clay-local-dev-loop
Configure Clay local development with hot reload and testing. Use when setting up a development environment, configuring test workflows, or establishing a fast iteration cycle with Clay. Trigger with phrases like "clay dev setup", "clay local development", "clay dev environment", "develop with clay".
Install
mkdir -p .claude/skills/clay-local-dev-loop && curl -L -o skill.zip "https://mcp.directory/api/skills/download/8715" && unzip -o skill.zip -d .claude/skills/clay-local-dev-loop && rm skill.zipInstalls to .claude/skills/clay-local-dev-loop
About this skill
Clay Local Dev Loop
Overview
Clay is a web-based platform with no local runtime. Your local dev loop consists of: (1) scripts that push data into Clay via webhooks, (2) Clay enrichment running in the cloud, and (3) HTTP API columns pushing enriched data back to your local endpoint via ngrok. This skill sets up that feedback loop.
Prerequisites
- Completed
clay-install-authsetup - Node.js 18+ or Python 3.10+
- ngrok installed (
npm install -g ngrokor ngrok.com) - Clay table with webhook source configured
Instructions
Step 1: Expose Your Local Server via ngrok
Clay's HTTP API enrichment columns need a public URL to call your local endpoints.
# Start ngrok tunnel to your local server
ngrok http 3000
# Copy the HTTPS forwarding URL (e.g., https://abc123.ngrok-free.app)
Step 2: Create a Local Webhook Receiver
// src/clay-receiver.ts — receives enriched data from Clay HTTP API columns
import express from 'express';
const app = express();
app.use(express.json());
// Clay HTTP API column calls this endpoint
app.post('/api/clay/enriched', (req, res) => {
const enrichedData = req.body;
console.log('Enriched record received from Clay:', {
email: enrichedData.email,
company: enrichedData.company_name,
title: enrichedData.job_title,
enrichment_source: enrichedData._clay_source,
});
// Process the enriched data (save to DB, trigger outreach, etc.)
res.json({ status: 'received', timestamp: new Date().toISOString() });
});
// Health check for Clay HTTP API column testing
app.get('/api/health', (req, res) => {
res.json({ status: 'ok', service: 'clay-dev-receiver' });
});
app.listen(3000, () => {
console.log('Clay dev receiver listening on http://localhost:3000');
console.log('Configure Clay HTTP API column to POST to: <ngrok-url>/api/clay/enriched');
});
Step 3: Build a Test Data Sender
// src/send-test-leads.ts — push test data into Clay via webhook
const CLAY_WEBHOOK_URL = process.env.CLAY_WEBHOOK_URL!;
const testLeads = [
{ email: '[email protected]', domain: 'stripe.com', source: 'dev-test' },
{ email: '[email protected]', domain: 'notion.so', source: 'dev-test' },
{ email: '[email protected]', domain: 'figma.com', source: 'dev-test' },
];
async function sendTestBatch() {
for (const lead of testLeads) {
const res = await fetch(CLAY_WEBHOOK_URL, {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify(lead),
});
console.log(`Sent ${lead.email}: ${res.status}`);
await new Promise(r => setTimeout(r, 200)); // Respect rate limits
}
console.log('\nCheck your Clay table — enrichment columns should auto-run.');
console.log('Enriched data will POST back to your ngrok endpoint.');
}
sendTestBatch();
Step 4: Configure Clay HTTP API Column to Call You Back
In your Clay table:
- Click + Add Column > HTTP API
- Set Method: POST
- Set URL:
https://your-ngrok-url.ngrok-free.app/api/clay/enriched - Set Body (JSON): Map enriched columns using Clay's
{{column_name}}syntax:
{
"email": "{{Email}}",
"company_name": "{{Company Name}}",
"job_title": "{{Job Title}}",
"employee_count": "{{Employee Count}}",
"linkedin_url": "{{LinkedIn URL}}"
}
- Enable Auto-run on new rows
Step 5: Dev Loop Iteration Cycle
# Terminal 1: Run ngrok
ngrok http 3000
# Terminal 2: Run your local receiver
npx tsx src/clay-receiver.ts
# Terminal 3: Send test data to Clay
npx tsx src/send-test-leads.ts
# Watch Terminal 2 for enriched data flowing back from Clay
Iteration cycle:
- Modify enrichment columns or Claygent prompts in Clay UI
- Re-send test data via webhook
- Observe enriched results in your local receiver
- Adjust and repeat
Step 6: Mock Clay Responses for Unit Tests
// tests/clay-webhook.test.ts — test without hitting Clay
import { describe, it, expect } from 'vitest';
const mockClayEnrichedPayload = {
email: '[email protected]',
company_name: 'Stripe',
employee_count: 8000,
industry: 'Financial Technology',
job_title: 'VP Engineering',
linkedin_url: 'https://linkedin.com/in/janedoe',
_clay_source: 'clearbit',
_clay_enriched_at: '2026-03-22T10:00:00Z',
};
describe('Clay enriched data handler', () => {
it('processes enriched lead correctly', async () => {
const res = await fetch('http://localhost:3000/api/clay/enriched', {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify(mockClayEnrichedPayload),
});
expect(res.status).toBe(200);
const body = await res.json();
expect(body.status).toBe('received');
});
});
Error Handling
| Issue | Cause | Solution |
|---|---|---|
| ngrok tunnel drops | Free tier session expired | Restart ngrok or upgrade to paid plan |
| Clay HTTP API column returns error | ngrok URL changed | Update the URL in Clay column settings |
| No data flows back | Auto-run disabled | Enable auto-run on the HTTP API column |
| Webhook returns 422 | Bad JSON in test data | Validate payload with jq . <<< '$JSON' |
| Enrichment columns empty | No provider configured | Add enrichment provider in Clay table |
Output
- Local server receiving enriched data from Clay
- Test data pipeline: local script -> Clay webhook -> enrichment -> HTTP API -> local server
- Unit tests with mocked Clay payloads
Resources
Next Steps
Once your dev loop works, see clay-sdk-patterns for production-ready integration patterns.
More by jeremylongshore
View all skills by jeremylongshore →You might also like
flutter-development
aj-geddes
Build beautiful cross-platform mobile apps with Flutter and Dart. Covers widgets, state management with Provider/BLoC, navigation, API integration, and material design.
drawio-diagrams-enhanced
jgtolentino
Create professional draw.io (diagrams.net) diagrams in XML format (.drawio files) with integrated PMP/PMBOK methodologies, extensive visual asset libraries, and industry-standard professional templates. Use this skill when users ask to create flowcharts, swimlane diagrams, cross-functional flowcharts, org charts, network diagrams, UML diagrams, BPMN, project management diagrams (WBS, Gantt, PERT, RACI), risk matrices, stakeholder maps, or any other visual diagram in draw.io format. This skill includes access to custom shape libraries for icons, clipart, and professional symbols.
ui-ux-pro-max
nextlevelbuilder
"UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 8 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient."
godot
bfollington
This skill should be used when working on Godot Engine projects. It provides specialized knowledge of Godot's file formats (.gd, .tscn, .tres), architecture patterns (component-based, signal-driven, resource-based), common pitfalls, validation tools, code templates, and CLI workflows. The `godot` command is available for running the game, validating scripts, importing resources, and exporting builds. Use this skill for tasks involving Godot game development, debugging scene/resource files, implementing game systems, or creating new Godot components.
nano-banana-pro
garg-aayush
Generate and edit images using Google's Nano Banana Pro (Gemini 3 Pro Image) API. Use when the user asks to generate, create, edit, modify, change, alter, or update images. Also use when user references an existing image file and asks to modify it in any way (e.g., "modify this image", "change the background", "replace X with Y"). Supports both text-to-image generation and image-to-image editing with configurable resolution (1K default, 2K, or 4K for high resolution). DO NOT read the image file first - use this skill directly with the --input-image parameter.
pdf-to-markdown
aliceisjustplaying
Convert entire PDF documents to clean, structured Markdown for full context loading. Use this skill when the user wants to extract ALL text from a PDF into context (not grep/search), when discussing or analyzing PDF content in full, when the user mentions "load the whole PDF", "bring the PDF into context", "read the entire PDF", or when partial extraction/grepping would miss important context. This is the preferred method for PDF text extraction over page-by-page or grep approaches.
Related MCP Servers
Browse all serversOfficial Laravel-focused MCP server for augmenting AI-powered local development. Provides deep context about your Larave
Foundry Toolkit: Deploy, test, and analyze smart contracts on EVM networks and local Anvil with powerful blockchain dev
Unlock AI-powered automation for Postman for API testing. Streamline workflows, code sync, and team collaboration with f
DebuggAI enables zero-config end to end testing for web applications, offering secure tunnels, easy setup, and detailed
Analyze your Cursor Chat History for coding insights, development patterns, and best practices with powerful search and
Simplify local cloud development with LocalStack tools to manage your container and related tasks. Ideal for Google Clou
Stay ahead of the MCP ecosystem
Get weekly updates on new skills and servers.