Which integrations are available for this server?

Used as a search engine for security-related queries to prioritize trusted advisory sources. Used as a search engine for security-related queries to prioritize trusted advisory sources. Used as a search engine for security-related queries to prioritize trusted advisory sources. Provides web search fallback via scraping when the primary SearXNG engine is unavailable. Integrates the SearXNG metasearch engine to provide web search with category filters and fallback support. Used as a search engine for security-related queries to prioritize trusted advisory sources.

How do I use SearchMCP?

1. Click on "Install 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., "@SearchMCP search for recent breakthroughs in quantum computing" 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.

SearchMCP

by MachineLearning-Nerd

Overview Schema Related Servers Score Discussions

Python

Remote

Web MCP Server

A privacy-focused web search MCP (Model Context Protocol) server that provides web search and content extraction capabilities. Uses SearxNG as the primary search engine with Google scraping as a fallback.

Features

Web Search - Search the web with category filters (general, news, images, videos, science, files)
Content Extraction - Extract readable content from URLs as markdown
Search Suggestions - Get query suggestions for better searches
Privacy-Focused - Uses SearxNG metasearch engine
Fallback Support - Automatically falls back to Google scraping if SearxNG is unavailable
Relevance Ranking - Query-aware reranking, deduplication, and low-signal filtering
Security-Aware Search - CVE/security queries prioritize trusted advisory sources
Rate Limiting - Built-in rate limiting to prevent abuse
Docker Ready - Single-container deployment with SearxNG included

Related MCP server: webmcp

Tools Provided

Tool	Description
`web_search`	Search the web with query, category, and limit options
`fetch_content`	Extract and convert webpage content to markdown
`get_suggestions`	Get search query suggestions

Installation

Option 1: Docker (Recommended)

# Build the image
docker build -t web-mcp:latest .

# Run the container
docker run --rm -i web-mcp:latest

Option 2: Python Package

# Clone the repository
git clone https://github.com/your-org/web-mcp.git
cd web-mcp

# Install dependencies
pip install -r requirements.txt
pip install -r requirements-dev.txt  # Optional: tests, lint, type checks

# Or install as package
pip install -e .

# Run the server
python -m web_mcp.server

Option 3: With External SearxNG

If you have an existing SearxNG instance:

# Set the SearxNG URL
export SEARXNG_URL=http://your-searxng-instance:8080

# Run the MCP server
python -m web_mcp.server

Configuration

Environment Variables

Variable	Default	Description
`SEARXNG_URL`	`http://localhost:8080`	SearxNG server URL
`SEARXNG_TIMEOUT`	`10`	Request timeout in seconds
`SEARCH_ENGINE_PROFILE_MODE`	`auto`	Query-aware engine profile mode (`auto` or `off`)
`SEARCH_SECURITY_ENGINES`	`brave,bing,duckduckgo,wikipedia,github,stackoverflow`	Engines used for security/CVE queries
`SEARCH_GENERAL_ENGINES`	``	Engines for general queries (empty = SearxNG defaults)
`SEARCH_CANDIDATE_MULTIPLIER`	`5`	Candidate expansion before reranking
`SEARCH_MAX_CANDIDATES`	`30`	Maximum candidates before reranking
`SEARCH_MIN_QUALITY_SCORE`	`2.5`	Security-query quality threshold for fallback merge
`FALLBACK_ENABLED`	`true`	Enable Google scraping fallback
`RATE_LIMIT_REQUESTS`	`30`	Max requests per period
`RATE_LIMIT_PERIOD`	`60`	Rate limit period in seconds
`MAX_CONTENT_LENGTH`	`10000`	Max characters in fetched content
`FETCH_ALLOW_PRIVATE_NETWORK`	`false`	Allow fetching localhost/private network URLs
`DEFAULT_SEARCH_LIMIT`	`5`	Default number of search results
`LOG_LEVEL`	`INFO`	Logging level (DEBUG, INFO, WARNING, ERROR)
`JSON_LOGS`	`false`	Output logs in JSON format

Configuration File

Create a .env file in the project root:

SEARXNG_URL=http://localhost:8080
SEARXNG_TIMEOUT=10
SEARCH_ENGINE_PROFILE_MODE=auto
SEARCH_SECURITY_ENGINES=brave,bing,duckduckgo,wikipedia,github,stackoverflow
SEARCH_GENERAL_ENGINES=
SEARCH_CANDIDATE_MULTIPLIER=5
SEARCH_MAX_CANDIDATES=30
SEARCH_MIN_QUALITY_SCORE=2.5
FALLBACK_ENABLED=true
RATE_LIMIT_REQUESTS=30
RATE_LIMIT_PERIOD=60
MAX_CONTENT_LENGTH=10000
FETCH_ALLOW_PRIVATE_NETWORK=false
DEFAULT_SEARCH_LIMIT=5
LOG_LEVEL=INFO
JSON_LOGS=false

Usage with MCP Clients

Claude Desktop

Add to your Claude Desktop configuration (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):

{
  "mcpServers": {
    "web-mcp": {
      "command": "docker",
      "args": ["run", "--rm", "-i", "web-mcp:latest"]
    }
  }
}

Or with Python:

{
  "mcpServers": {
    "web-mcp": {
      "command": "python",
      "args": ["-m", "web_mcp.server"],
      "env": {
        "SEARXNG_URL": "http://localhost:8080"
      }
    }
  }
}

Other MCP Clients

The server uses stdio transport, making it compatible with any MCP-compatible client.

Tool Reference

web_search

Search the web for information.

Parameters:

Parameter	Type	Required	Description
`query`	string	Yes	The search query
`category`	string	No	Search category: `general`, `images`, `videos`, `news`, `science`, `files`
`limit`	integer	No	Maximum results (default: 5, min: 1, max: 10)

Example:

{
  "name": "web_search",
  "arguments": {
    "query": "Python async programming",
    "category": "general",
    "limit": 5
  }
}

Response:

# Search Results for: Python async programming

*Provider: searxng | 5 results*

---

## 1. Async IO in Python: A Complete Guide
**URL:** https://realpython.com/async-io-python/

Complete guide to async programming in Python...

## 2. Python asyncio Documentation
**URL:** https://docs.python.org/3/library/asyncio.html

Official Python asyncio documentation...

fetch_content

Extract readable content from a URL. By default, only public http/https targets are allowed (FETCH_ALLOW_PRIVATE_NETWORK=false).

Parameters:

Parameter	Type	Required	Description
`url`	string	Yes	The URL to fetch content from
`max_length`	integer	No	Maximum content length (default: 10000, min: 500, max: 20000)

Example:

{
  "name": "fetch_content",
  "arguments": {
    "url": "https://example.com/article",
    "max_length": 5000
  }
}

Response:

# Article Title

> Brief description of the article

**Author:** John Doe
**Source:** example.com
**URL:** https://example.com/article

---

[Article content in markdown format...]

get_suggestions

Get search query suggestions.

Parameters:

Parameter	Type	Required	Description
`query`	string	Yes	The partial search query

Example:

{
  "name": "get_suggestions",
  "arguments": {
    "query": "python asyn"
  }
}

Response:

# Suggestions for: python asyn

1. python async await
2. python asyncio tutorial
3. python async http requests
4. python async context manager
5. python asyncio vs threading

Development

Setup

# Create virtual environment
python -m venv venv
source venv/bin/activate

# Install development dependencies
pip install -e ".[dev]"

# Run tests
pytest

# Run linting
ruff check src tests

# Run type checking
mypy src

Manual MCP Smoke Test (Container + stdio)

Use this to verify the real MCP integration path used by CLI agents.

test.py starts the containerized MCP server as a child process with: docker run --rm -i web-mcp:latest and validates initialize, list_tools, and call_tool flows.

The container contract is stdio-only. Detached mode (docker run -d ...) is intentionally not supported for MCP clients.

# 1) Build image
docker build -t web-mcp:latest .

# 2) Run smoke script from repo root (with your virtualenv active)
.venv/bin/python test.py

# Optional: custom inputs
.venv/bin/python test.py \
  --image web-mcp:latest \
  --query "python asyncio" \
  --suggest-query "python asyn" \
  --content-url "https://example.com" \
  --limit 3 \
  --max-length 800

# Optional: full response blocks
.venv/bin/python test.py --verbose

What test.py verifies:

MCP session initialization against containerized server
Expected tools are registered: web_search, fetch_content, get_suggestions
Tool calls succeed over MCP stdio transport

Script behavior notes:

If you pass only one of --query or --suggest-query, that value is reused for both
test.py prints compact pass/fail summaries by default; use --verbose to show full tool outputs
Use --docker-command if your environment uses a different container runtime command

Project Structure

web-mcp/
├── src/web_mcp/
│   ├── __init__.py
│   ├── config.py           # Configuration management
│   ├── server.py           # MCP server entry point
│   ├── search/
│   │   ├── base.py         # SearchResult, SearchResponse, SearchProvider ABC
│   │   ├── searxng.py      # SearxNG provider
│   │   ├── google.py       # Google scraping fallback
│   │   ├── fallback.py     # Fallback orchestration + quality gate
│   │   ├── relevance.py    # Scoring, ranking, dedup, snippet cleaning
│   │   └── provider_registry.py # Shared provider singleton
│   ├── tools/
│   │   ├── web_search.py   # web_search tool
│   │   ├── fetch_content.py # fetch_content tool
│   │   └── suggestions.py  # get_suggestions tool
│   └── utils/
│       ├── logger.py       # Structured logging
│       ├── rate_limiter.py  # Rate limiting
│       ├── content_extractor.py # HTML-to-markdown extraction
│       └── validation.py   # Shared input validation
├── tests/                  # Test suite
├── docker/                 # Docker configuration
│   ├── searxng/           # SearxNG settings
│   └── entrypoint.sh      # Container entrypoint
├── Dockerfile             # Single-container Docker build
├── pyproject.toml         # Python project config
├── requirements.txt       # Runtime dependencies
└── requirements-dev.txt   # Test/lint/type dependencies

Troubleshooting

Common Issues

1. SearxNG Connection Refused

Error: Failed to connect to SearxNG

Ensure SearxNG is running: curl http://localhost:8080/config
Check SEARXNG_URL environment variable
If using Docker via MCP stdio, ensure the image is current (docker build -t web-mcp:latest .)

2. Google Rate Limiting

Error: Google rate limit hit (429)

Reduce request frequency
SearxNG should be used as primary; Google is fallback only
Wait a few minutes before retrying

3. Content Extraction Failed

Error: Failed to extract content from page

The page may use JavaScript rendering (not supported)
The page may block automated requests
Try with a different URL

4. Import Errors

ModuleNotFoundError: No module named 'web_mcp'

Ensure you're in the virtual environment
Install the package: pip install -e .
Check PYTHONPATH includes src/

Debug Mode

Enable debug logging:

export LOG_LEVEL=DEBUG
python -m web_mcp.server

Docker Debugging

# Run container interactively
docker run -it --entrypoint /bin/sh web-mcp:latest

# View logs
docker logs <container>

Security Considerations

SearxNG Secret: Change SEARXNG_SECRET in production
Rate Limiting: Configure RATE_LIMIT_REQUESTS to prevent abuse
Network: Container exposes port 8080 (for debugging only)
User Permissions: Container defaults to root-managed processes; harden users/permissions for production

License

MIT License - see LICENSE for details.

Contributing

Fork the repository
Create a feature branch
Make your changes
Run tests: pytest
Submit a pull request

Acknowledgments

SearxNG - Privacy-respecting metasearch engine
MCP - Model Context Protocol
Trafilatura - Web content extraction

Available Tools

3 tools

fetch_contentB

Fetch and extract readable content from a URL. Returns content as markdown.

ParametersJSON Schema

Name	Required	Description	Default
`url`	Yes	The URL to fetch content from
`max_length`	No	Maximum content length in characters (default: 10000)

TDQS

B3.4/5.0

Behavior2/5

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

No annotations provided, so description carries full burden. It says 'readable content' but defines it only as markdown. Does not disclose whether it handles non-HTML, authentication, rate limits, or failure modes (e.g., unreachable URLs). Under-specified for safe autonomous use.

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, front-loaded with verb and resource, second sentence adds output format. No redundancy. Every word is necessary.

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 sibling tools, the description is too minimal. Lacks guidance on edge cases, expected behavior for different URL types, and any prerequisites. Incomplete for an agent to use reliably.

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 coverage is 100%, so description adds minimal value beyond schema. The description does not elaborate on parameters beyond what schema provides. 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?

Clear verb ('Fetch and extract'), resource ('content from a URL'), and output format ('Returns as markdown'). Distinguishes from siblings: web_search returns search results, get_suggestions returns suggestions, not page content.

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?

Implies usage for extracting content from a specific URL, but no explicit when-to-use or when-not-to-use versus alternatives like web_search. No prerequisites or limitations mentioned.

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

get_suggestionsB

Get search query suggestions. Useful for autocomplete or query refinement.

ParametersJSON Schema

Name	Required	Description	Default
`query`	Yes	The partial search query to get suggestions for

TDQS

B3.1/5.0

Behavior2/5

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

No annotations are provided, and the description does not disclose any behavioral traits such as whether suggestions are personalized, require authentication, have rate limits, or are real-time. The tool's behavior is under-specified.

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 concise with two sentences, no redundancy. It is front-loaded and efficient, though could include more detail without becoming verbose.

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 no output schema, the description should hint at the return format (e.g., a list of suggestion strings). It lacks this detail, as well as information on result limits or sorting, making it incomplete for a simple suggestion 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 coverage is 100% and the parameter 'query' is adequately described. The description adds no additional meaning beyond the schema, so baseline score 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 tool retrieves search query suggestions, and the sibling tools ('fetch_content', 'web_search') indicate it is for suggestions rather than content retrieval or full searches. However, it could be more specific about the type of suggestions (e.g., completions).

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 mentions 'useful for autocomplete or query refinement', which provides context, but does not explicitly state when to use alternatives like 'web_search' for full results or 'fetch_content' for content.

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

web_searchC

Search the web for information. Returns relevant search results with titles, URLs, and descriptions.

ParametersJSON Schema

Name	Required	Description
`limit`	No	Maximum number of results to return (default: 5)
`query`	Yes	The search query
`category`	No	Search category: general (default), images, videos, news, science, files

TDQS

C2.9/5.0

Behavior2/5

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

With no annotations, description should disclose behavioral traits. It only mentions returned fields but omits rate limits, authentication, or special behaviors. Insufficient for a search tool.

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?

Single sentence with no filler. Efficiently conveys the tool's core 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 3 parameters, no output schema, and no annotations, description is too brief. Lacks details on output structure, error handling, or search limitations.

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 baseline is 3. Description adds minimal extra meaning beyond the schema, only noting that results are 'relevant'.

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?

Description clearly states the tool searches the web and returns results with titles, URLs, and descriptions. Verb 'Search' and resource 'web' are explicit. Does not explicitly differentiate from siblings fetch_content and get_suggestions, but the purpose is distinct enough.

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?

No guidance on when to use this tool versus alternatives. Description only states functionality without any contextual advice or exclusions.

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. Dates show when Glama detected each change.

3 tool updatesv0.1.0Jul 13, 2026
- First observedfetch_content
- First observedget_suggestions
- First observedweb_search

Install Server

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A3.5/5.0

Disambiguation5/5

Each tool has a clearly distinct purpose: fetching content from a URL, getting search suggestions, and performing a web search. There is no overlap or ambiguity between them.

Naming Consistency5/5

All tool names use a consistent verb_noun pattern in snake_case: fetch_content, get_suggestions, web_search. The naming is predictable and follows the same convention.

Tool Count5/5

With 3 tools covering search, suggestions, and content retrieval, the set is well-scoped. It is neither too few nor too many for a search-focused server.

Completeness4/5

The tool surface covers the core search workflow: querying, getting suggestions, and fetching results. A minor gap is the absence of a tool for advanced search parameters or filtering, but it is not critical.

Maintenance

ActivityInactive

ResponsivenessNo issues

Resources

GitHub Repository

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

mcp-serpOAuth
io.github.AceDataCloud
MCP server for Google search results via SERP API
Search Browser Automation Web Scraping
21
mcp A
ai.llmse
Public MCP server for the LLM Search Engine
Search RAG Systems Developer Tools
102
Serper A
io.github.pipeworx-io
Serper MCP — wraps the Serper Google Search API (serper.dev)
Search RAG Systems
342
serp-content-mcp
io.github.sercanmetalore
SERP + haber + içerik çıkarımı MCP sunucusu — web araması (Brave/SerpApi BYOK), anahtarsız haber…
Search Web Scraping Browser Automation
1

Related MCP Servers

searxng-mcp
Search Browser Automation Web Scraping
TadMSTR
A
license
A
quality
A
maintenance
MCP server for private web search via self-hosted SearXNG with local reranking, full-page content fetching via Firecrawl, and optional Ollama-powered query expansion and summaries.
Updated 2 days ago (2026-09-04 22:51 UTC)
7
116
21
MIT
webmcpofficial
Browser Automation Web Scraping Search
AuthBits
A
license
Not graded
quality
C
maintenance
MCP server for web search and content extraction using DuckDuckGo or SearXNG, with Playwright-based fetching and LLM-powered data extraction.
Updated 5 months ago (2026-04-10 20:28 UTC)
139
MIT
searxNcrawl
Browser Automation Web Scraping
DasDigitaleMomentum
A
license
A
quality
A
maintenance
MCP server for web search and crawling, integrating SearXNG metasearch and Crawl4AI for privacy-respecting search and content extraction.
Updated 2 months ago (2026-07-15 07:17 UTC)
3
161
MIT
searxng-mcp
Search Browser Automation
Jian-Zhan
F
license
Not graded
quality
D
maintenance
Privacy-focused web search MCP server using SearXNG with Streamable HTTP transport, supporting authentication and advanced search parameters.
Updated 6 months ago (2026-02-23 16:51 UTC)
-

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/MachineLearning-Nerd/SearchMCP'

If you have feedback or need assistance with the MCP directory API, please join our Discord server

Web MCP Server

Features

Tools Provided

Installation

Option 1: Docker (Recommended)

Option 2: Python Package

Option 3: With External SearxNG

Configuration

Environment Variables

Configuration File

Usage with MCP Clients

Claude Desktop

Other MCP Clients

Tool Reference

web_search

fetch_content

get_suggestions

Development

Setup

Manual MCP Smoke Test (Container + stdio)

Project Structure

Troubleshooting

Common Issues

Debug Mode

Docker Debugging

Security Considerations

License

Contributing

Acknowledgments

Available Tools

TDQS

TDQS

TDQS

Tool Schema Changelog

TDQS

Maintenance

Resources

Looking for Admin?

Related MCP Connectors

Related MCP Servers

searxng-mcp

webmcpofficial

searxNcrawl

searxng-mcp

Latest Blog Posts

MCP directory API