一个 Model Context Protocol (MCP) 服务器，用于将 AI 助手连接到 Leadloadz B2B 潜在客户开发平台。
搜索潜在客户 — 使用自然语言查询查找经过验证的 B2B 潜在客户
验证电子邮件 — 具有送达率评分的实时电子邮件验证
获取统计信息 — 查看您的使用情况和剩余配额
Related MCP server: LeadClaw
无需安装。AI 客户端可以直接运行该服务器：
npx -y @leadloadz/mcp-servernpm install -g @leadloadz/mcp-server
leadloadz-mcp您需要一个 Leadloadz API 密钥才能使用此服务器。
在 leadloadz.com 注册
前往 Dashboard → API Tokens
生成一个新令牌
复制令牌值
添加到您的 claude_desktop_config.json：
{
"mcpServers": {
"leadloadz": {
"command": "npx",
"args": ["-y", "@leadloadz/mcp-server"],
"env": {
"LEADLOADZ_API_KEY": "your-api-key-here"
}
}
}
}添加到您的 Cline MCP 设置中：
{
"mcpServers": {
"leadloadz": {
"command": "npx",
"args": ["-y", "@leadloadz/mcp-server"],
"env": {
"LEADLOADZ_API_KEY": "your-api-key-here"
}
}
}
}任何支持 stdio 传输的 MCP 客户端都可以使用：
{
"command": "npx",
"args": ["-y", "@leadloadz/mcp-server"],
"env": {
"LEADLOADZ_API_KEY": "your-api-key-here"
}
}变量 | 必需 | 默认值 | 描述 |
| 是 | — | 您的 Leadloadz API 令牌 |
| 否 |
| API 基础 URL |
| 否 |
| 请求超时时间（毫秒） |
# 安装依赖
npm install
# 构建
npm run build
# 类型检查
npm run typecheck
# 本地测试
node dist/index.js在以下情况下发布新版本：
添加新工具或更改现有工具架构
更改 API 端点行为，从而影响 MCP 响应
修复 MCP 服务器代码中的错误
更新依赖项（特别是 @modelcontextprotocol/sdk）
更改环境变量或配置选项
不要为以下更改发布版本：
主要的 Leadloadz Web 应用程序（这是单独的代码库）
Next.js 应用程序中的 API 路由（MCP 服务器代理到这些路由）
数据库架构（由主应用程序处理）
UI 组件或营销页面
根据需要编辑 src/ 中的文件。在本地测试：
npm run build
npm testnpm version patch # 用于错误修复
npm version minor # 用于新功能
npm version major # 用于重大更改如果您更改了版本，请更新 server.json 以匹配：
{
"version": "1.0.X",
"packages": [
{
"version": "1.0.X"
}
]
}git add .
git commit -m "Describe your changes"
git push origin masterecho "//registry.npmjs.org/:_authToken=YOUR_NPM_TOKEN" > .npmrc
npm publish --access public
rm -f .npmrc注意： npm 令牌以 npm_ 开头。请妥善保管，切勿提交。
每当您发布新的 npm 版本时，都需要更新 Anthropic MCP 注册表：
# 登录（令牌会过期，因此您可能每次都需要执行此操作）
./mcp-publisher login github
# 按照设备授权流程操作：
# 1. 前往 https://github.com/login/device
# 2. 输入显示的代码
# 3. 授权应用程序
# 发布
./mcp-publisher publish关键： package.json 中的 mcpName 必须与 server.json 中的 name 完全匹配（区分大小写）。目前两者都使用 io.github.Ali1041/leadloadz。
平台 | URL | 用途 |
npm | 包分发 | |
GitHub | 源代码 | |
Anthropic MCP Registry | Anthropic 官方目录 | |
Glama.ai | 社区目录 | |
PulseMCP | 社区目录 | |
Smithery.ai | 社区目录 | |
MCP.Directory | 社区目录 |
“Token expired”（令牌过期）错误：
重新运行 ./mcp-publisher login github
“You do not have permission”（您没有权限）错误：
确保 server.json 中的名称与您的 GitHub 用户名大小写匹配：io.github.Ali1041/leadloadz
确保 package.json 中的 mcpName 完全匹配
“Validation failed”（验证失败）错误：
描述必须 ≤ 100 个字符
必须包含 server.json 中的所有必需字段
npm 包必须已经以匹配的版本发布
您的 API 密钥永远不会被记录或在错误消息中泄露
所有错误都经过清理，以防止信息泄露
服务器通过 HTTPS 直接与 Leadloadz API 通信
速率限制由 Leadloadz API 强制执行
MIT
Read current usage counters: searches performed, emails verified, and remaining quota. Read-only. Requires API key. Rate limit: 30/min per user. Use before batch operations to check available allowance.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses read-only nature, API key requirement, and rate limit (30/min per user). No annotations exist, so the description carries full burden; it adequately covers behavioral traits for a safe read operation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three concise sentences front-load the purpose and add necessary behavioral info without redundancy. Every sentence adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Provides enough context for a parameterless tool: what it reads, when to use it, and constraints. Lacks details on return format, but acceptable for simple stats retrieval.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
No parameters in input schema, so baseline score is 4. Description does not need to add parameter information.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it reads usage counters (searches, emails, quota). It distinguishes itself from siblings 'search_leads' and 'verify_email' by specifying a different resource and action.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly advises to use before batch operations to check allowance. While it doesn't discuss when not to use or alternatives, the provided context is sufficient for a simple read tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search indexed B2B contacts by role, company, location, or technology. Read-only; returns verified leads with deliverability scores. Requires API key. Rate limit: 30/min per user. Use verify_email after discovery to confirm deliverability before outreach.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Specific natural-language search query. Narrow criteria yield better precision (e.g., 'CTOs at Series A B2B SaaS in London') | |
| limit | No | Maximum results to return. Default: 10. Cap: 50. Higher values consume more quota. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description fully covers behavioral traits: read-only, returns verified leads with deliverability scores, requires API key, and rate limit of 30/min per user.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three sentences, front-loaded with purpose, no wasted words. Each sentence adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a 2-param search tool with no output schema, the description adequately explains input (search criteria), behavior (read-only, deliverability scores), constraints (rate limit, API key), and follow-up action (verify_email). Complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% and schema descriptions already detail both parameters. The tool description adds no new parameter information beyond what's in the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states it searches indexed B2B contacts by role, company, location, or technology. Distinct from siblings get_user_stats and verify_email.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides guidance on when to use (searching leads) and recommends verify_email for further action. Lacks explicit when-not-to-use but implies context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Check email deliverability in real-time: MX records, SMTP, disposable/role detection. Read-only. Requires API key. Rate limit: 30/min per user. Use after search_leads or before sending campaigns. Returns deliverability score and risk assessment.
| Name | Required | Description | Default |
|---|---|---|---|
| Yes | Single email address to verify. Must be a valid RFC-like address format. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses read-only nature, API key requirement, and rate limit (30/min per user) without any annotations. Also describes return value (deliverability score and risk assessment).
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Concise, packing core purpose, behavior, guidelines, and return info into a few sentences. No wasted words, well front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Covers all essential aspects for a simple tool: purpose, behavior, auth, rate limit, usage context, and return summary. No gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Input schema already provides 100% coverage with description for 'email' parameter. Description does not add additional semantic detail beyond the schema, so baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states 'Check email deliverability in real-time' with specific checks (MX records, SMTP, disposable/role detection). Differentiates from siblings like get_user_stats and search_leads by focusing on email verification.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly says 'Use after search_leads or before sending campaigns', providing clear context. Lacks explicit exclusions or alternatives, but sufficiently guides usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.6get_user_statssearch_leadsverify_emailv1.0.5get_user_statssearch_leadsverify_emailv0.1.0get_user_statssearch_leadsverify_emailScored across 3 tools
Each tool serves a distinct purpose: usage stats, lead searching, and email verification. No functional overlap.
All tool names follow a consistent verb_noun pattern (get_user_stats, search_leads, verify_email).
Three tools is well-scoped for a lead generation and verification service, covering essential operations without redundancy.
The set covers the full workflow: check quota, search leads, and verify email deliverability. No missing critical operations given the read-only nature.
MCP server for Tomba email finder, verification, and contact enrichment API
Managed LinkedIn MCP server for AI agents: search, connect, message and enrich on accounts you own.
Hosted MCP for verified B2B lead campaigns with success-only billing.
Lead enrichment plus AI-written cold emails in one run.
