TAPAC MCP
A native MCP server for real-time B2B contact finding and SMTP email validation, scraping company websites, Discord, and Telegram to deliver live, verified contacts that AI agents like Claude and Cursor can query directly.
README
TAPAC — MCP Server for B2B Contact Finding
Find & verify B2B contacts in real time. Scrapes company websites, Discord, and Telegram — then validates every email via SMTP. Built as a native MCP server, so Claude, ChatGPT, Cursor, and any AI agent can call it directly.
Install in one command:
uvx --from git+https://github.com/axelfreeman/tapac-mcp tapac-mcpThen ask your agent: "Find 20 VP Sales at US SaaS companies with 50–500 employees."
Why TAPAC
Databases rot. 23% of contacts change jobs every year (ZoomInfo 2025), 40% of emails die within 2 years (NeverBounce). Buy a contact list and a quarter of it is stale before you send a single email.
TAPAC doesn't sell a database. It scrapes live and validates at request time:
| TAPAC | Static DBs (Apollo, ZoomInfo, Hunter) | |
|---|---|---|
| Data source | Real-time scraping | Frozen snapshot |
| Bounce rate | 2–5% | 10–35% |
| Validation | SMTP, in the moment | None / after the fact |
| MCP / AI agents | ✅ native | ❌ |
| Discord / Telegram | ✅ | ❌ |
| Pricing | Pay-per-use, $0.10–0.50/contact | $34–$15,000+/mo or /yr |
Quick Start
1. Install
uvx --from git+https://github.com/axelfreeman/tapac-mcp tapac-mcp
Requires uv (one-liner installer: curl -LsSf https://astral.sh/uv/install.sh | sh).
2. Wire into your agent
The same command + args work everywhere. Pick your agent:
Claude Desktop — claude_desktop_config.json:
{
"mcpServers": {
"tapac": {
"command": "uvx",
"args": ["--from", "git+https://github.com/axelfreeman/tapac-mcp", "tapac-mcp"]
}
}
}
Claude Code (terminal):
claude mcp add tapac -- uvx --from git+https://github.com/axelfreeman/tapac-mcp tapac-mcp
Codex (OpenAI) — ~/.codex/config.toml:
[mcp_servers.tapac]
command = "uvx"
args = ["--from", "git+https://github.com/axelfreeman/tapac-mcp", "tapac-mcp"]
Cursor — .cursor/mcp.json:
{
"mcpServers": {
"tapac": {
"command": "uvx",
"args": ["--from", "git+https://github.com/axelfreeman/tapac-mcp", "tapac-mcp"]
}
}
}
Windsurf — ~/.codeium/windsurf/mcp_config.json (same JSON as Cursor).
DeepSeek — the chat app doesn't register local MCP servers natively. Use DeepSeek through an MCP-capable client (Claude Code / Cursor with the DeepSeek API), or connect to the hosted endpoint https://tapacapi.com/mcp/sse (coming soon).
3. Get your free API key
First run points you to https://tapacapi.com/get-key. Set it once:
export TAPAC_API_KEY=your_key_here
4. Ask for contacts
"Find 20 VP Sales at US SaaS companies with 50–500 employees, verify emails."
The agent asks for the criteria it needs, calls tapac_find_contacts, and returns verified contacts (name, title, company, email, source, verification status).
100 free searches, no credit card.
Tools
tapac_find_contacts
Find and verify B2B contacts.
| Param | Type | Description |
|---|---|---|
industry |
string | Vertical, e.g. "SaaS", "healthcare", "fintech" |
job_titles |
string[] | Roles, e.g. ["VP Sales", "CTO"] |
company_size |
string | "50-500 employees", "startup", "enterprise" |
location |
string | "US", "Europe", "DACH", "remote" |
source |
string | website · telegram · discord |
limit |
int | How many contacts (default 10) |
tapac_status
Server version + API-key state.
Status
Beta. The install + tool interface + API-key onboarding are live. The full scrape → SMTP-validation engine is being wired in — it ships next. Until then, tapac_find_contacts captures your target and returns a clear beta response, so you can install and look inside the product today.
Links
- Website: https://tapacapi.com
- Deep Research Guide: https://tapacapi.com/deep-research-guide.html
- Free toolkit (self-hosted): https://github.com/axelfreeman/b2b-contact-mining-kit
- Author: Axel Freeman
License
MIT.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.