MCP Server for Stealth Web Search and Fetching

by maxylev

Overview Schema Source Related Servers Discussions Admin

Python

Local

Web Search

websearch

Search the web through DuckDuckGo or Google to get clean lists of titles, URLs, and snippets.

Instructions

Search the web using DuckDuckGo or Google. Returns a clean list of titles, URLs, and snippets. Excellent for researching general knowledge, news, and finding URLs.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`query`	Yes	The search query string.
`engine`	No	Search engine to use. Can be 'duckduckgo' or 'google'. Default is 'duckduckgo'.	duckduckgo
`region`	No	Region and language code to localize search results (e.g., 'us-en', 'uk-en', 'de-de'). For DuckDuckGo it maps directly. For Google, 'us' is country code and 'en' is language. Default is null (uses template default).
`block_media`	No	Block images, videos, and fonts entirely at the network layer. Default is true.
`max_results`	No	Maximum number of search results to return. Default is 10.
`safe_search`	No	Enable safe search filtering. null = use template default. Applies to both DuckDuckGo and Google.

Schema Changelog

Changes observed during successful MCP inspections.

Changed8 schema fields changedv3.3.4Sep 21, 2026
- addedInput schema / properties / max_results / exclusiveMinimum
```
Added value: +0
```
- addedInput schema / properties / max_results / maximum
```
Added value: +9007199254740991
```
- changedInput schema / properties / max_results / type
```
Previous value: -"number"New value: +"integer"
```
- addedInput schema / properties / query / minLength
```
Added value: +1
```
- removedInput schema / properties / region / anyOf
```
Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]
```
- addedInput schema / properties / region / type
```
Added value: +[
+  "string",
+  "null"
+]
```
- removedInput schema / properties / safe_search / anyOf
```
Removed value: -[
-  {
-    "type": "boolean"
-  },
-  {
-    "type": "null"
-  }
-]
```
- addedInput schema / properties / safe_search / type
```
Added value: +[
+  "boolean",
+  "null"
+]
```
First observedv3.3.2Aug 3, 2026

TDQS

A3.8/5.0

Behavior3/5

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

With no annotations, the description carries the full burden of behavioral disclosure. It does reveal that results are a clean list of titles, URLs, and snippets and that DuckDuckGo or Google may be used. However, it omits behavioral nuances such as network-layer media blocking, safe-search defaults, and engine-specific behavior, which would make behavior more transparent.

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 long with no filler. The first sentence states the action and output format; the second adds use cases. It is front-loaded and every phrase 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 relatively simple search tool, the description plus fully documented schema covers essentials: what it does, what it returns, and when it is useful. The main missing piece is explicit differentiation from the sibling webfetch, but this is a minor gap given the straightforward nature of the tool.

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%, and each parameter already has a detailed description with defaults and accepted formats. The tool description adds no parameter-specific guidance beyond situating the tool for general research, so the baseline of 3 is appropriate.

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 ('Search the web') and the resource, names the two engines used, and describes the output as a clean list of titles, URLs, and snippets. It does not explicitly contrast with sibling webfetch, so it falls just short of a 5, but the core purpose is unmistakable.

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?

It provides clear context on when the tool is appropriate ('general knowledge, news, and finding URLs'). It does not explicitly state when not to use it or point to webfetch as the alternative for fetching page content, so it lacks explicit exclusions/alternatives that would earn a 5.

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

Deploy Server

Other Tools

webfetchA
websearchA