Customer Intelligence & Segmentation
Server Details
Analyze customer data to make segmentation and predict which customer to focus on for more sales.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- OAuth
- Works in Glama
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-06-18
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 2 tools
The two tools are split by an explicit, unambiguous trigger: <=500 rows goes to customer_tiering, >500 rows goes to customer_tiering_get_engine. Their outputs and execution models (inline result vs. returned runnable script) are described clearly enough that an agent can pick correctly without guessing.
Both names use the same snake_case, shared-prefix convention (customer_tiering / customer_tiering_get_engine), making the relationship between the two obvious. No mixed conventions or vague verbs.
Two tools is thin for a server titled 'Customer Intelligence & Segmentation', which implies more than tiering alone. The two tools themselves are well justified as small/large-book paths, so the count is defensible but borderline.
The core scoring lifecycle is fully covered: one path for small books, one for large, with identity cleaning and override re-submission handled inside the calls. Minor gaps remain — no tool to retrieve or re-open a previously written ledger, and no surface for the broader segmentation implied by the server name.
Publisher details
- Operator
- Saifs.ai · Publisher source
- Operator website
- https://saifs.ai/ · Publisher source
- Vendor relationship
- Not applicable
- Documentation
- Not applicable
- Trust center
- Not applicable
- Restrictions
- Not applicable
Available Tools
2 toolscustomer_tieringScore Customer Book (A/B/C/D)ARead-onlyInspect
Scores a customer book of 500 transaction rows OR FEWER into A/B/C/D tiers. Send the rows directly; this server runs the survival model (BG/NBD), spend model (Gamma-Gamma), tier migration, money layer and decision cards, and returns the full result including a per-customer ledger with explanation traces. For books LARGER than 500 rows use customer_tiering_get_engine instead — sending thousands of rows as tool arguments is slow and risks truncated JSON. Optionally accepts rep_contacts, which lets the money layer learn contact uplift from data rather than assuming it. Customer identifiers are CLEANED HERE before scoring: capitalisation, spacing, punctuation, legal-suffix and word-order variants (ACME PVT LTD / Acme Pvt. Ltd. / Acme Private Limited) are merged into one account by rule, so send the values exactly as they appear in the source and do not pre-normalise them. Anything that needs context instead of rules — 'Acme & Co' vs 'Acme Pvt Ltd', a name under two codes — comes back in identity_cleaning.review_candidates, unmerged, for you to judge from the surrounding rows and re-send via identity_overrides. Pass customer_name alongside a coded customer_id to have accounts reported by name.
Inputs: transactions (required), as_of, currency, rep_contacts, +12 more. Returns: alerts, status, message, metadata, +10 more
customer_tiering_get_engineCustomer Tiering — Get Scoring Script (large books)ARead-onlyInspect
For books LARGER than 500 transaction rows. Returns a complete, runnable Python script that scores the book into A/B/C/D tiers with survival modelling (BG/NBD), spend modelling (Gamma-Gamma), tier migration, a money layer and plain-language decision cards. Run it in your code sandbox against the user's transaction file. The rows never pass through you as tokens, so a 10,000-row book costs the same to run as a 600-row one. Needs numpy. Prints ranked decisions and headline figures; writes the full per-customer ledger to customer_tiering_result.json beside the input file. No customer data reaches this server on this path. SAVE AND RUN THE RETURNED SCRIPT VERBATIM — every block of it is required for the computation. Do not retype it from memory, shorten it, reformat it, split it up, or reimplement the maths with pandas/sklearn; only the PATH / AS_OF / CURRENCY / OUT / OVERRIDES / CONTACTS lines at the bottom may be edited. The script cleans customer identities itself before scoring — merging capitalisation and spelling variants by rule, printing what it merged, and listing the similar-but-unproven groups for you to rule on via OVERRIDES — so do not pre-clean the file or edit those rules. Optionally takes contacts_path, a log of rep calls or visits (customer_id + date only). It is not required and the book scores fine without it, but it is valuable: with it the money layer MEASURES what a contact is worth per tier from touched-vs-untouched tier transitions instead of assuming a flat rate, so ask for it whenever the user mentions a CRM, a call log or a visit register.
Inputs: file_path (required), as_of, currency, contacts_path. Returns: notes, script, currency, language, +11 more
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Sales analytics, ML forecasting, customer segmentation, and trend analysis.
AI analytics — sales analysis, ML forecasting, customer segmentation.
Analyze and score leads to identify high-potential prospects and prioritize sales outreach.
Prioritise overdue accounts by recovery uplift and recommend a compliant contact strategy.
Related MCP Servers
- AlicenseAqualityFmaintenanceRevenue intelligence MCP server: RFM analysis, 14.5-point ICP scoring, pipeline health scoring. Embeds Artefact Formula methodology. HubSpot integration.7Business Source 1.1
- FlicenseNot gradedqualityDmaintenanceTransforms natural language queries into SQL for customer segmentation, enabling democratized access to customer data insights.1-
- FlicenseNot gradedqualityDmaintenanceProvides ML-powered revenue intelligence for sales and customer success teams, enabling lead scoring, churn risk detection, and conversion predictions with explainable feature attribution and production monitoring capabilities.-
- FlicenseNot gradedqualityBmaintenanceEnables MCP-compliant clients to run deterministic customer churn prediction and 12-month CLV regression synthesis through a zero-dependency Python skill.8-
Glama MCP Gateway
Add one secure layer between your agents and this server.