A
licenseNot graded
qualityF
maintenanceProvides AI-powered web search capabilities using Tavily's search API, enabling LLMs to perform sophisticated web searches, get direct answers to questions, and search recent news articles.
72
MIT
MCP Deep Research
by baranwang
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., "@MCP Deep Researchresearch the latest developments in quantum computing for 2024"
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.
MCP Deep Research
简体中文 | English
Overview
MCP Deep Research is a tool that allows you to search the web for information. It is built with the Model Context Protocol and the Tavily API.
Related MCP server: Tavily MCP Server
Configuration
{
"mcpServers": {
"deep-research": {
"command": "npx",
"args": ["-y", "mcp-deep-research@latest"],
"env": {
"TAVILY_API_KEY": "your_tavily_api_key", // Required
"MAX_SEARCH_KEYWORDS": "5", // Optional, default 5
"MAX_PLANNING_ROUNDS": "5" // Optional, default 5
}
}
}
}The tool can be configured using the following environment variables:
TAVILY_API_KEY: The API key for the Tavily API.MAX_SEARCH_KEYWORDS: The maximum number of search keywords to use.MAX_PLANNING_ROUNDS: The maximum number of planning rounds to use.TAVILY_HTTP_PROXY/TAVILY_HTTPS_PROXY: The proxy address for the Tavily API.
Use with Smithery
Install via Smithery, compatible with Claude Desktop client:
npx -y @smithery/cli install @baranwang/mcp-deep-research --client claudeCompatibility Notice
This MCP server is optimized for prompt-based MCP clients. For MCP clients implemented using function calling mechanisms, the performance and results may not be optimal.
Verified prompt-based MCP clients:
Verified function calling-based MCP clients:
Available Tools
1 tooldeep-researchC
Deep web information search tool that can conduct multi-round in-depth research based on keywords and topics
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| question | Yes | User question | |
| reference | No | Reference materials | |
| keywords | No | Search keywords, please provide 1~5 keywords. Each keyword must: include complete subject and predicate, avoid pronouns and references, have independent search value, avoid logical overlap between keywords, and be directly relevant to the question | |
| topic | No | Search topic | general |
| rounds | No | Current search round, defaults to 1 |
TDQS
C2.9/5.0
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description notes multi-round capability but does not explain what multi-round entails or any behavioral details. No annotations are provided, so the description should carry the burden, but it only gives a high-level overview. No disclosure of side effects, auth requirements, or error handling.
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 a single sentence, concise and front-loaded with the main purpose. It avoids unnecessary words but could be slightly more informative without increasing length significantly.
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?
The tool has 5 parameters, no output schema, and no annotations. The description only gives a high-level purpose but does not explain the return format, result structure, or how to use the tool effectively. It lacks completeness for a research tool with multi-round capability.
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 parameters are well-documented in the schema. The tool description mentions 'keywords and topics' but does not add new information beyond the schema. It does not explain parameter usage or constraints further.
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 it is a deep web information search tool capable of multi-round research. It mentions keywords and topics, providing a clear purpose. However, it does not differentiate from siblings (none present) and could elaborate on the output or scope.
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 usage guidance is provided. The description does not specify when to use this tool over others, nor does it mention any prerequisites or limitations. It only describes the tool's function.
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
v1.0.0- Changed
deep-research2 fields changed- added
Input schema / $schemaAdded value: +"http://json-schema.org/draft-07/schema#" - added
Input schema / additionalPropertiesAdded value: +false
1 tool update
- First observed
deep-research
TDQS
B3.3/5.0
Scored across 1 tool
Disambiguation5/5
With only one tool, there is no possible confusion between overlapping functions. The single tool has a clear, distinct purpose.
Naming Consistency5/5
The single tool name 'deep-research' is lowercase hyphens, consistent and descriptive of the action. There are no other names to conflict.
Tool Count3/5
One tool is quite thin for a deep research capability, though the tool explicitly says it conducts multi-round research internally, making a single entry point feasible. It borders between too few and acceptable for a narrow scope.
Completeness4/5
The tool covers the full research workflow in one call, including multi-round searching. Minor gaps exist around controlling research depth, output formats, or retrieving past research, but the core purpose is served.
Maintenance
ActivityInactive
ResponsivenessNo issues
Related MCP Connectors
Web research for agents: quality-scored Google search, webpage extraction, and deep research.
Real-time web search, reasoning, and research through Perplexity's API
Real-time web and scholarly search with cited answers and multi-step deep research.
Web search, fetch, extract, and research for AI agents. Markdown output + AI-synthesized answers.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to perform up-to-date web searches through the Tavily API, providing comprehensive search results with AI-generated summaries.7MIT
- FlicenseCqualityDmaintenanceEnables web search capabilities through the Tavily API, allowing users to perform web searches and retrieve information from the internet through natural language queries.3-
- FlicenseNot gradedqualityCmaintenanceProvides web search capabilities using the Tavily API, enabling AI models to search the internet and retrieve up-to-date information.-