A
licenseA
qualityD
maintenanceA general MCP server providing web search capabilities using DeepSeek's native online search API.
1
16 npm
28
MIT
deep-search-mcp
by joaomj
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., "@deep-search-mcpsearch for the latest advancements 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.
Deep Search MCP Server
A deep web search MCP server using LinkUp API.
This is a TypeScript-based MCP server that implements deep web search capabilities. It demonstrates core MCP concepts by providing:
Tools for performing deep web searches
Structured results from LinkUp API
Features
Tools
deep_search- Perform deep web searchesTakes query string as required parameter
Optional max_results parameter (default: 5)
Returns structured search results
Related MCP server: tavily-mcp
Setup
Install dependencies:
npm installBuild the server:
npm run buildConfigure the MCP server in your settings:
{
"mcpServers": {
"deep-search-mcp": {
"command": "node",
"args": ["/home/joao/Cline/MCP/linkup-mcp-server/build/index.js"],
"env": {
"LINKUP_API_KEY": "your-api-key-here"
}
}
}
}The API key can be obtained from LinkUp API service.
Running
For development with auto-rebuild:
npm run watchFor production:
npm startDebugging
Since MCP servers communicate over stdio, debugging can be challenging. We recommend using the MCP Inspector:
npm run inspectorNEXT STEPS
Future improvements to consider:
Add caching for search results to improve performance
Implement pagination for large result sets
Add filtering options for search results
Support different output formats (markdown, HTML)
Add rate limiting and request throttling
Implement authentication for API access
Add more search parameters (date ranges, domains, etc.)
Improve error handling and user feedback
Add logging for debugging and monitoring
Implement health check endpoints
Available Tools
1 tooldeep_searchB
Perform a deep web search using LinkUp API
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Search query | |
| max_results | No | Maximum number of results to return |
TDQS
B3.3/5.0
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 only states what the tool does (deep web search) but doesn't mention any potential side effects, rate limits, authentication, return format, or other behavioral traits.
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 sentence with no wasted words. It immediately states the core action and the API used, making it appropriately concise and front-loaded.
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?
For a simple tool with two parameters and no output schema, the description is minimally adequate. However, it lacks details about LinkUp API specifics, result format, or any limitations, leaving some context gaps for a tool that could have more complexity.
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 provides 100% coverage with descriptions for both parameters (query and max_results), so the description doesn't need to add parameter details. The schema already does the heavy lifting, making this a baseline 3.
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 performs a deep web search using the LinkUp API, which is a specific verb+resource combination. There are no sibling tools to differentiate from, so it doesn't need to distinguish itself, but the purpose is clear.
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 implies the tool is used when a deep web search is needed, but it doesn't provide explicit context about when to use it vs alternatives or any exclusions. No alternatives are mentioned, so the usage guidance is minimal.
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 tool update
v0.1.0- First observed
deep_search
TDQS
A3.5/5.0
Scored across 1 tool
Disambiguation5/5
With only one tool, there is no possibility of confusion between tools. The tool's purpose is clearly stated as performing a deep web search.
Naming Consistency5/5
The single tool name 'deep_search' follows a clear verb_noun convention. There are no other tools to introduce naming inconsistencies.
Tool Count3/5
A single tool is borderline thin for a search server, which might benefit from additional operations like result filtering or history. However, for a very narrow scope, it could be acceptable.
Completeness3/5
The tool covers the core search action but lacks ancillary capabilities that users might expect, such as pagination, saved searches, or multi-phase queries. This leaves the surface minimal and somewhat incomplete for complex workflows.
Maintenance
ActivityInactive
ResponsivenessNo issues
Related MCP Connectors
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.
An MCP server for deep research or task groups
Serper MCP — wraps the Serper Google Search API (serper.dev)
Related MCP Servers
- AlicenseBqualityDmaintenanceMCP server providing search, extract, map, and crawl tools powered by Tavily for real-time web data access.413 npmMIT
- FlicenseAqualityCmaintenanceMCP server that provides a search_web tool to query a self-hosted SearXNG instance and return structured web search results.1-
- AlicenseAqualityBmaintenanceA DeepSeek-powered MCP server that provides high-accuracy web search using the native DeepSeek V4-Flash search API, offering standard and deep research tools that return cited answers and cross-verified reports.41MIT