Skip to main content
Glama

Server Details

Analyze and score leads to identify high-potential prospects and prioritize sales outreach.

Ownership verified
Status
Healthy
Uptime
83.3% over the last 24 hours
OAuth
Works in Glama
Last Tested
Transport
Streamable HTTP · MCP 2025-06-18
URL
Repository
Saify-Technologies/saifs-ai-mcps-docs
GitHub Stars
0
ChatGPT
–
Claude
–

TDQS

A4.3/5.0

Scored across 2 tools

Disambiguation4/5

The two tools perform the same scoring job but are cleanly partitioned by input size: lead_pipeline for ≤500 rows sent as arguments, lead_pipeline_get_engine for larger exports. The descriptions state this threshold explicitly and each warns about the other's failure mode, though an agent that doesn't know its row count upfront could still misselect.

Naming Consistency4/5

Both names share a clear lead_pipeline stem in snake_case, so they are visibly related. The second appends a verb phrase (get_engine) while the first is a bare noun, a minor convention drift but still readable and predictable.

Tool Count3/5

Two tools is on the thin side, but each maps to a genuine delivery mode (direct scoring vs. generated sandbox script) rather than redundancy. Still, a two-tool surface leaves little room for narrowing, validation, or result retrieval operations.

Completeness3/5

The scoring lifecycle is covered end-to-end: input ingestion, conversion probabilities, money layer, Shapley attribution, and the CALL/NURTURE/VERIFY queue, with a fallback path for large pipelines. However, there is no way to validate or preview data first, re-score incrementally, or fetch a previously generated ledger, leaving some workflow dead ends.

Publisher details

Operator
Saifs.ai · Publisher source
Vendor relationship
Not applicable
Documentation
Not applicable
Privacy policy
Not provided
Trust center
Not applicable
Restrictions
No setup restrictions

Available Tools

2 tools
lead_pipelineScore Lead PipelineA
Read-only
Inspect

Scores an open sales pipeline of 500 lead rows OR FEWER into conversion probabilities, money at risk / value of contact, funnel stage outlook, multi-touch Shapley attribution, and a daily CALL / NURTURE / VERIFY queue. Send the rows directly; this server scores them and returns the full result including the per-lead ledger. For pipelines LARGER than 500 leads use lead_pipeline_get_engine instead — sending thousands of rows as tool arguments is slow and risks truncated JSON. Needs lead rows (lead_id, created_date; optional stage, status, closed_date, deal_size, source) from CSV, Salesforce, HubSpot, or any CRM. Optional touches and stage_history improve uplift learning, Markov funnel, and attribution. Returns manager decisions (CALL TODAY / PUSH FORWARD / QUALIFY), call queue, pipeline exposure headline, per-lead money, and explanation traces. Do not invent scores — call this tool when lead data is available.

Inputs: leads (required), as_of, touches, currency, +11 more. Returns: leads, alerts, status, message, +10 more

lead_pipeline_get_engineLead Pipeline — Get Scoring Script (large pipelines)A
Read-only
Inspect

For pipelines LARGER than 500 lead rows. Returns a complete, runnable Python script that loads the lead export in your sandbox and scores it locally (conversion probabilities, money layer, Shapley attribution, CALL / NURTURE / VERIFY queue). Makes no network calls — same shape as Customer Tiering — so Copilot Studio works even when outbound POST is blocked. The rows never pass through you as tokens. Needs numpy. Prints ranked decisions and headline figures; writes the full per-lead ledger to lead_pipeline_result.json. SAVE AND RUN THE RETURNED SCRIPT VERBATIM — do not retype, shorten, reformat, or reimplement it; only PATH / TOUCHES / STAGE_HISTORY / AS_OF / CURRENCY / OUT may be edited. Optionally takes touches_path and stage_history_path for engagement and funnel history.

Inputs: file_path (required), as_of, currency, touches_path, +1 more. 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

    Related MCP Servers

    • F
      license
      Not graded
      quality
      Not graded
      maintenance
      Enables scoring of customer leads and evaluation of interaction velocity to predict conversion outcomes. It exposes deterministic, dependency-free analysis through the Model Context Protocol for integration with MCP-compliant clients such as Claude Desktop and Cursor.
      -
    • F
      license
      Not graded
      quality
      B
      maintenance
      Enables predictive B2B outbound buying propensity scoring by aggregating time-decayed hiring, funding, and technographic signals, then classifying accounts into outbound action tiers.
      8
      -
    • A
      license
      Not graded
      quality
      F
      maintenance
      Validates email deliverability, assesses domain credibility, and scores B2B leads from A-F to help prioritize outreach, with batch processing and a free tier.
      MIT
    Try in Browser

    Glama MCP Gateway

    Add one secure layer between your agents and this server.