快速查找损坏的联盟链接，按影响程度排序，并生成 AI 代理可执行的修复建议。
一次调用。检查 38+ 个联盟网络。预估收入损失。
一键安装： 在 MCPize 上安装 |
pip install linkrescue-mcp
LinkRescue MCP 通过模型上下文协议 (MCP) 提供断链扫描、监控和修复工作流，使 Claude 和 Cursor 等工具能够直接运行链接健康检查操作。
check_broken_links：扫描 URL（或站点地图）并返回结构化的断链报告
monitor_links：为网站设置定期监控
get_fix_suggestions：生成优先级的修复建议
health_check：验证 MCP 服务器和后端 API 的连接性
如果 LinkRescue 后端 API 无法访问，服务器将回退到真实的模拟数据，以便本地测试和演示能够继续运行。
Related MCP server: webcheck-mcp
{
"mcpServers": {
"linkrescue": {
"command": "linkrescue-mcp"
}
}
}然后询问你的 AI 代理：
"Scan example.com for broken affiliate links"
工具 | 免费版 | 专业版 ($19/月) | 代理版 ($29/月) |
| 是 | 是 | 是 |
| 是 | 是 | 是 |
| - | 是 | 是 |
| - | - | 是 |
| - | 是 | 是 |
| - | 是 | 是 |
| - | - | 是 |
收入损失预估 | - | 是 | 是 |
多站点监控 | - | 5 个站点 | 25 个站点 |
免费版提供单页断链检查。专业版解锁完整的爬虫 + 修复建议 + 定期监控。代理版增加了每小时检查、Webhooks 和无限站点数量。
在 MCPize 上升级到专业版 — $19/月 或 $190/年。代理版 $29/月 或 $290/年。
通过托管服务一键安装：在 MCPize 上安装
pip install linkrescue-mcp
linkrescue-mcpgit clone https://github.com/carsonroell-debug/linkrescue-mcp.git
cd linkrescue-mcp
pip install -r requirements.txt
python main.pyMCP 端点：
http://localhost:8000/mcp
变量 | 描述 | 默认值 |
| LinkRescue API 的基础 URL |
|
| 用于认证请求的 API 密钥 | 空 |
示例：
export LINKRESCUE_API_BASE_URL="https://www.linkrescue.io/api/v1"
export LINKRESCUE_API_KEY="your-api-key"
linkrescue-mcp在 linkrescue.io/settings/api 获取 API 密钥（仅限专业版和代理版）。
通过已安装的入口点运行：
linkrescue-mcp直接从源码运行：
python main.py通过 FastMCP CLI 运行：
fastmcp run main.py --transport streamable-http --port 8000将其添加到 claude_desktop_config.json：
{
"mcpServers": {
"linkrescue": {
"command": "linkrescue-mcp"
}
}
}claude mcp add linkrescue --transport http http://localhost:8000/mcpfastmcp list-tools main.py
fastmcp call-tool main.py health_check '{}'
fastmcp call-tool main.py check_broken_links '{"url":"https://example.com"}'check_broken_links输入：
url (必填)：要扫描的网站 URL
sitemap_url (可选，代理版)：从站点地图爬取
max_depth (可选，默认 3)：爬取深度
返回扫描元数据、断链详情和汇总统计信息。专业版和代理版包含断链联盟链接的预估月收入损失。
monitor_links输入：
url (必填)
frequency_hours (可选，默认 24；代理版支持 1)
返回监控 ID、计划详情和状态。免费版返回模拟监控（无持久化）。
get_fix_suggestions输入：
来自 check_broken_links 的完整报告，或
原始 broken_links 数组，或
任意格式的 JSON 字符串
返回优先级的操作和建议的修复步骤。仅限专业版和代理版。
health_check无输入。返回服务器状态和后端 API 可达性。
此仓库包含 smithery.yaml 和 smithery.json。
将仓库推送到 GitHub
在 Smithery 中创建/添加服务器
将 Smithery 指向此仓库
包含一个用于 Railway、Fly.io 和其他容器主机的 Dockerfile。
# Railway
railway up
# Fly.io
fly launch
fly deploy在你的主机环境中设置 LINKRESCUE_API_BASE_URL 和 LINKRESCUE_API_KEY。
Agent (Claude, Cursor, etc.)
-> MCP
LinkRescue MCP Server (this repo)
-> HTTP API
LinkRescue Backend API (linkrescue.io)此服务器是 MCP 工具调用与 LinkRescue API 操作之间的转换层。
MIT — 由 Freedom Engineers 构建
SelfHeal MCP — MCP 服务器的自愈代理
SiteHealth MCP — 全站健康审计
LeadEnrich MCP — 瀑布流线索丰富化
开发者专注版本：README.dev.md
市场专注版本：README.marketplace.md
Scans a single URL or entire site/sitemap for broken links.
Returns a structured report with every broken link found, its HTTP status code, the page it was discovered on, link type (affiliate/external/internal), SEO impact rating, and estimated revenue loss.
Agents can pass the output directly to get_fix_suggestions for remediation steps.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | The website URL to scan (e.g. "https://example.com"). | |
| sitemap_url | No | Optional sitemap URL to crawl instead of discovering pages by depth. | |
| max_depth | No | How many levels deep to crawl from the start URL. Default 3. |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It describes the output format well ('structured report with every broken link found...') and mentions integration with another tool. However, it doesn't cover important behavioral aspects like rate limits, authentication needs, execution time, or error handling for a scanning tool that could be resource-intensive.
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 perfectly structured and concise - three sentences that each earn their place. The first states the purpose, the second details the output, and the third provides integration guidance. No wasted words, front-loaded with the core functionality.
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 the tool has an output schema (mentioned in context signals), the description doesn't need to explain return values in detail. It provides good context about the scanning scope and output integration. However, for a scanning tool with no annotations, it could better address behavioral aspects like performance characteristics or limitations.
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 description coverage is 100%, so the schema already fully documents all 3 parameters. The description adds no additional parameter information beyond what's in the schema. The baseline score of 3 is appropriate when the schema does all the parameter documentation work.
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 with specific verbs ('scans', 'returns') and resources ('URL or entire site/sitemap', 'broken links'). It distinguishes from siblings by mentioning the specific output format and direct integration with get_fix_suggestions, which differentiates it from health_check and monitor_links.
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 clear context about when to use this tool ('scans a single URL or entire site/sitemap for broken links') and mentions integration with get_fix_suggestions for remediation. However, it doesn't explicitly state when NOT to use it or provide alternatives among siblings like health_check or monitor_links.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Given a broken links report, returns prioritized remediation suggestions.
Each suggestion includes the broken URL, a recommended action (update link, follow redirect, remove, etc.), a human-readable explanation, and a code snippet where applicable.
Accepts either the full JSON report from check_broken_links or just the broken_links array.
| Name | Required | Description | Default |
|---|---|---|---|
| broken_links_report | Yes | The scan report (JSON string or dict) from check_broken_links. |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden. It discloses the tool's output format (prioritized suggestions with specific fields) and input flexibility (accepts full JSON or just array). However, it doesn't mention performance characteristics, error handling, or whether this is a read-only operation (though implied by 'returns').
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 perfectly front-loaded with the core purpose in the first sentence, followed by details about output format and input flexibility. Every sentence adds value with zero waste. The structure flows logically from purpose to output details to input requirements.
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 the tool has an output schema (which covers return values), no annotations, and 100% schema coverage, the description provides good context about purpose, usage, and behavioral aspects. However, for a tool that processes potentially complex broken link data, more detail about prioritization logic or suggestion criteria would enhance completeness.
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 description coverage is 100%, so the baseline is 3. The description adds meaningful context by explaining the parameter accepts either 'the full JSON report from check_broken_links or just the broken_links array' - clarifying format flexibility beyond what the schema's 'anyOf' indicates. This elevates the score above baseline.
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 with specific verbs ('returns prioritized remediation suggestions') and resources ('broken links report'). It distinguishes from sibling tools by specifying it processes output from 'check_broken_links' rather than performing scanning or monitoring itself.
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 clear context for when to use this tool ('Given a broken links report') and mentions the specific sibling tool 'check_broken_links' as the source. However, it doesn't explicitly state when NOT to use it or mention alternatives among the other siblings like 'health_check' or 'monitor_links'.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Confirms the LinkRescue MCP server is alive and can reach the backend API.
Use this to verify connectivity before running scans. Returns server status, API reachability, and current configuration.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden and does well by disclosing what the tool returns ('server status, API reachability, and current configuration') and its verification purpose. It doesn't mention error behavior or performance characteristics, but provides solid operational context.
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?
Perfectly structured with two sentences: first states purpose, second provides usage guidance and return values. Every word earns its place with zero redundancy or wasted text.
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?
Complete for a zero-parameter health check tool with output schema. The description explains what it does, when to use it, and what it returns - covering all necessary context given the tool's simplicity and available structured data.
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?
The tool has zero parameters with 100% schema coverage, so baseline is 4. The description appropriately doesn't discuss parameters since none exist, focusing instead on the tool's purpose and output.
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 with specific verbs ('confirms', 'verify connectivity') and resources ('LinkRescue MCP server', 'backend API'). It distinguishes from siblings by focusing on server health rather than link scanning or monitoring operations.
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 states when to use this tool ('before running scans') and provides clear context about its verification purpose. The description distinguishes it from sibling tools that perform actual link operations rather than connectivity checks.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Sets up ongoing broken-link monitoring for a website.
The monitor runs on a schedule (default: every 24 hours) and will detect new broken links, links that were fixed, and changes in site health score.
Returns a monitoring_id you can reference later to check status or cancel.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | The website URL to monitor. | |
| frequency_hours | No | How often to re-scan, in hours. Default 24. |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden and does well by disclosing key behavioral traits: it's a setup/creation tool (implies mutation), runs on a schedule with a default frequency, detects specific changes (new broken links, fixed links, health score changes), and returns a monitoring_id for future reference. It doesn't mention permissions, rate limits, or error handling, but covers core behavior adequately.
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 appropriately sized and front-loaded: the first sentence states the core purpose, followed by details on schedule and detection scope, ending with return value. Every sentence adds value with zero waste, making it easy for an agent to parse quickly.
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 the tool's moderate complexity (setup of ongoing monitoring), no annotations, 100% schema coverage, and the presence of an output schema (implied by 'Returns a monitoring_id'), the description is complete enough. It explains what the tool does, how it behaves, and the return value, leaving schema details to structured fields.
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 description coverage is 100%, so the schema already fully documents both parameters (url and frequency_hours). The description adds no additional parameter semantics beyond what's in the schema, such as URL format constraints or frequency limits. Baseline 3 is appropriate when schema does the heavy lifting.
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 with specific verbs ('Sets up ongoing broken-link monitoring') and identifies the resource ('for a website'). It distinguishes from sibling tools like 'check_broken_links' (one-time check) by emphasizing ongoing monitoring on a schedule.
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 clear context for when to use this tool (ongoing monitoring vs. one-time checks) and implies alternatives through sibling tool names like 'check_broken_links'. However, it doesn't explicitly state when NOT to use it or directly compare to all siblings.
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.
v0.1.1check_broken_linksget_fix_suggestionshealth_checkmonitor_linksScored across 4 tools
Each tool has a clearly distinct purpose: check_broken_links for scanning, get_fix_suggestions for remediation, health_check for connectivity, and monitor_links for ongoing monitoring. There is no overlap or ambiguity in their functions.
The tools follow a consistent verb_noun pattern (check_broken_links, get_fix_suggestions, monitor_links), with one minor deviation (health_check uses noun_verb). This is mostly consistent and readable.
With 4 tools, the server is well-scoped for its purpose of broken link detection and management. Each tool earns its place, covering scanning, remediation, monitoring, and health checks without being too sparse or bloated.
The tool set provides complete coverage for the domain: check_broken_links for detection, get_fix_suggestions for remediation, monitor_links for ongoing tracking, and health_check for connectivity. There are no obvious gaps, and agents can follow a full workflow from scan to fix to monitoring.
Security, SEO and AI-visibility scanner for web apps · free scans and focused checks via MCP.
SEO MCP server: crawl your site, find AI-visibility gaps, and ship the fix from your coding agent.
Crawl a site for broken links, 404s, dead images, redirect chains and slow pages, with sources
Monitor MCP servers, API contracts and AI outputs for schema drift. Alerts on breaking changes.
