Which integrations are available for this server?

Allows searching the web using DuckDuckGo, returning a list of results with titles, URLs, and snippets. Allows searching the web using Google's search engine, returning a list of results with titles, URLs, and snippets.

How do I use free-web-search-mcp?

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@free-web-search-mcp search the web for MCP server best practices" 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.

free-web-search-mcp

by adi-santoso

Overview Schema Source Related Servers Discussions Admin

Python

Local

free-web-search-mcp

A free web search MCP server powered by real browsers.

Features · Install · Configure · Tools · Contributing · License

Features

MCP server exposing web_search, fetch_page, and setup_camoufox tools
Multiple browser backends selectable at runtime:
- camoufox — stealth Firefox (anti-detect), default when installed
- chrome — Playwright Chromium via installed Google Chrome
- msedge — Playwright Chromium via installed Microsoft Edge
- chromium — Playwright bundled Chromium
- firefox — Playwright Firefox
- webkit — Playwright WebKit
Auto-setup Camoufox — pip install + binary download on demand
Multiple search engines: Google (default), Bing, DuckDuckGo
Page content extraction (plain text) for deep-reading a result URL
Humanized typing, configurable proxy, locale, headless mode
Block detection with actionable hints (e.g. "retry with browser='camoufox'")

Related MCP server: CloakBrowser Search MCP

Install

# Default install (Playwright path)
pip install -e .

# With Camoufox (recommended for stealth)
pip install -e ".[camoufox]"
camoufox fetch

# Playwright browsers (only download the ones you'll use)
playwright install chromium        # for backend=chromium
playwright install firefox         # for backend=firefox
playwright install webkit          # for backend=webkit
# chrome / msedge backends use the already-installed system browser, no download needed.

Camoufox missing on first run? It is installed and downloaded automatically — no manual steps required.

Configure

cp .env.example .env
# edit .env

Env	Default	Description
`SEARCH_ENGINE`	`google`	Default search engine: `google` \| `bing` \| `duckduckgo`
`MAX_RESULTS`	`10`	Max results returned per search
`DEFAULT_BROWSER`	auto	`camoufox` if installed, else `chrome`. Override per-call via param
`HEADLESS`	`true`	Run browser headless
`HUMANIZE`	`true`	Humanized typing
`LOCALE`	`en-US`	Browser locale
`PROXY_URL`	empty	Optional proxy `http://user:pass@host:port`
`MCP_LOG_LEVEL`	`INFO`	`DEBUG` \| `INFO` \| `WARNING` \| `ERROR`

Run

# Direct
python -m free_web_search_mcp

# Via script entry point
free-web-search-mcp

Integrate

Claude Desktop — `claude_desktop_config.json`

{
  "mcpServers": {
    "free-web-search": {
      "command": "python",
      "args": ["-m", "free_web_search_mcp"],
      "cwd": "<path-to-this-project>"
    }
  }
}

opencode — `opencode.json` (global or project)

{
  "mcp": {
    "free-web-search": {
      "type": "local",
      "command": ["python", "-m", "free_web_search_mcp"],
      "enabled": true,
      "environment": {
        "HEADLESS": "true",
        "HUMANIZE": "true",
        "DEFAULT_BROWSER": "camoufox"
      }
    }
  }
}

Tools

`web_search(query, max_results=10, engine="google", browser="")`

Search the web and return a list of {position, title, url, snippet}.

Parameter	Type	Default	Description
`query`	str	required	Search query string
`max_results`	int	`10`	1-20
`engine`	str	`google`	`google` \| `bing` \| `duckduckgo`
`browser`	str	auto	`camoufox` \| `chrome` \| `msedge` \| `chromium` \| `firefox` \| `webkit`

`fetch_page(url, max_chars=20000, browser="")`

Fetch a URL and extract its main content as plain text.

Parameter	Type	Default	Description
`url`	str	required	Page URL
`max_chars`	int	`20000`	1000-50000
`browser`	str	auto	Same options as `web_search`

`setup_camoufox(force=False)`

Ensure the Camoufox stealth browser is installed and its binary is downloaded. Runs pip install camoufox and python -m camoufox fetch automatically if missing. No-op if already installed.

Parameter	Type	Default	Description
`force`	bool	`False`	Re-download the binary even if present

Tips: avoid captcha & blocks

Search engines flag requests by IP reputation, not just browser fingerprint. Camoufox handles the fingerprint side, but the IP matters more than people expect.

Run locally when possible. A residential home IP is clean and almost never gets captchas. A VPS/datacenter IP is frequently flagged — even with Camoufox, Google may serve reCAPTCHA. Prefer running this server on your local machine (or home server) and pointing your MCP client at it.

If you must run on a VPS:

Set HUMANIZE=true and keep requests spaced out (no rapid bursts).
Use a residential proxy via PROXY_URL (http://user:pass@host:port). This is the single most effective fix for captcha on datacenter IPs.
Fall back to engine="bing" or engine="duckduckgo" — they are generally more permissive than Google.
Rotate locale / user-agent across calls.

Block detection is built in. When a search hits a captcha/consent page, the tool returns a clear error and suggests retrying with browser="camoufox" — so the caller can switch backend automatically.

Contributing

Pull requests are welcome. Please open them against a feature branch (not main):

git checkout -b feature/your-feature
git push -u origin feature/your-feature

Then open a PR targeting main. Keep commits focused and titled in the imperative mood (e.g. "Add support for Yandex"). Run ruff check . before submitting.

License

MIT — see LICENSE.

Available Tools

3 tools

fetch_pageA

Fetch a web page and return its main content as plain text. Browser backend: 'camoufox' (stealth Firefox, default if installed), 'chrome', 'msedge', 'chromium', 'firefox', or 'webkit'. Omit to use the default. Useful for reading the full content of a search result URL.

ParametersJSON Schema

Name	Required	Description	Default
`url`	Yes
`browser`	No
`max_chars`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

A4/5.0

Behavior3/5

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

With no annotations, the description carries the full burden. It discloses that the output is 'main content as plain text' (not raw HTML) and explains browser backend options, including the default. However, it does not mention potential errors, redirects, or handling of dynamic content, leaving some behavioral gaps.

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: the first states the core function, the second lists browser options and usage context. Every sentence adds value, is front-loaded, and there is 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?

Given the tool's moderate complexity and the presence of an output schema, the description covers the main aspects: purpose, browser selection, and a typical use case. It does not mention the max_chars limit or error behavior, but these are marginal for a straightforward fetch 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?

The schema description coverage is 0%, so the description must compensate. It thoroughly explains the 'browser' parameter by listing valid values and the default behavior ('Omit to use the default'). However, it does not explain 'max_chars' or provide any semantics for the required 'url' parameter beyond what is obvious from the purpose.

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 explicitly states 'Fetch a web page and return its main content as plain text', using a specific verb and resource. This clearly distinguishes it from siblings like web_search (searching) and setup_camoufox (configuration).

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 a concrete use case: 'Useful for reading the full content of a search result URL.' This implies when to use the tool after obtaining a URL via search. However, it does not explicitly state when not to use it or mention alternatives beyond the implied workflow.

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

setup_camoufoxA

Ensure the Camoufox stealth browser is installed and its binary is downloaded. Runs pip install camoufox and python -m camoufox fetch automatically if missing. Returns current status. No-op if already installed.

ParametersJSON Schema

Name	Required	Description	Default
`force`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

A4/5.0

Behavior4/5

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

Even though no annotations are provided, the description discloses the main behaviors: it runs pip install and python -m camoufox fetch, is a no-op if already installed, and returns current status. It doesn't detail potential side effects or the exact meaning of 'force', but it gives a solid overview of 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 three concise sentences, front-loaded with the purpose, and every sentence adds useful information. There is no wasted wording, and the structure is logical: purpose, mechanism, conditional behavior.

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

Completeness3/5

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

The description covers the tool's operation and return type, but it omits the meaning of the 'force' parameter, which is a significant gap for an otherwise simple tool. The output schema exists, so return values are handled structurally, but the parameter gap makes the description incomplete.

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

Parameters2/5

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

The description doesn't explain the 'force' parameter at all, and the schema provides no description either. Since schema description coverage is 0%, the description should compensate, but it doesn't. The agent would have to guess what 'force' does based on the title alone.

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 tool's function with a specific verb ('Ensure') and resource ('Camoufox stealth browser installed'). It distinguishes itself from sibling tools (web_search, fetch_page) by focusing on setup/installation, and includes key behaviors like idempotency and status return.

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 implies when to use it: any time the Camoufox browser is needed, it ensures it's installed. It doesn't explicitly mention alternatives or exclusions, but the sibling tools are unrelated, making the context clear. It could have been more explicit about calling it before other tools, but the implied usage is sufficient.

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

web_searchA

Search the web via a real browser and return results. Browser backend: 'camoufox' (stealth Firefox, default if installed), 'chrome', 'msedge', 'chromium', 'firefox', or 'webkit'. Omit to use the default. Engine options: 'google', 'bing', or 'duckduckgo'.

ParametersJSON Schema

Name	Required	Default
`query`	Yes
`engine`	No	google
`browser`	No
`max_results`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

A3.6/5.0

Behavior3/5

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

With no annotations provided, the description carries the full burden. It discloses that the tool uses a real browser and lists configurable backends, but it does not mention side effects, rate limits, required setup, or what 'return results' entails. This gives some context but leaves significant behavioral traits undisclosed.

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 compact and front-loaded: the purpose is stated first, followed by useful parameter details in a scannable list. Every sentence contributes new information, and there is no fluff or repetition of the schema.

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

Completeness3/5

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

The tool has 4 parameters and an output schema, so return structure is likely covered elsewhere. However, the description lacks guidance on when to use the tool, how max_results works, or any prerequisites like browser setup. It is complete enough for a straightforward search tool but misses key context.

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

Parameters2/5

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

Schema description coverage is 0%, so the description must compensate. It explicitly explains the browser and engine parameters, but completely omits query and max_results. The description adds value for two of four parameters, leaving the remaining parameters to be inferred from the schema alone.

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 opens with a specific verb+resource: 'Search the web via a real browser and return results.' It clearly identifies the tool's function and distinguishes it from siblings like fetch_page and setup_camoufox. The browser and engine options further sharpen its scope.

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?

Usage context is implied through the description of browser and engine options, but there is no explicit guidance on when to prefer this tool over siblings or when not to use it. No alternatives or exclusions are mentioned, leaving room for ambiguity.

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.

3 tool updatesv0.1.0Aug 7, 2026
- First observedfetch_page
- First observedsetup_camoufox
- First observedweb_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

A4.1/5.0

Scored 2026-08-07 20:25 across 3 tools

Disambiguation5/5

Each tool has a distinct purpose: setup_camoufox handles installation, web_search performs queries, and fetch_page retrieves page content. No overlap in functionality.

Naming Consistency4/5

All names use snake_case, but web_search is a compound noun rather than a clear verb_noun construction like the other two. Minor deviation from the otherwise consistent pattern.

Tool Count5/5

Three tools is a well-scoped set for a web search server, covering setup, searching, and fetching without unnecessary bloat.

Completeness5/5

The domain of web search is fully covered: setup ensures the browser is ready, web_search finds results, and fetch_page reads full content. No obvious gaps for basic search workflows.

Maintenance

ActivitySlowing

ResponsivenessNo issues

Resources

GitHub Repository

Need Help?

Related Servers

Related MCP Connectors

Keenable Web Search A
ai.keenable.api
Docs: https://docs.keenable.ai/mcp-server Keenable is a free, remote MCP server that gives agents access to the web index. Search the web with ranked results and date/site filters, then fetch any indexed page as clean markdown. Works out of the box with no account or API key.
Research & Data Search Web Scraping
23
VPN.FAIL MCP A
io.github.vpnfail
Free remote MCP server for fetching public web pages through a rotating proxy pool.
Web Scraping Browser Automation
31
Aginx Browser A
net.aginx
Stealth web browser for agents: search, fetch, click, download and type in persistent MCP sessions.
Browser Automation Agent Orchestration
37128
mcp A
ai.llmse
Public MCP server for the LLM Search Engine
Search RAG Systems Developer Tools
102

Related MCP Servers

AgentWebSearch-MCP
Browser Automation Web Scraping Search
insung8150
A
license
Not graded
quality
D
maintenance
An MCP server that provides web search and content fetching using real Chrome browsers via CDP, bypassing bot detection and requiring no API keys.
Updated 7 months ago (2026-02-19 02:12 UTC)
20
MIT
CloakBrowser Search MCP
Browser Automation Web Scraping
rishabhsfdc
A
license
Not graded
quality
D
maintenance
A local web search MCP server that uses stealth Chromium to bypass CAPTCHAs and bot blocks, supporting Google and DuckDuckGo with automatic fallback.
Updated 3 months ago (2026-06-13 05:34 UTC)
18 npm
MIT
evo-scry
Search Web Scraping
krich11
A
license
Not graded
quality
D
maintenance
MCP server for internet search via direct Google and DuckDuckGo HTML scraping with AI-powered result normalization and optional summarization, requiring no API keys for search.
Updated 5 months ago (2026-04-06 21:02 UTC)
MIT
fast-web-search-mcp
Browser Automation Web Scraping Search
iPraBhu
A
license
A
quality
B
maintenance
A production-ready MCP server for free web search, news search, and webpage content extraction using DuckDuckGo and Bing.
Updated 2 months ago (2026-07-13 23:49 UTC)
4
8 npm
MIT

free-web-search-mcp

Features

Install

Configure

Run

Integrate

Claude Desktop — claude_desktop_config.json

opencode — opencode.json (global or project)

Tools

web_search(query, max_results=10, engine="google", browser="")

fetch_page(url, max_chars=20000, browser="")

setup_camoufox(force=False)

Tips: avoid captcha & blocks

Contributing

License

Available Tools

Output Schema

Output Schema

Output Schema

Tool Schema Changelog

Maintenance

Resources

Related MCP Connectors

Related MCP Servers

Claude Desktop — `claude_desktop_config.json`

opencode — `opencode.json` (global or project)

`web_search(query, max_results=10, engine="google", browser="")`

`fetch_page(url, max_chars=20000, browser="")`

`setup_camoufox(force=False)`