TAPAC MCP
TAPAC — B2B 联系人查找 MCP 服务器
实时查找并验证 B2B 联系人。 抓取公司网站、Discord 和 Telegram —— 然后通过 SMTP 验证每封电子邮件。作为原生 MCP 服务器构建,Claude、ChatGPT、Cursor 以及任何 AI 代理均可直接调用。
一条命令安装:
uvx --from git+https://github.com/axelfreeman/tapac-mcp tapac-mcp然后询问你的代理:"查找 20 位美国 SaaS 公司(50–500 名员工)的销售副总裁,并验证邮箱。"
为什么选择 TAPAC
数据库会腐烂。每年有 23% 的联系人更换工作(ZoomInfo 2025),40% 的电子邮件在 2 年内失效(NeverBounce)。购买一份联系人名单,在你发送第一封邮件之前,已有四分之一过时。
TAPAC 不销售数据库。它实时抓取并在请求时验证:
TAPAC | 静态数据库(Apollo, ZoomInfo, Hunter) | |
数据源 | 实时抓取 | 冻结快照 |
退信率 | 2–5% | 10–35% |
验证 | SMTP,即时验证 | 无 / 事后验证 |
MCP / AI 代理 | ✅ 原生 | ❌ |
Discord / Telegram | ✅ | ❌ |
定价 | 按使用付费,$0.10–0.50/联系人 | $34–$15,000+/月或/年 |
Related MCP server: Bytemine MCP Server - Contact Search & Enrich
快速开始
1. 安装
uvx --from git+https://github.com/axelfreeman/tapac-mcp tapac-mcp需要 uv(一行命令安装:curl -LsSf https://astral.sh/uv/install.sh | sh)。
2. 接入你的代理
相同的 command + args 可在任何环境中使用。选择你的代理:
Claude Desktop — claude_desktop_config.json:
{
"mcpServers": {
"tapac": {
"command": "uvx",
"args": ["--from", "git+https://github.com/axelfreeman/tapac-mcp", "tapac-mcp"]
}
}
}Claude Code(终端):
claude mcp add tapac -- uvx --from git+https://github.com/axelfreeman/tapac-mcp tapac-mcpCodex (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(与 Cursor 相同的 JSON)。
DeepSeek — 聊天应用原生不支持注册本地 MCP 服务器。通过支持 MCP 的客户端(使用 DeepSeek API 的 Claude Code / Cursor)使用 DeepSeek,或连接到托管端点 https://tapacapi.com/mcp/sse(即将推出)。
3. 获取免费 API 密钥
首次运行将跳转到 https://tapacapi.com/get-key。设置一次:
export TAPAC_API_KEY=your_key_here4. 搜索联系人
"查找 20 位美国 SaaS 公司(50–500 名员工)的销售副总裁,验证邮箱。"
代理会询问所需条件,调用 tapac_find_contacts,并返回已验证的联系人(姓名、职位、公司、邮箱、来源、验证状态)。
100 次免费搜索,无需信用卡。
工具
tapac_find_contacts
查找并验证 B2B 联系人。
参数 | 类型 | 描述 |
| string | 垂直行业,例如 "SaaS"、"healthcare"、"fintech" |
| string[] | 职位,例如 |
| string | "50-500 employees"、"startup"、"enterprise" |
| string | "US"、"Europe"、"DACH"、"remote" |
| string |
|
| int | 返回联系人数量(默认 10) |
tapac_status
服务器版本 + API 密钥状态。
状态
测试版。 安装、工具接口和 API 密钥注册现已上线。完整的抓取 → SMTP 验证引擎正在接入中——即将推出。在此之前,tapac_find_contacts 会捕获你的目标并返回清晰的测试版响应,以便你今天即可安装并了解产品内部。
链接
许可证
MIT。
Available Tools
2 toolstapac_find_contactsA
Find and verify B2B business contacts in real time.
Ask the user for these criteria before calling:
industry: vertical, e.g. "SaaS", "healthcare", "fintech"
job_titles: roles, e.g. ["VP Sales", "CTO", "Head of Growth"]
company_size: e.g. "50-500 employees", "startup", "enterprise"
location: geography, e.g. "US", "Europe", "DACH", "remote"
source: where to search — "website", "telegram", or "discord"
limit: how many contacts to return (default 10)
Returns verified contacts (name, title, company, email, source, verification status) as structured data.
Inputs: limit, source, industry, location, +2 more. Returns: result
tapac_statusA
Check TAPAC server status, version, and API-key state.
Inputs: no named parameters. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 2 tools
The two tools serve completely distinct purposes: one checks server status, the other finds contacts. There is no overlap or ambiguity.
Both tools follow a consistent snake_case pattern with the prefix 'tapac_', one describing a state (status) and the other an action (find_contacts). The naming is uniform.
With only two tools, the server feels thin for a contact-finding service, but each tool is clearly defined and serves a necessary function. It is borderline but not excessive.
The server covers the core operation of finding and verifying contacts with extensive filtering, plus a status check. Minor gaps like retrieving a specific contact by ID are absent, but the main workflow is complete.
Maintenance
Related MCP Connectors
Sales MCP server for AI agents: find, enrich, score and reach leads on LinkedIn, track replies.
Managed LinkedIn MCP server for AI agents: search, connect, message and enrich on accounts you own.
LinkedIn outreach MCP server — 19 tools for AI agents to prospect, sequence, and manage contacts.
Unlimited B2B Contact Data for AI Agents, Starting from $29/mo. Remote MCP server with eight tools: search_people, search_companies, enrich_person, enrich_company, verify_email, scrape_jobs, scrape_company, get_usage. Results include match reasons, email verification status and checked_at dates. Sign in with OAuth. Flat pricing with a free tier of 1,000 records.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceAn MCP server providing real-time access to comprehensive B2B company and contact data for lead generation and business intelligence. It enables AI tools to search firmographics, discover key contacts, and automate personalized outreach workflows.294MIT
- FlicenseNot gradedqualityDmaintenanceBytemine MCP Server – Search 130M+ B2B contacts and enrich profiles with verified emails & phone numbers directly from Claude, Cursor, and other AI assistants via the Model Context Protocol.4-
- AlicenseNot gradedqualityDmaintenanceMCP server giving AI agents real-time web search, page scraping, company intelligence, email discovery, local lead generation, and a persistent knowledge graph. Pay only for what you use, no subscriptions.MIT
- AlicenseNot gradedqualityBmaintenanceMCP server that enables AI agents to discover and qualify B2B leads from Leadbay's knowledge base, with tools for lead research, enrichment, and outreach logging.MIT