Customer Intelligence & Segmentation MCP server
Commit Nov 13, 2026Analyzes customer purchase history to tier accounts, predict revenue risk, and generate actionable sales call lists.
Also known as Saify-Technologies/saifs-ai-mcps-docs, customer-intelligence
- Stars
- 4
- Tools
- 2
- Downloads, 30 days
- —
- Latest version
- 1.0.2
- Last commit
- Nov 13, 2026
- License
- MIT
What is Customer Intelligence & Segmentation MCP?
Customer Intelligence & Segmentation analyzes customer purchase history to tier accounts, predict revenue risk, and generate actionable sales call lists. It exposes 2 tools, such as customer_tiering, customer_tiering_get_engine.
Summary generated from the project's README
About Customer Intelligence & Segmentation MCP server
Sales teams and analysts can transform raw transaction data into strategic sales priorities by using this remote MCP server. It processes customer purchase history from sources like Salesforce, HubSpot, Zoho, or CSV and Excel files to categorize accounts into A, B, C, or D tiers. By applying BG/NBD survival and Gamma-Gamma spend models, the system identifies revenue at risk and potential growth opportunities.
Users connect via Streamable HTTP using OAuth 2.1 PKCE authentication, which triggers a sign-in page on the first use. For datasets containing up to 500 transaction rows, the customer_tiering tool performs the scoring directly. For larger datasets, the customer_tiering_get_engine tool provides a Python script to run the analysis locally, ensuring sensitive customer data remains on your machine rather than being sent to the remote endpoint.
What you can do with it
- 1Identify high-priority sales targetsAsk the AI to analyze a sales export to find top-tier accounts and determine who needs a phone call this week.
- 2Predict revenue lossDetermine which customers are becoming inactive and calculate the total amount of revenue currently at risk.
- 3Analyze account tiering logicInvestigate the specific reasons why a particular customer was assigned a specific tier.
- 4Process large datasets privatelyGenerate a local Python script to score transaction files that exceed the 500-row limit without uploading them.
Written from the project's README. Every use case is checked against a quote from it.
How to install Customer Intelligence & Segmentation MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall Customer Intelligence & Segmentation MCP in Claude Code
$ claude mcp add --transport http customer-intelligence https://customer-tiering-mcp-latest.saifs.ai/mcpInstall Customer Intelligence & Segmentation MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"customer-intelligence": {
"url": "https://customer-tiering-mcp-latest.saifs.ai/mcp"
}
}
}Install Customer Intelligence & Segmentation MCP in VS Code
.vscode/mcp.json
{
"servers": {
"customer-intelligence": {
"type": "http",
"url": "https://customer-tiering-mcp-latest.saifs.ai/mcp"
}
}
}Install Customer Intelligence & Segmentation MCP in VS Code CLI
$ code --add-mcp '{"name":"customer-intelligence","type":"http","url":"https://customer-tiering-mcp-latest.saifs.ai/mcp"}'Install Customer Intelligence & Segmentation MCP in Codex
$ codex mcp add customer-intelligence --url https://customer-tiering-mcp-latest.saifs.ai/mcpInstall Customer Intelligence & Segmentation MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.customer-intelligence] url = "https://customer-tiering-mcp-latest.saifs.ai/mcp"
Install Customer Intelligence & Segmentation MCP in Gemini CLI
$ gemini mcp add -s user --transport http customer-intelligence https://customer-tiering-mcp-latest.saifs.ai/mcpInstall Customer Intelligence & Segmentation MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"customer-intelligence": {
"url": "https://customer-tiering-mcp-latest.saifs.ai/mcp",
"type": "http"
}
}
}Customer Intelligence & Segmentation MCP tools 2
Detected from the READMEcustomer_tieringcustomer_tiering_get_engine
| customer_tiering | — | |
| customer_tiering_get_engine | — |
Automated checks
Ran Nov 13, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachablesaify-technologies/saifs-ai-mcps-docs is public and reachablegithub.com/saify-technologies/saifs-ai-mcps-docs ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-13github.com/saify-technologies/saifs-ai-mcps-docs ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model2 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNo tool named like delete, drop or execPass
- Remote endpoint answers the MCP handshakeHTTPS endpoint answered 401 (sign-in required)Pass
README
View on GitHubCustomer Intelligence & Segmentation
Ranks a customer book into A/B/C/D tiers from purchase history, flags accounts that are slipping or ready to grow, estimates revenue at risk and upside, and builds a short SAVE / GROW / VERIFY call list for sales reps. Works from CSV, Excel, Tally, Salesforce, HubSpot, Zoho or any CRM export with a customer id, a date and an amount.
| Registry name | ai.saifs/customer-intelligence |
| Endpoint | https://customer-tiering-mcp-latest.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-customer-intelligence": {
"type": "http",
"url": "https://customer-tiering-mcp-latest.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://customer-tiering-mcp-latest.saifs.ai/mcp
Claude Code
claude mcp add --transport http saifs-customer-intelligence https://customer-tiering-mcp-latest.saifs.ai/mcp
Any other MCP client
Point it at https://customer-tiering-mcp-latest.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 |
|---|---|
customer_tiering |
Scores a customer book of up to 500 transaction rows into A/B/C/D tiers (BG/NBD survival model, Gamma-Gamma spend model, tier migration, money layer) and returns decision cards and a per-customer ledger. Cleans customer-name variants before scoring. |
customer_tiering_get_engine |
For books over 500 rows: returns a runnable Python script that scores the file locally, so customer data never reaches the server. |
Example prompts
- “Here's our sales export. Who are our A accounts, and who should we call this week?”
- “Which customers are going quiet and how much revenue is at risk?”
- “Why is customer ACME-104 a C account?”
Support
- Website: https://saifs.ai
- Issues: https://github.com/Saify-Technologies/saifs-ai-mcps-docs/issues
- Privacy: https://saifs.ai/privacy_policy
Customer Intelligence & Segmentation MCP questions
How do I add Customer Intelligence & Segmentation MCP to Claude Code?
Run claude mcp add --transport http customer-intelligence https://customer-tiering-mcp-latest.saifs.ai/mcp in your terminal. Add --scope user to make it available in every project.
How do I add Customer Intelligence & Segmentation MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What tools does Customer Intelligence & Segmentation MCP provide?
It exposes 2 tools, including customer_tiering, customer_tiering_get_engine.
What data formats are supported?
The server works with CSV, Excel, Tally, Salesforce, HubSpot, Zoho, or any CRM export containing a customer id, a date, and an amount.
How does the server handle large datasets to ensure privacy?
For datasets exceeding 500 rows, the server provides a runnable Python script to score the file locally so data does not reach the server.
What kind of customer tiers are provided?
It ranks customer books into A, B, C, and D tiers using survival and spend models.