connector, and paste:
https://lead-scoring-mcp.saifs.ai/mcp
Claude Code
claude mcp add --transport http saifs-lead-intelligence https://lead-scoring-mcp.saifs.ai/mcp
Any other MCP client
Point it at https://lead-scoring-mcp.saifs.ai/mcp using the Streamable HTTP transport. The server returns 401 with a
WWW-Authenticate: Bearer … resource_metadata=… challenge, so OAuth-aware clients sign in automatically.
Tools
| Tool | What it does |
|---|---|
lead_pipeline | Scores up to 500 leads: conversion probabilities, pipeline value at risk, stage outlook, channel attribution, manager decisions (CALL TODAY / PUSH FORWARD / QUALIFY) and a per-lead ledger. Optional touch log and stage history improve the results. |
lead_pipeline_get_engine | For pipelines over 500 leads: returns a runnable Python script that scores the export locally with no network calls. |
Example prompts
- “Here's our HubSpot lead export. Who should the team call today?”
- “Which leads are going cold and how much pipeline value is at risk?”
- “Which channels actually drive conversions — email, demo or webinar?”
Support
- Website: https://saifs.ai
- Issues: https://github.com/Saify-Technologies/saifs-ai-mcps-docs/issues
- Privacy: https://saifs.ai/privacy_policy
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.