Skip to main content
Glama
enesjakozh
jevy

MCP Web Research Server

by jevy
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Local

MCP 网络研究服务器

用于网络研究的模型上下文协议 (MCP) 服务器。

将实时信息带入 Claude 并轻松研究任何主题。

特征

  • Google 搜索集成

  • 网页内容提取

  • 研究会话跟踪（访问过的页面列表、搜索查询等）

  • 屏幕截图

Related MCP server: MCP Web Research Server

先决条件

安装

首先，确保您已经下载并安装了Claude Desktop 应用程序，并且已经安装了 npm。

接下来，将此条目添加到您的claude_desktop_config.json中（在 Mac 上，位于~/Library/Application\ Support/Claude/claude_desktop_config.json ）：

{
  "mcpServers": {
    "webresearch": {
      "command": "npx",
      "args": ["-y", "@mzxrai/mcp-webresearch@latest"]
    }
  }
}

此配置允许 Claude Desktop 在需要时自动启动网络研究 MCP 服务器。

用法

只需与 Claude 开始聊天，并发送一个有助于进行网络研究的提示即可。如果您想要一个预先构建的、针对更深入的网络研究而定制的提示，您可以使用我们通过此软件包提供的agentic-research提示。在 Claude Desktop 中，点击聊天输入框中的回形针图标，然后选择Choose an integration → webresearch研究”→ agentic-research即可访问该提示。

工具

  1. search_google

    • 执行 Google 搜索并提取结果

    • 参数： { query: string }

  2. visit_page

    • 访问网页并提取其内容

    • 参数： { url: string, takeScreenshot?: boolean }

  3. take_screenshot

    • 截取当前页面的屏幕截图

    • 无需任何参数

提示

agentic-research

引导式研究提示，帮助 Claude 进行深入的网络研究。该提示指导 Claude 执行以下操作：

  • 从广泛的搜索开始，了解主题概况

  • 优先考虑高质量、权威的来源

  • 根据研究结果反复完善研究方向

  • 让您随时了解情况，并让您以交互方式指导研究

  • 始终引用带有 URL 的来源

资源

我们将两件事作为 MCP 资源公开：（1）捕获的网页截图，以及（2）研究会话。

截图

截取的屏幕截图会被保存为 MCP 资源。您可以通过 Claude Desktop 中的回形针图标访问截取的屏幕截图。

研究会议

服务器维护一个研究会话，其中包括：

  • 搜索查询

  • 访问过的页面

  • 提取的内容

  • 截图

  • 时间戳

建议

为了获得最佳效果，如果您选择在研究时不使用agentic-research提示，建议 Claude 在研究一般主题时使用高质量的来源可能会有所帮助。例如，您可以提示news today from reuters or AP ，而不是news today 。

问题

这基本上是 pre-alpha 代码。而且它也是 AIGC，所以可能会有 bug。

如果您遇到问题，检查 Claude Desktop 的 MCP 日志可能会有所帮助：

tail -n 20 -f ~/Library/Logs/Claude/mcp*.log

发展

# Install dependencies
pnpm install

# Build the project
pnpm build

# Watch for changes
pnpm watch

# Run in development mode
pnpm dev

要求

  • Node.js >= 18

  • Playwright（作为依赖项自动安装）

已验证的平台

  • [x] macOS

  • Linux

执照

麻省理工学院

作者

mzxrai

Available Tools

3 tools
search_googleC

Search Google for a query

ParametersJSON Schema
NameRequiredDescriptionDefault
queryYesSearch query

TDQS

C2.7/5.0
Behavior2/5

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the action ('Search Google') but doesn't reveal any behavioral traits such as whether it requires authentication, rate limits, what the output format is (since no output schema exists), or if it performs a live web search versus cached results. The description is minimal and lacks critical operational details.

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 a single, efficient sentence with zero wasted words: 'Search Google for a query'. It is front-loaded and directly conveys the core action without unnecessary elaboration, making it highly concise and well-structured for its purpose.

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

Completeness2/5

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

Given the complexity of a search tool with no annotations and no output schema, the description is incomplete. It doesn't explain what the tool returns (e.g., search results, links, snippets), any limitations (e.g., number of results, pagination), or behavioral aspects like error handling. For a tool that likely involves external API calls or web interactions, more context is needed to guide effective 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 input schema has 100% description coverage, with the 'query' parameter documented as 'Search query'. The description adds no additional meaning beyond this, as it only repeats the concept of a 'query' without elaborating on syntax, examples, or constraints. Given the high schema coverage, the baseline score of 3 is appropriate, as the description doesn't compensate but also doesn't detract.

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

Purpose3/5

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

The description 'Search Google for a query' clearly states the verb ('Search') and resource ('Google'), making the purpose understandable. However, it lacks specificity about what kind of search this is (e.g., web search, image search, news search) and doesn't distinguish it from potential sibling tools like 'visit_page', which might also involve Google. The description is functional but vague in scope.

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

Usage Guidelines2/5

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

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention sibling tools like 'take_screenshot' or 'visit_page', nor does it specify contexts where this search is appropriate (e.g., for general information retrieval vs. navigating to a specific page). Without any usage context or exclusions, the agent must infer when to apply it.

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

take_screenshotB

Take a screenshot of the current page

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

TDQS

B3.1/5.0
Behavior2/5

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 states the action ('take a screenshot') but doesn't explain what happens—e.g., whether it saves the screenshot, returns it as data, requires permissions, or has side effects. This leaves significant gaps in understanding the tool's 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 a single, clear sentence with no wasted words, making it highly efficient and easy to parse. It's front-loaded with the core action, which is ideal for quick understanding.

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

Completeness2/5

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

Given the lack of annotations and output schema, the description is incomplete for a tool that performs an action like taking a screenshot. It doesn't cover what the tool returns, how the screenshot is handled, or any behavioral nuances, leaving the agent with insufficient context to use it effectively.

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

Parameters4/5

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

The input schema has 0 parameters with 100% coverage, so no parameter documentation is needed. The description doesn't add parameter details, which is appropriate here, as there are no parameters to describe, aligning with the baseline for zero parameters.

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

Purpose4/5

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

The description clearly states the action ('take') and target resource ('screenshot of the current page'), making the tool's purpose immediately understandable. It doesn't explicitly differentiate from sibling tools like 'visit_page' or 'search_google', which serve different functions, but the purpose is unambiguous.

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

Usage Guidelines2/5

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

The description provides no guidance on when to use this tool versus alternatives or in what context it should be applied. It lacks any mention of prerequisites, such as needing a page to be loaded first, or exclusions, leaving usage entirely implicit.

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

visit_pageC

Visit a webpage and extract its content

ParametersJSON Schema
NameRequiredDescriptionDefault
urlYesURL to visit
takeScreenshotNoWhether to take a screenshot

TDQS

C2.9/5.0
Behavior2/5

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

With no annotations provided, the description carries full burden for behavioral disclosure. It mentions visiting and extracting content but fails to describe important traits: what 'extract content' means (HTML, text, metadata?), whether authentication is needed, rate limits, timeouts, or what happens with invalid URLs. This leaves significant gaps for a tool that interacts with external resources.

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 extremely concise with just one sentence containing no wasted words. It's front-loaded with the core purpose and efficiently communicates the essential function without unnecessary elaboration.

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

Completeness2/5

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

For a tool with no annotations and no output schema that performs external web interactions, the description is insufficient. It doesn't explain what 'extract its content' returns, doesn't mention error conditions or limitations, and provides minimal behavioral context. Given the complexity of web scraping/visiting operations, this leaves too many unknowns.

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 the schema already documents both parameters adequately. The description adds no additional parameter semantics beyond what's in the schema descriptions. The baseline of 3 is appropriate when the schema does the heavy lifting.

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

Purpose4/5

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 ('visit' and 'extract') and resource ('webpage content'). It distinguishes from sibling 'take_screenshot' by mentioning content extraction, though it doesn't explicitly differentiate from 'search_google' which likely has different functionality.

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

Usage Guidelines2/5

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

The description provides no guidance on when to use this tool versus alternatives like 'search_google' or 'take_screenshot'. It doesn't mention prerequisites, constraints, or appropriate contexts for usage, leaving the agent with minimal direction.

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. 3 tool updates
    • First observedsearch_google
    • First observedtake_screenshot
    • First observedvisit_page
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

B3.2/5.0

Scored across 3 tools

Disambiguation5/5

Each tool has a clearly distinct purpose with no overlap: search_google finds web pages, visit_page loads and extracts content from a specific URL, and take_screenshot captures visual data from the current page. An agent can easily differentiate these functions without confusion.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern using snake_case: search_google, take_screenshot, and visit_page. This uniformity makes the set predictable and easy to understand at a glance.

Tool Count3/5

With only 3 tools, the server feels thin for a 'Web Research Server' scope, as it lacks operations like navigating pages, interacting with elements, or managing browser sessions. While the tools cover basic functions, the count is borderline low for comprehensive web research tasks.

Completeness2/5

There are significant gaps in the tool surface for web research: no navigation tools (e.g., go_back, click_element), no interaction capabilities (e.g., fill_form, scroll), and no session management. This incomplete coverage will likely cause agent failures in complex research workflows.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

Appeared in Searches