io.github.CSOAI-ORG/crm-ai-mcp

Score a sales lead (0-100) based on firmographic data, engagement signals, and source quality. Returns tier, recommended action, and score breakdown. Args: company_size: Number of employees industry: Industry vertical (e.g. "technology", "finance", "healthcare") budget: Estimated budget in dollars engagement_signals: Behavioral data as {signal: count} (e.g. {"demo_requested": 1, "email_clicks": 5}) source: Lead source (referral, organic_search, paid_search, linkedin, etc.) days_since_first_touch: Days since first interaction Behavior: This tool is read-only and stateless — it produces analysis output without modifying any external systems, databases, or files. Safe to call repeatedly with identical inputs (idempotent). Free tier: 10/day rate limit. Pro tier: unlimited. No authentication required for basic usage. When to use: Use this tool when you need structured analysis or classification of inputs against established frameworks or standards. When NOT to use: Not suitable for real-time production decision-making without human review of results.

Predict deal win probability and estimated close date based on pipeline stage, velocity, and deal characteristics. Args: deal_value: Deal amount in dollars days_in_pipeline: Days since deal was created current_stage: Pipeline stage (prospecting, qualification, discovery, proposal, negotiation) activities_count: Number of logged activities (calls, emails, meetings) competitor_mentioned: Whether a competitor has been mentioned champion_identified: Whether an internal champion has been identified Behavior: This tool generates structured output without modifying external systems. Output is deterministic for identical inputs. No side effects. Free tier: 10/day rate limit. Pro tier: unlimited. No authentication required for basic usage. When to use: Use this tool when you need structured analysis or classification of inputs against established frameworks or standards. When NOT to use: Not suitable for real-time production decision-making without human review of results. Behavioral Transparency: - Side Effects: This tool is read-only and produces no side effects. It does not modify any external state, databases, or files. All output is computed in-memory and returned directly to the caller. - Authentication: No authentication required for basic usage. Pro/Enterprise tiers require a valid MEOK API key passed via the MEOK_API_KEY environment variable. - Rate Limits: Free tier: 10 calls/day. Pro tier: unlimited. Rate limit headers are included in responses (X-RateLimit-Remaining, X-RateLimit-Reset). - Error Handling: Returns structured error objects with 'error' key on failure. Never raises unhandled exceptions. Invalid inputs return descriptive validation errors. - Idempotency: Fully idempotent — calling with the same inputs always produces the same output. Safe to retry on timeout or transient failure. - Data Privacy: No input data is stored, logged, or transmitted to external services. All processing happens locally within the MCP server process.

Schedule follow-ups for a list of contacts based on priority, last contact date, and engagement strategy. Args: contacts: List as [{"name": "X", "email": "x@y.com", "last_contact_date": "2026-01-01", "priority": "high", "deal_value": 50000}] strategy: Follow-up cadence (aggressive, standard, nurture, reactivation) Behavior: This tool is read-only and stateless — it produces analysis output without modifying any external systems, databases, or files. Safe to call repeatedly with identical inputs (idempotent). Free tier: 10/day rate limit. Pro tier: unlimited. No authentication required for basic usage. When to use: Use this tool when you need structured analysis or classification of inputs against established frameworks or standards. When NOT to use: Not suitable for real-time production decision-making without human review of results.

Calculate a customer health score (0-100) from usage, support, NPS, adoption, and tenure signals. Args: usage_metrics: Usage data as {"monthly_logins": N, "active_users": N, "total_users": N} support_tickets: Open support tickets in last 30 days nps_score: Net Promoter Score (0-10) contract_value: Annual contract value months_as_customer: Customer tenure in months feature_adoption_pct: Percentage of features adopted (0-100) Behavior: This tool is read-only and stateless — it produces analysis output without modifying any external systems, databases, or files. Safe to call repeatedly with identical inputs (idempotent). Free tier: 10/day rate limit. Pro tier: unlimited. No authentication required for basic usage. When to use: Use this tool when you need structured analysis or classification of inputs against established frameworks or standards. When NOT to use: Not suitable for real-time production decision-making without human review of results.

Predict churn probability and recommend a retention playbook based on usage trends, support patterns, and contract timeline. Args: months_as_customer: Customer tenure in months monthly_usage_trend: Recent monthly usage values (e.g. [100, 95, 80, 60]) support_tickets_last_90d: Support tickets opened in last 90 days nps_score: Latest NPS score (0-10) contract_renewal_days: Days until contract renewal competitor_mentions: Times competitor was mentioned in interactions Behavior: This tool is read-only and stateless — it produces analysis output without modifying any external systems, databases, or files. Safe to call repeatedly with identical inputs (idempotent). Free tier: 10/day rate limit. Pro tier: unlimited. No authentication required for basic usage. When to use: Use this tool when you need structured analysis or classification of inputs against established frameworks or standards. When NOT to use: Not suitable for real-time production decision-making without human review of results. Behavioral Transparency: - Side Effects: This tool is read-only and produces no side effects. It does not modify any external state, databases, or files. All output is computed in-memory and returned directly to the caller. - Authentication: No authentication required for basic usage. Pro/Enterprise tiers require a valid MEOK API key passed via the MEOK_API_KEY environment variable. - Rate Limits: Free tier: 10 calls/day. Pro tier: unlimited. Rate limit headers are included in responses (X-RateLimit-Remaining, X-RateLimit-Reset). - Error Handling: Returns structured error objects with 'error' key on failure. Never raises unhandled exceptions. Invalid inputs return descriptive validation errors. - Idempotency: Fully idempotent — calling with the same inputs always produces the same output. Safe to retry on timeout or transient failure. - Data Privacy: No input data is stored, logged, or transmitted to external services. All processing happens locally within the MCP server process.