Provides web search and content extraction using Google Custom Search JSON API, supporting domain filtering, time ranges, and result depth.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@FindIt Search for AI ethics articles from .edu sites"
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.
A powerful web search and content extraction tool that provides comprehensive, real-time results using Google's search engine. Returns relevant web content with customizable parameters for result count, content type, time range, and domain filtering. Ideal for gathering current information, news, and detailed web content analysis.
Python 3.8 or higher
uv package manager
Clone the repository:
git clone https://github.com/KSDeshappriya/findit-mcp.git
cd findit-mcpInstall dependencies using uv:
uv pip install fastmcp httpx pydantic-settings python-dotenv beautifulsoup4Set up Google API credentials:
Create a Custom Search Engine ID from Google Programmable Search Engine
Follow the setup instructions at Google Custom Search JSON API
Set the environment variables or update the configuration file with your credentials:
GOOGLE_API_KEY=your_google_api_key # https://developers.google.com/custom-search/v1/introduction
GOOGLE_CSE_ID=your_custom_search_engine_id # https://programmablesearchengine.google.com/Configure your MCP client to use FindIt as specified in the Configuration section.
Related MCP server: Web Search MCP
{
"mcpServers": {
"FindIt": {
"command": "uv",
"args": [
"run",
"--with",
"fastmcp",
"--with",
"httpx",
"--with",
"pydantic-settings",
"--with",
"python-dotenv",
"--with",
"beautifulsoup4",
"fastmcp",
"run",
"/path/to/server.py"
],
"env": {
"GOOGLE_API_KEY": "your_google_api",
"GOOGLE_CSE_ID": "google_cse_id"
}
}
}
}Performs a web search using Google Programmable Search Engine with enhanced parameters.
Parameters:
query*: Search query string
search_depth: The depth of the search - 'basic' (faster) or 'advanced' (more comprehensive)
time_range: Limit results to a specific time frame ('day', 'week', 'month', 'year')
max_results: The maximum number of search results to return (1-10)
include_domains: List of domains to specifically include in the search results
exclude_domains: List of domains to specifically exclude from the search results
include_raw_content: Include the cleaned and parsed content from top results (limited to first 3 results)
Extracts and processes content from specified URLs, supporting in-depth content analysis.
Parameters:
urls*: List of URLs to extract content from
extract_depth: Depth of extraction - 'basic' or 'advanced'
include_images: Include a list of images extracted from the URLs in the response (limited to 10 per URL)
Research with Domain Filtering:
"Search for recent studies on climate change from .edu and .gov domains only and summarize the key findings."
Content Extraction:
"Extract the full content from these three articles about artificial intelligence ethics and create a comparative analysis."
Targeted Research with Time Constraints:
"Find news articles about renewable energy innovations from the past month and extract the most significant breakthroughs."
Competitive Analysis:
"Search for information about Tesla's latest electric vehicles and extract detailed specifications from their official website."
Academic Research:
"Find scientific papers on mRNA vaccines published in the last year, excluding results from news sites."
Technical Documentation:
"Extract the installation instructions from the official documentation pages for TensorFlow, PyTorch, and Keras."
Market Analysis:
"Search for recent financial reports about the semiconductor industry from the past week and extract key market trends."
Image Collection:
"Find websites about sustainable architecture and extract all relevant images with their descriptions."
Product Comparison:
"Search for detailed reviews of the latest MacBook Pro and extract specifications and performance benchmarks."
News Analysis:
"Find articles about the recent tech layoffs from major news sources published this month and extract the main facts."
"Large Concept Model (LCM) : A giant step towards AGI" generate report about that using web search and web scrap
This project is licensed under the Creative Commons Attribution-NonCommercial 4.0 International License (CC BY-NC 4.0) - see the LICENSE file for details.
Performs a web search using Google Programmable Search Engine with enhanced parameters. Returns search results with metadata and optionally raw content from top results.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | The search query string. | |
| time_range | No | Limit results to the specified time range. | |
| max_results | No | Number of search results to return (1-10). | |
| search_depth | No | The depth of the search. 'basic' is faster, 'advanced' is more comprehensive. | basic |
| exclude_domains | No | List of domains to specifically exclude from the search results. | |
| include_domains | No | List of domains to specifically include in the search results. | |
| include_raw_content | No | Include the cleaned and parsed content from top results. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It does disclose the return shape ('metadata and optionally raw content from top results'), which is useful, but says nothing about authentication/API key requirements, rate limits, or cost/latency differences between 'basic' and 'advanced' depth that the schema alludes to.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two short sentences, front-loaded with the action and the return behavior. The phrase 'with enhanced parameters' is filler that doesn't earn its place, keeping it out of 5 territory.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
There is no output schema, so the description must explain returns, and it does partially (metadata + optional raw content). However, for a 7-parameter search tool with no annotations, it omits key operational context such as result source restrictions and how 'include_raw_content' affects output size.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so every parameter is already documented in the schema (query, time_range, max_results range, search_depth, include/exclude domains, include_raw_content). The description adds no parameter-level meaning beyond the phrase 'enhanced parameters', so the baseline 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb+resource ('Performs a web search using Google Programmable Search Engine') which is clear enough to distinguish from the sibling findIt_scrap, though it never names that sibling directly. The addition of 'enhanced parameters' is vague and adds no discriminating power.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this versus the sibling findIt_scrap (search vs. fetch a specific page), and no prerequisites or exclusions. The agent must infer usage entirely from the tool name.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Extracts and processes content from specified URLs, supporting in-depth content analysis and optional image extraction. Perfect for research and content gathering tasks.
| Name | Required | Description | Default |
|---|---|---|---|
| urls | Yes | List of URLs to extract content from. | |
| extract_depth | No | Depth of extraction - basic extracts main content, advanced attempts to get more detailed content. | basic |
| include_images | No | Include a list of images extracted from the URLs in the response. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and falls short: it says nothing about authentication, rate limits, failure behavior on unreachable URLs, whether JavaScript is rendered, or how batch URLs are handled. 'Processes' is left undefined, and the only behavioral hints (depth modes) merely restate the schema.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two short sentences that are front-loaded with the core action, which is good. The second sentence, 'Perfect for research and content gathering tasks,' is unsupported marketing filler that consumes space without informing invocation.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no annotations and no output schema, the description should explain what a call returns (extracted text shape, image list) and how partially failed URLs are reported. It provides none of this, so an agent cannot predict results or handle errors from the definition alone.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so all three parameters are already documented in the schema, making 3 the baseline. The description's mention of 'in-depth content analysis' and 'optional image extraction' loosely parallels extract_depth and include_images but adds no syntax, defaults, or trade-off detail beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a concrete verb and resource: 'Extracts and processes content from specified URLs,' with optional image extraction. An agent can tell it is a URL-scraping tool, though it never names or contrasts itself with the sibling findIt_google, leaving their division of labor to inference.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The only guidance is the vague marketing line 'Perfect for research and content gathering tasks,' which does not say when to pick this over findIt_google, when not to use it, or what prerequisites (e.g., already having URLs) exist. No alternative is named.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.1.0findIt_googlefindIt_scrapScored across 2 tools
findIt_google performs web search, while findIt_scrap extracts content from specified URLs. Their actions and inputs are clearly distinct, so an agent can easily choose the right tool.
Both tools share the findIt_ prefix and snake_case style. The suffixes are slightly inconsistent: 'google' is a service noun, while 'scrap' is an abbreviated verb, but the convention is still readable.
Two tools cover the basic search-and-scrape workflow, but a 2-tool surface is thin and sits at the borderline of the typical 3-15 range. It is acceptable for a narrow purpose but feels minimal.
The server covers core web research needs: searching the web and extracting page content. Minor gaps such as batch scraping, pagination controls, or alternate search backends exist but are not essential for basic usage.
Search Google straight from your AI agent. Web results, images, videos, news, products, scholarly ar
Provides AI assistants with access to Seltz's powerful Web Search capabilities.
Web search, scraping, Google Trends and data lookups. Paid per call in USDC on Base via x402.
Web search, news, page retrieval, sitemaps, and trending topics through Search1API.
