Skip to main content
Glama
enesjakozh
w0h1v

mcp-shodan

by w0h1v
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Shodan MCP 服务器

铁匠徽章

用于查询Shodan API和Shodan CVEDB 的模型上下文协议 (MCP) 服务器。该服务器提供对 Shodan 网络情报和安全服务的全面访问，包括 IP 侦察、DNS 操作、漏洞追踪和设备发现。所有工具均提供结构化、格式化的输出，方便分析和集成。

快速启动（推荐）

通过 Smithery 安装

要通过Smithery自动为 Claude Desktop 安装 Shodan 服务器：

npx -y @smithery/cli install @burtthecoder/mcp-shodan --client claude

手动安装

  1. 通过 npm 全局安装服务器：

npm install -g @burtthecoder/mcp-shodan

  1. 添加到您的 Claude Desktop 配置文件：

{
  "mcpServers": {
    "shodan": {
      "command": "mcp-shodan",
      "env": {
        "SHODAN_API_KEY": "your-shodan-api-key"
      }
    }
  }
}

配置文件位置：

  • macOS： ~/Library/Application Support/Claude/claude_desktop_config.json

  • Windows： %APPDATA%\Claude\claude_desktop_config.json

  1. 重启Claude桌面

Related MCP server: Shodan-MCP-Server

替代设置（来自源）

如果您希望从源代码运行或需要修改代码：

  1. 克隆并构建：

git clone https://github.com/BurtTheCoder/mcp-shodan.git
cd mcp-shodan
npm install
npm run build

  1. 添加到您的 Claude Desktop 配置：

{
  "mcpServers": {
    "shodan": {
      "command": "node",
      "args": ["/absolute/path/to/mcp-shodan/build/index.js"],
      "env": {
        "SHODAN_API_KEY": "your-shodan-api-key"
      }
    }
  }
}

特征

  • 网络侦察：查询IP地址的详细信息，包括开放端口、服务和漏洞

  • DNS 操作：域和 IP 地址的正向和反向 DNS 查找

  • 漏洞情报：访问 Shodan 的 CVEDB 获取详细的漏洞信息、CPE 查找和特定于产品的 CVE 跟踪

  • 设备发现：使用高级过滤功能搜索 Shodan 的互联网连接设备数据库

工具

1. IP查找工具

  • 名称： ip_lookup

  • 描述：检索有关 IP 地址的综合信息，包括地理位置、开放端口、正在运行的服务、SSL 证书、主机名和云提供商详细信息（如果可用）

  • 参数：

    • ip （必填）：要查找的 IP 地址

  • 返回：

    • IP 信息（地址、组织、ISP、ASN）

    • 位置（国家、城市、坐标）

    • 服务（端口、协议、横幅）

    • 云提供商详细信息（如果有）

    • 关联的主机名和域

    • 标签

2. Shodan 搜索工具

  • 名称： shodan_search

  • 描述：搜索 Shodan 的互联网连接设备数据库

  • 参数：

    • query （必填）：Shodan 搜索查询

    • max_results （可选，默认值：10）：返回的结果数

  • 返回：

    • 包含总结果的搜索摘要

    • 基于国家的分布统计数据

    • 详细的设备信息包括：

      • 基本信息（IP、组织、ISP）

      • 位置数据

      • 服务详情

      • Web 服务器信息

      • 关联的主机名和域

3. CVE 查找工具

  • 名称： cve_lookup

  • 描述：从 Shodan 的 CVEDB 查询详细的漏洞信息

  • 参数：

    • cve （必填）：CVE 标识符，格式为 CVE-YYYY-NNNNN（例如，CVE-2021-44228）

  • 返回：

    • 基本信息（ID、发布日期、摘要）

    • 严重程度评分：

      • CVSS v2 和 v3 及其严重性等级

      • EPSS概率和排序

    • 影响评估：

      • KEV 状态

      • 建议的缓解措施

      • 勒索软件协会

    • 受影响的产品（CPE）

    • 参考

4. DNS查找工具

  • 名称： dns_lookup

  • 描述：使用 Shodan 的 DNS 服务将域名解析为 IP 地址

  • 参数：

    • hostnames （必需）：要解析的主机名数组

  • 返回：

    • DNS 解析将主机名映射到 IP

    • 总查找次数和查询主机名的摘要

5.反向DNS查找工具

  • 名称： reverse_dns_lookup

  • 描述：执行反向 DNS 查找以查找与 IP 地址关联的主机名

  • 参数：

    • ips （必需）：要查找的 IP 地址数组

  • 返回：

    • 将 IP 映射到主机名的反向 DNS 解析

    • 总查找次数和结果摘要

6. CPE查询工具

  • 名称： cpe_lookup

  • 描述：按产品名称搜索通用平台枚举（CPE）条目

  • 参数：

    • product （必填）：要搜索的产品名称

    • count （可选，默认值：false）：如果为 true，则仅返回匹配的 CPE 的数量

    • skip （可选，默认值：0）：要跳过的 CPE 数量（用于分页）

    • limit （可选，默认值：1000）：返回的最大 CPE 数量

  • 返回：

    • 当 count 为 true 时：匹配的 CPE 总数

    • 当 count 为 false 时：包含分页详细信息的 CPE 列表

7. 按产品工具分类的 CVE

  • 名称： cves_by_product

  • 描述：搜索影响特定产品或 CPE 的漏洞

  • 参数：

    • cpe23 （可选）：CPE 2.3 标识符（格式：cpe:2.3:part:vendor:product:version）

    • product （可选）：要搜索 CVE 的产品名称

    • count （可选，默认值：false）：如果为 true，则仅返回匹配的 CVE 的数量

    • is_kev （可选，默认值：false）：如果为 true，则仅返回设置了 KEV 标志的 CVE

    • sort_by_epss （可选，默认值：false）：如果为 true，则按 EPSS 分数对 CVE 进行排序

    • skip （可选，默认值：0）：要跳过的 CVE 数量（用于分页）

    • limit （可选，默认值：1000）：返回的最大 CVE 数量

    • start_date （可选）：过滤 CVE 的开始日期（格式：YYYY-MM-DDTHH:MM:SS）

    • end_date （可选）：过滤 CVE 的结束日期（格式：YYYY-MM-DDTHH:MM:SS）

  • 笔记：

    • 必须提供 cpe23 或产品，但不能同时提供两者

    • 日期过滤使用 CVE 的发布时间

  • 返回：

    • 查询信息

    • 带有分页详细信息的结果摘要

    • 详细的漏洞信息包括：

      • 基本信息

      • 严重程度评分

      • 影响评估

      • 参考

要求

故障排除

API 密钥问题

如果您看到与 API 密钥相关的错误（例如“请求失败，状态代码为 401”）：

  1. 验证您的 API 密钥：

    • 必须是您帐户设置中的有效 Shodan API 密钥

    • 确保密钥具有足够的信用/权限以执行操作

    • 检查配置中键周围是否有多余的空格或引号

    • 验证密钥是否在 SHODAN_API_KEY 环境变量中正确设置

  2. 常见错误代码：

    • 401 未授权：无效的 API 密钥或缺少身份验证

    • 402 需要付款：超出查询信用额度

    • 429 请求过多：超出速率限制

  3. 配置步骤：a. 从Shodan 帐户获取您的 API 密钥 b. 将其添加到您的配置文件：

    {
  "mcpServers": {
    "shodan": {
      "command": "mcp-shodan",
      "env": {
        "SHODAN_API_KEY": "your-actual-api-key-here"
      }
    }
  }
}

    c. 保存配置文件 d. 重启 Claude Desktop

  4. 测试您的密钥：

    • 首先尝试一个简单的查询（例如，dns_lookup 查找“google.com”）

    • 检查您的Shodan 帐户仪表板以了解信用状况

    • 验证密钥是否可以直接与 curl 一起使用：

      curl "https://api.shodan.io/dns/resolve?hostnames=google.com&key=your-api-key"

模块加载问题

如果您看到模块加载错误：

  1. 对于全局安装：使用快速入门中显示的简单配置

  2. 对于源安装：确保您使用的是 Node.js v18 或更高版本

发展

要在开发模式下使用热重载运行：

npm run dev

错误处理

该服务器包括针对以下方面的全面错误处理：

  • 无效的 API 密钥

  • 速率限制

  • 网络错误

  • 输入参数无效

  • 无效的 CVE 格式

  • CPE 查找参数无效

  • 无效的日期格式

  • 互斥参数验证

版本历史记录

  • v1.0.12：添加反向 DNS 查找并改进输出格式

  • v1.0.7：添加了按产品搜索 CVE 的功能，并将漏洞工具重命名为 cve_lookup

  • v1.0.6：添加了 CVEDB 集成，以增强 CVE 查找和 CPE 搜索功能

  • v1.0.0：具有核心功能的初始版本

贡献

  1. 分叉存储库

  2. 创建功能分支（ git checkout -b feature/amazing-feature ）

  3. 提交您的更改（ git commit -m 'Add amazing feature' ）

  4. 推送到分支（ git push origin feature/amazing-feature ）

  5. 打开拉取请求

执照

该项目根据 MIT 许可证获得许可 - 有关详细信息，请参阅LICENSE文件。

Available Tools

7 tools
cpe_lookupA
Read-only

Search for Common Platform Enumeration (CPE) entries by product name in Shodan's CVEDB. Supports pagination and can return either full CPE details or just the total count. Useful for identifying specific versions and configurations of software and hardware.

ParametersJSON Schema
NameRequiredDescriptionDefault
skipNoNumber of CPEs to skip (for pagination).
countNoIf true, returns only the count of matching CPEs.
limitNoMaximum number of CPEs to return (max 1000).
productYesThe name of the product to search for CPEs.

TDQS

A4.2/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and openWorldHint=true, and the description adds pagination support and the option to return only a count. These are behavioral traits beyond what annotations provide, with no contradictions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences, front-loaded with the core purpose, followed by key capabilities. Every sentence earns its place with no redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only lookup with fully documented parameters and no output schema, the description covers the main behavioral options (pagination, count mode) and a clear use case. It doesn't detail return format, but given the simplicity and annotation coverage, this is adequate.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all four parameters are documented in the schema. The description mentions pagination and count, but these are already covered in the schema descriptions, so it adds minimal semantic value beyond what is structured.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the specific verb 'Search' and resource 'CPE entries' within 'Shodan's CVEDB'. It distinguishes from the sibling cves_by_product by focusing on CPEs rather than CVEs, and the name reinforces this.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides a clear use case: 'identifying specific versions and configurations of software and hardware.' However, it does not explicitly mention alternatives or exclusion criteria. The sibling cves_by_product likely covers CVEs, so the contrast is implied but not stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

cve_lookupA
Read-only

Query detailed vulnerability information from Shodan's CVEDB. Returns comprehensive CVE details including CVSS scores (v2/v3), EPSS probability and ranking, KEV status, proposed mitigations, ransomware associations, and affected products (CPEs).

ParametersJSON Schema
NameRequiredDescriptionDefault
cveYesThe CVE identifier to query (format: CVE-YYYY-NNNNN).

TDQS

A4/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint and openWorldHint, covering safety and openness. The description adds substantial behavioral context by listing the specific fields returned (CVSS v2/v3, EPSS, KEV status, mitigations, ransomware associations, CPEs), which goes beyond the annotations and helps the agent set expectations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences with zero fluff. The first sentence front-loads the core purpose, and the second enumerates the key return fields. Every clause earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a single-parameter lookup tool with no output schema, the description adequately covers the return content by listing the major fields. It does not mention error handling or pagination, but given the simplicity and the openWorldHint annotation, the essential information is present. Minor gaps prevent a 5.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema fully describes the parameter (pattern and description), so schema coverage is 100%. The description does not add new parameter semantics beyond what the schema already provides; it merely reinforces that a CVE ID is needed. With full schema coverage, baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb ('Query') and resource ('detailed vulnerability information from Shodan's CVEDB'), and enumerates the concrete data returned (CVSS, EPSS, KEV, mitigations, ransomware, CPEs). This clearly distinguishes it from siblings like cves_by_product, which likely searches by product.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage when you have a CVE identifier (the required parameter), but it does not explicitly mention when not to use it or recommend alternatives like cves_by_product for product-based queries. Guidance is implicit rather than explicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

cves_by_productA
Read-only

Search for vulnerabilities affecting specific products or CPEs. Supports filtering by KEV status, sorting by EPSS score, date ranges, and pagination. Can search by product name or CPE 2.3 identifier. Returns detailed vulnerability information including severity scores and impact assessments.

ParametersJSON Schema
NameRequiredDescriptionDefault
skipNoNumber of CVEs to skip (for pagination).
countNoIf true, returns only the count of matching CVEs.
cpe23NoThe CPE version 2.3 identifier (format: cpe:2.3:part:vendor:product:version).
limitNoMaximum number of CVEs to return (max 1000).
is_kevNoIf true, returns only CVEs with the KEV flag set.
productNoThe name of the product to search for CVEs.
end_dateNoEnd date for filtering CVEs (format: YYYY-MM-DDTHH:MM:SS).
start_dateNoStart date for filtering CVEs (format: YYYY-MM-DDTHH:MM:SS).
sort_by_epssNoIf true, sorts CVEs by EPSS score in descending order.

TDQS

A3.9/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and openWorldHint=true, so the tool is known to be a read-only, broad-scope operation. The description adds value by disclosing the return content ('detailed vulnerability information including severity scores and impact assessments') and mentions pagination support, which goes beyond the annotations. It does not contradict any annotation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences, with the primary purpose front-loaded and the supporting capabilities summarized in the second sentence. It is not overly verbose, though the second sentence packs multiple features into one clause. No extraneous information is present, and the structure is logical.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (9 parameters, all with schema descriptions) and the absence of an output schema, the description provides a sufficient overview, including the two search modes (product name vs. CPE identifier) and the return of severity/impact info. It could be more explicit about the relationship between product and cpe23 (e.g., whether they can be combined), but overall it covers the key usage context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so each parameter is already documented in the schema (e.g., skip, count, cpe23, limit, is_kev, product, dates, sort_by_epss). The description adds only a high-level summary (supports filtering by KEV, sorting by EPSS, date ranges, pagination) without adding new semantic detail. This aligns with the baseline of 3 for fully covered schemas.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb ('Search') and a precise resource ('vulnerabilities affecting specific products or CPEs'), and lists the supported filtering/sorting capabilities. This clearly distinguishes it from sibling tools like cve_lookup (individual CVE lookup) and cpe_lookup (CPE details), making its purpose unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description clearly conveys that this tool is for product/CPE-based vulnerability searches and mentions the search options (by product name or CPE 2.3). However, it does not explicitly state when to prefer this over sibling tools, such as using cve_lookup for a specific CVE or cpe_lookup for CPE metadata. The guidance is implied rather than explicit, so it earns a 3.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

dns_lookupA
Read-only

Resolve domain names to IP addresses using Shodan's DNS service. Supports batch resolution of multiple hostnames in a single query. Returns IP addresses mapped to their corresponding hostnames.

ParametersJSON Schema
NameRequiredDescriptionDefault
hostnamesYesList of hostnames to resolve.

TDQS

A4.1/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, so the description isn't required to state safety. It adds the batch resolution feature and the mapping behavior, which is useful context. No contradictions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, no waste, key purpose first.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a single-parameter read-only tool with no output schema, the description covers purpose, behavior, and return format adequately. No gaps for an agent to call it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema covers the parameter fully (100%). Description adds the 'batch' nuance but essentially repeats the schema's 'list' semantics. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (Resolve), resource (domain names to IP addresses), and names the service (Shodan's DNS). Implicitly differentiates from reverse_dns_lookup by direction.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Implied usage: if you need to resolve domain names to IPs, this is the tool. But no explicit when-not-to-use or alternatives mentioned. Batch capability is mentioned but not as a selection criterion.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

ip_lookupA
Read-only

Retrieve comprehensive information about an IP address, including geolocation, open ports, running services, SSL certificates, hostnames, and cloud provider details if available. Returns service banners and HTTP server information when present.

ParametersJSON Schema
NameRequiredDescriptionDefault
ipYesThe IP address to query.

TDQS

A4/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description accurately reflects a read-only lookup operation and adds helpful qualifiers like 'if available' and 'when present.' It does not contradict the readOnlyHint annotation, though it omits potential error or rate-limit behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences, free of fluff, and front-loads the core purpose before listing specific return categories.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema provided, the description usefully enumerates expected return data. It lacks error/edge-case details, but the listed outputs give sufficient context for typical use.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema already documents the ip parameter as 'The IP address to query,' and the description repeats this without adding format constraints, IPv4/IPv6 guidance, or examples. Schema coverage is effectively complete, so baseline score applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states the tool retrieves comprehensive information about an IP address and enumerates the types of data returned (geolocation, open ports, services, SSL certificates, hostnames, cloud details). This distinguishes it from sibling tools like dns_lookup or cve_lookup.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description makes the tool's scope clear but does not explicitly state when to use it over alternatives such as shodan_search or dns_lookup. Usage guidance is implied rather than stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

reverse_dns_lookupA
Read-only

Perform reverse DNS lookups to find hostnames associated with IP addresses. Supports batch lookups of multiple IP addresses in a single query. Returns all known hostnames for each IP address, with clear indication when no hostnames are found.

ParametersJSON Schema
NameRequiredDescriptionDefault
ipsYesList of IP addresses to perform reverse DNS lookup on.

TDQS

A4.1/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered. The description adds behavioral context beyond annotations: it supports batch queries, returns all known hostnames per IP, and provides clear indication when none are found. This is useful operational detail that the schema and annotations do not convey.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, no filler. The first sentence states the core purpose, the second adds batch and return details. Information is front-loaded and every word earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

This is a simple one-parameter tool with a clear return description. The description explains what the tool does, how it handles multiple IPs, and what it returns (hostnames and a not-found indication). Annotations cover read-only and open-world aspects. Nothing essential for correct invocation is missing, even without an output schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, with the ips parameter clearly documented as a list of IP addresses. The description adds no new semantic meaning—'batch lookups' is implied by the array type. Per the baseline rule for high coverage, a 3 is appropriate; the description does not compensate or add value beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific action (perform reverse DNS lookups), a clear resource (IP addresses), and the expected output (hostnames). It also distinguishes itself from forward DNS lookups by the term 'reverse,' which is reinforced by the sibling dns_lookup. This is unambiguous and not a tautology.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for IP-to-hostname resolution but does not explicitly contrast with alternatives like dns_lookup or ip_lookup. It mentions batch support, which is a feature, but offers no when-to-use/when-not-to-use guidance. Usage is inferred from the tool name and context rather than stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 7 tool updatesv1.0.0
    • Changedcpe_lookup2 fields changed
      • addedInput schema / $schema
        Added value: +"http://json-schema.org/draft-07/schema#"
      • addedInput schema / additionalProperties
        Added value: +false
    • Changedcve_lookup2 fields changed
      • addedInput schema / $schema
        Added value: +"http://json-schema.org/draft-07/schema#"
      • addedInput schema / additionalProperties
        Added value: +false
    • Changedcves_by_product2 fields changed
      • addedInput schema / $schema
        Added value: +"http://json-schema.org/draft-07/schema#"
      • addedInput schema / additionalProperties
        Added value: +false
    • Changeddns_lookup2 fields changed
      • addedInput schema / $schema
        Added value: +"http://json-schema.org/draft-07/schema#"
      • addedInput schema / additionalProperties
        Added value: +false
    • Changedip_lookup2 fields changed
      • addedInput schema / $schema
        Added value: +"http://json-schema.org/draft-07/schema#"
      • addedInput schema / additionalProperties
        Added value: +false
    • Changedreverse_dns_lookup2 fields changed
      • addedInput schema / $schema
        Added value: +"http://json-schema.org/draft-07/schema#"
      • addedInput schema / additionalProperties
        Added value: +false
    • Changedshodan_search2 fields changed
      • addedInput schema / $schema
        Added value: +"http://json-schema.org/draft-07/schema#"
      • addedInput schema / additionalProperties
        Added value: +false
  2. 7 tool updates
    • First observedcpe_lookup
    • First observedcve_lookup
    • First observedcves_by_product
    • First observeddns_lookup
    • First observedip_lookup
    • First observedreverse_dns_lookup
    • First observedshodan_search
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A3.9/5.0

Scored across 7 tools

Disambiguation4/5

Most tools are clearly distinct: ip_lookup, shodan_search, dns_lookup, and reverse_dns_lookup each target a different resource. However, cve_lookup and cves_by_product both return vulnerability information, which could cause some confusion despite their different query approaches.

Naming Consistency4/5

Tool names mostly follow a consistent noun-based pattern (ip_lookup, dns_lookup, cve_lookup, cpe_lookup) with descriptive compound names for searches. The mix of 'lookup' and 'search' verbs is a minor inconsistency, but the pattern is still predictable and readable.

Tool Count5/5

Seven tools is well-scoped for a Shodan-focused server, covering IP intelligence, device search, DNS, and vulnerability data without unnecessary bloat. Each tool serves a distinct purpose within the security research domain.

Completeness4/5

The tool set covers core Shodan functionality: IP lookup, device search, DNS resolution, and CVE/CPE vulnerability research. Minor gaps exist such as account/API info or network/port-specific queries, but the primary workflows for security research are well covered.

Maintenance

ActivityMaintained
ResponsivenessSlow

Resources

Related MCP Connectors

Related MCP Servers

  • Shodan MCP Server

    X3r0K
    F
    license
    Not graded
    quality
    D
    maintenance
    A WebSocket server that provides MCP interface for searching and retrieving information about internet-connected devices, IP addresses, DNS data, and CVE vulnerabilities through the Shodan API.
    3
    -

  • Shodan-MCP-Server

    X3r0K
    F
    license
    Not graded
    quality
    D
    maintenance
    This is a Model Context Protocol (MCP) server that provides access to the Shodan API. It allows you to programmatically query Shodan for information about devices, vulnerabilities, and more.
    2
    -

  • Shodan MCP Server

    irootsec
    F
    license
    Not graded
    quality
    D
    maintenance
    Integrates Shodan search capabilities into MCP-compatible applications for discovering internet-connected devices. Enables domain searches, IP lookups, and advanced queries to identify exposed services, infrastructure mapping, and security analysis.
    3
    -

Appeared in Searches