Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Website Contacts Scraper scrape contacts from wsgr.com and other.com"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
用于访问 Website Contacts Scraper API 的 MCP 服务器。
EMCP 是一个强大的 MCP 服务器管理平台，让您无需手动配置即可快速使用各种 MCP 服务器！
🌐 访问 EMCP 平台
📝 注册并登录账号
🎯 进入 MCP 广场，浏览所有可用的 MCP 服务器
🔍 搜索或找到本服务器（bach-website_contacts_scraper）
🎉 点击 "安装 MCP" 按钮
✅ 完成！即可在您的应用中使用
✨ 零配置：无需手动编辑配置文件
🎨 可视化管理：图形界面轻松管理所有 MCP 服务器
🔐 安全可靠：统一管理 API 密钥和认证信息
🚀 一键安装：MCP 广场提供丰富的服务器选择
📊 使用统计：实时查看服务调用情况
立即访问 EMCP 平台 开始您的 MCP 之旅！
Related MCP server: MCP WebSearch Server
这是一个 MCP 服务器，用于访问 Website Contacts Scraper API。
PyPI 包名: bach-website_contacts_scraper
版本: 1.0.0
传输协议: stdio
pip install bach-website_contacts_scraperpip install -e .# 运行（uvx 会自动安装并运行）
uvx --from bach-website_contacts_scraper bach_website_contacts_scraper
# 或指定版本
uvx --from bach-website_contacts_scraper@latest bach_website_contacts_scraperpython server.py# 安装
pip install bach-website_contacts_scraper
# 运行（命令名使用下划线）
bach_website_contacts_scraper此 API 需要认证。请设置环境变量:
export API_KEY="your_api_key_here"变量名 | 说明 | 必需 |
| API 密钥 | 是 |
| 不适用 | 否 |
| 不适用 | 否 |
编辑 Cursor MCP 配置文件 ~/.cursor/mcp.json:
{
"mcpServers": {
"bach-website_contacts_scraper": {
"command": "uvx",
"args": ["--from", "bach-website_contacts_scraper", "bach_website_contacts_scraper"],
"env": {
"API_KEY": "your_api_key_here"
}
}
}
}编辑 Claude Desktop 配置文件 claude_desktop_config.json:
{
"mcpServers": {
"bach-website_contacts_scraper": {
"command": "uvx",
"args": ["--from", "bach-website_contacts_scraper", "bach_website_contacts_scraper"],
"env": {
"API_KEY": "your_api_key_here"
}
}
}
}此服务器提供以下工具:
scrape_contacts_from_websiteScrape emails, phone numbers, and social profile links from a website root domain. Supports batching of up to 20 domains in a single request. Note that by default, the emals returned by the endpoint are not restricted to match the website domain (after the \
端点: GET /scrape-contacts
参数:
query (string) 必需: Domain from which to scrape emails and contacts (e.g. wsgr.com). Accepts any valid url and uses its root domain as a starting point for the extraction. Support batching of up to 20 domains in a single request, separated by comma (e.g. wsgr.com,other.com). Please note that each domain in the request will consume a request credit from the quota.
match_email_domain (string): Example value:
external_matching (string): Example value:
get_website_by_keywordGet company website URL by keyword / company name. Up to 20 keywords are supported in a single query. This endpoint can be used in case you only have a company name and need to get the website domain before scraping emails and contacts from it.
端点: POST /website-url-by-keyword
传输协议: stdio
HTTP 客户端: httpx
MIT License - 详见 LICENSE 文件。
此服务器由 API-to-MCP 工具生成。
版本: 1.0.0
Get company website URL by keyword / company name. Up to 20 keywords are supported in a single query. This endpoint can be used in case you only have a company name and need to get the website domain before scraping emails and contacts from it.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description bears full responsibility for behavioral disclosure. It claims support for 'up to 20 keywords' but the input schema has no parameters, creating a contradiction. No other behavioral traits (e.g., auth needs, rate limits, error behavior) are mentioned.
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?
The description is relatively concise (three sentences) but includes information that contradicts the schema, reducing its effectiveness. It is front-loaded with the core purpose but the mismatch undermines its 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?
Given no output schema, the description does not explain return values or possible error cases. It provides some context via the sibling tool mention, but the missing parameter definition makes it incomplete for an agent to use reliably.
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% but the schema defines zero parameters. The description adds information about keywords that is not reflected in the schema, causing confusion. It does not clarify how to pass the keywords when the schema has no parameters.
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 the tool's purpose: getting a company website URL by keyword or company name. It distinguishes itself from the sibling tool 'scrape_contacts_from_website' by noting it is used to obtain the domain before scraping contacts.
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?
The description provides explicit usage guidance: it can be used when only a company name is known and the website domain is needed before scraping contacts. It also mentions that up to 20 keywords are supported per query, but does not specify when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Scrape emails, phone numbers, and social profile links from a website root domain. Supports batching of up to 20 domains in a single request. Note that by default, the emals returned by the endpoint are not restricted to match the website domain (after the \
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Domain from which to scrape emails and contacts (e.g. wsgr.com). Accepts any valid url and uses its root domain as a starting point for the extraction. Support batching of up to 20 domains in a single request, separated by comma (e.g. wsgr.com,other.com). Please note that each domain in the request will consume a request credit from the quota. | |
| match_email_domain | No | Example value: | |
| external_matching | No | Example value: |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses batching behavior and a default email restriction, but without annotations it should provide more behavioral context (e.g., rate limits, auth requirements, read-only nature). The note is incomplete due to truncation, reducing transparency.
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?
The description is concise and front-loaded, but appears truncated at the end (note cut off), which detracts from clarity. Otherwise, efficient in word count.
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?
Given no output schema and three parameters (two poorly described), the description lacks critical information on return format, error handling, or rate limits. The truncated note suggests incomplete context for the optional parameters.
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?
Despite 100% schema coverage, the descriptions for 'match_email_domain' and 'external_matching' are unhelpful ('Example value: '), adding no meaning beyond parameter names. The main parameter 'query' is adequately described in the description but not linked to schema details.
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 scrapes emails, phone numbers, and social profile links from a website root domain, distinguishing it from the sibling tool 'get_website_by_keyword' which likely finds websites by keyword rather than extracting contacts.
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?
The description mentions batching up to 20 domains and a note about email domain restriction, providing context for when to use the tool. However, it does not explicitly state when to use this tool over the sibling or when not to use it.
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. Dates show when Glama detected each change.
v1.0.0get_website_by_keywordscrape_contacts_from_websiteThe two tools have clearly distinct purposes: one retrieves a website URL from a keyword, the other scrapes contacts from a given domain. No overlap or ambiguity.
Both tools follow a consistent verb_noun pattern using snake_case: get_website_by_keyword and scrape_contacts_from_website. Perfectly predictable.
With only two tools, the server is minimal but focused. For a website contacts scraper, this covers the core workflow. A few more tools (e.g., email verification) could enhance completeness, but the count is reasonable.
The tools cover the essential lifecycle: finding a website from a company name and then scraping contacts from it. There are no obvious gaps for the stated purpose of scraping emails, phones, and social profiles from root domains.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Find verified B2B emails and phone numbers; search and enrich people and companies for prospecting.
B2B sales intelligence: find companies, extract leads, enrich contacts with emails/phones.
Search B2B contacts, enrich verified emails and phone numbers, and export results.
Find verified work emails from a name, company, role or LinkedIn URL, and verify emails you have.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/BACH-AI-Tools/bachai-website-contacts-scraper'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
