Lead Leak Check
Analyzes Google Sheets used as lead storage in a lead pipeline, checking for risks such as missing deduplication, unowned leads, routing gaps, and lack of unanswered-lead monitoring.
Analyzes lead pipelines automated with Make.com, identifying risks where runs may report success while leads are silently dropped due to filters, disabled workflows, missing ownership, or absent alerts.
Analyzes n8n lead automation workflows for dropped-lead risks, including failed or filtered runs, long gaps in execution history, stale workflows, and missing response monitoring.
Analyzes Slack channels used for lead notifications and sales routing, checking whether leads posted to a shared channel have a clear owner and whether unanswered leads trigger alerts.
Analyzes Typeform as an inbound lead source, checking required contact fields, storage handoff, owner assignment, response SLA coverage, and monitoring gaps.
Analyzes WhatsApp as an inbound lead source, checking whether leads are logged to storage, assigned to an owner, and covered by response and unanswered-lead alerts.
Analyzes lead pipelines automated through Zapier, identifying risks where Zap runs show success but leads are never answered due to filters, disabled workflows, missing ownership, or absent monitoring.
lead-leak-check (MCP server)
Find where inbound leads are silently dropped between the first touch and the first human reply.
Your Zapier, Make or n8n runs say Success. The lead still never hears back: nobody owned the reply, a filter stopped on an empty field, the workflow was switched off for a day, or an AI draft sat unsent. lead-leak-check turns a description of your lead pipeline into a ranked list of those risks, each with a concrete fix.
Tools
Tool | Input | Output |
| JSON config of your pipeline (sources, storage, routing, response, monitoring…) | Risk score 0–100 and findings ranked high / medium / low / verify |
| Plain English, e.g. "Typeform and WhatsApp go to Google Sheets via Zapier, nobody is assigned" | Same report, plus how the text was interpreted |
| CSV export of run history ( | Failed and filtered runs, long gaps with no runs, stale workflows |
Resource: leakcheck://rules lists all 15 rules with their explanation and fix.
Anything you don't describe is reported as verify, never as safe. No network calls, no data leaves your machine.
Related MCP server: linkedin-profile-manager-mcp
Install
git clone https://github.com/paopao-studio-ai/lead-leak-check-mcp && cd lead-leak-check-mcp
pip install . # Python 3.10+, works with mcp 1.x and 2.xOne-click bundle (MCPB)
Download lead-leak-check-mcp-0.1.0.mcpb from the latest release and open it in Claude Desktop (or any MCPB-aware client). Needs uv; dependencies install automatically.
Claude Desktop / Cursor / any MCP client
{
"mcpServers": {
"lead-leak-check": { "command": "lead-leak-check-mcp" }
}
}Without installing: {"command": "python", "args": ["-m", "lead_leak_check.server"], "env": {"PYTHONPATH": "/path/to/lead-leak-check-mcp/src"}}
Command line
lead-leak-check check examples/pipeline.json
lead-leak-check describe "WhatsApp leads land in Google Sheets via Make.com. Nobody is assigned."
lead-leak-check history examples/run_history.csv --interval 30
lead-leak-check --json check examples/pipeline.jsonConfig shape (all keys optional)
{
"name": "Typeform -> Google Sheets -> Slack #sales",
"sources": [{ "type": "web_form", "required_contact_field": false }, { "type": "whatsapp", "logged_to_storage": false }],
"storage": { "type": "google_sheets", "dedupe": false },
"routing": { "owner_assignment": "none", "after_hours_coverage": false },
"response": { "sla_minutes": 30, "auto_ack": true, "ai_drafts": true, "human_send_step": false },
"monitoring": { "error_alerts": false, "unanswered_lead_alert": false, "run_history_review": "never" },
"automation": { "platform": "zapier", "plan": "free" },
"timezone": { "business_tz": "America/New_York", "automation_tz": "UTC" },
"follow_up": { "sequence": false }
}Example output (top of the report for the config above):
# Lead leak risk: Typeform -> Google Sheets -> Slack #sales
Risk score: **100/100** (12 findings)
## 1. [HIGH] Nobody owns the first reply
- Why it leaks: Leads posted to a shared sheet or channel are seen by everyone and answered by no one.
- Fix: Assign an owner per lead (round robin or fixed) at the moment it is created, and name them in the notification.Fix the #1 finding for free
The most common high-severity finding is "no alert when a lead goes unanswered". The free n8n missed-lead heartbeat template (https://github.com/paopao-studio-ai/n8n-missed-lead-heartbeat) checks your sheet or CRM every 5 minutes and pings Slack, Discord or any webhook when a lead waits past your SLA.
Want a human to map it?
Paopao Studio runs a fixed-price Lead Leak Check ($197): a written leak map of 1–2 lead workflows, credited in full to a Starter build within 30 days. Free screenshot triage by email. → https://paopao-studio.pages.dev/?utm_source=github&utm_medium=oss&utm_campaign=lead_leak_1029
Develop
pip install -e ".[test]"
pytest -q # rule tests + an end-to-end stdio round trip with the official MCP clientLicense
MIT, see LICENSE.
Available Tools
3 toolsanalyze_run_historyA
Analyze a run-history CSV (needs a status column; a timestamp column enables gap and stale checks).
Flags failed/halted runs, filtered runs that end without errors, long gaps with no runs, and a stale last run.
Inputs: csv_text (required), expected_interval_minutes. Returns: object
check_pipelineA
Check a structured lead-pipeline config and return a ranked leak-risk list.
Keys (all optional; omitted ones are reported as 'verify'): name; sources: [{type: web_form|whatsapp|email|ads_lead_form|instagram_dm|..., required_contact_field: bool, logged_to_storage: bool}]; storage: {type: google_sheets|crm|airtable|none, dedupe: bool}; routing: {owner_assignment: round_robin|fixed|none, after_hours_coverage: bool}; response: {sla_minutes: int, auto_ack: bool, ai_drafts: bool, human_send_step: bool}; monitoring: {error_alerts: bool, unanswered_lead_alert: bool, run_history_review: weekly|never}; automation: {platform: zapier|make|n8n, plan: free|paid}; timezone: {business_tz, automation_tz}; follow_up: {sequence: bool}
Inputs: config (required). Returns: object
check_pipeline_descriptionC
Check a plain-English description of how leads arrive, where they are stored, who replies and what alerts exist.
Inputs: description (required). Returns: object
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 3 tools
The three tools target distinct input types: structured config, plain-English description, and run-history CSV. However, check_pipeline and check_pipeline_description have nearly identical names and purposes, which could cause misselection when the input format is ambiguous.
All tools use consistent snake_case verb_noun naming (check_pipeline, check_pipeline_description, analyze_run_history). The longer check_pipeline_description is still predictable within the same convention.
Three tools are well-scoped for a focused lead-leak diagnostic server. The count is slightly thin and two tools are input-format variants of the same check, but neither is excessive.
The surface covers structured pipeline checks, natural-language descriptions, and run-history analysis, which are the main diagnostic inputs. Minor gaps remain: no tool to consolidate findings or recommend fixes, and no direct lead-level audit.
Maintenance
Related MCP Connectors
Open-source Zapier/n8n alternative as an MCP server: agents build, run and debug your workflows.
Second Shift agent-native MCP server: a machine-readable front door to client leads.
Sales MCP server for AI agents: find, enrich, score and reach leads on LinkedIn, track replies.
API-first CRM for LLMs - contacts, companies, deals and activities over a native MCP server.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceA local MCP server that parses Terraform .tfstate files and lets AI agents audit enterprise infrastructure for security misconfigurations without requiring direct cloud credentials.MIT
- AlicenseAqualityDmaintenanceA local-first MCP server for auditing, drafting, and planning updates to your personal LinkedIn profile safely, without automation or scraping.101MIT
- AlicenseNot gradedqualityCmaintenanceA sovereign, MIT-licensed MCP server for professional-service workflow automation, enabling offline-capable, cryptographically signed operations without vendor lock-in.MIT
- AlicenseAqualityDmaintenanceAn unofficial MCP server for Smartlead that exposes the SmartProspect API and core Smartlead operations, enabling agents to search for leads, manage campaigns, and control credit spending with configurable safety modes.3911 npm1MIT