接入你的智能体
從發布者安裝。不是 PlugMCP 端點。
遠端 URL 還是本機指令? 兩種安裝方式的差異
Your AI-Powered Research Assistant. Conduct iterative, deep research using Google Gemini 2.5 Flash with Google Search Grounding and URL context. No web-scraping dependency is required.
The goal of this project is to provide the simplest yet most effective implementation of a deep research agent. It's designed to be easily understood, modified, and extended, aiming for a codebase under 500 lines of code (LoC).
Key Features:
flowchart TB
subgraph Input
Q[User Query]
B[Breadth Parameter]
D[Depth Parameter]
end
DR[Deep Research] -->
SQ[SERP Queries] -->
PR[Process Results]
subgraph Results[Results]
direction TB
NL((Learnings))
ND((Directions))
end
PR --> NL
PR --> ND
DP{depth > 0?}
RD["Next Direction:
- Prior Goals
- New Questions
- Learnings"]
MR[Markdown Report]
%% Main Flow
Q & B & D --> DR
%% Results to Decision
NL & ND --> DP
%% Circular Flow
DP -->|Yes| RD
RD -->|New Context| DR
%% Final Output
DP -->|No| MR
%% Styling
classDef input fill:#7bed9f,stroke:#2ed573,color:black
classDef process fill:#70a1ff,stroke:#1e90ff,color:black
classDef recursive fill:#ffa502,stroke:#ff7f50,color:black
classDef output fill:#ff4757,stroke:#ff6b81,color:black
classDef results fill:#a8e6cf,stroke:#3b7a57,color:black
class Q,B,D input
class DR,SQ,PR process
class DP,RD recursive
class MR output
class NL,ND results
What are Persona Agents?
In deep-research, we utilize the concept of "persona agents" to guide the behavior of the Gemini language models. Instead of simply prompting the LLM with a task, we imbue it with a specific role, skills, personality, communication style, and values. This approach helps to:
Examples of Personas in use:
By leveraging persona agents, deep-research aims to achieve more targeted, consistent, and high-quality research outcomes from the Gemini language models.
Core modules:
src/deep-research.ts — orchestrates queries, batching, analysis, and synthesis
generateSerpQueries() uses Gemini to propose SERP-style queries from your prompt and prior learningsprocessSerpResult() splits content, batches Gemini calls with tools enabled, extracts learnings and citationsconductResearch() runs analysis passes over semantic chunkswriteFinalReport() builds the final professional Markdown reportsrc/ai/providers.ts — GoogleGenAI wrapper for Gemini 2.5 Flash, batching, token control, optional toolssrc/ai/text-splitter.ts — RecursiveCharacter and Semantic splitterssrc/mcp-server.ts — MCP server entry point and typessrc/run.ts — CLI entry pointPipeline highlights:
generateBatch, generateBatchWithTools)deep-research-mcp-server/
├─ src/
│ ├─ ai/
│ │ ├─ providers.ts # Gemini wrapper, tools, batching, caching
│ │ └─ text-splitter.ts # Semantic/recursive splitters
│ ├─ mcp-server.ts # MCP server entry/types
│ ├─ deep-research.ts # Orchestrator: queries → analysis → synthesis
│ ├─ prompt.ts # System + templates
│ ├─ feedback.ts # Refinement/feedback loop
│ ├─ output-manager.ts # Report/output formatting
│ ├─ progress-manager.ts # CLI progress
│ ├─ terminal-utils.ts # CLI helpers
│ ├─ types.ts # Zod schemas/types
│ └─ utils/ # JSON/sanitize helpers
├─ dist/ # Build output
├─ .env.example # Environment template
├─ package.json # Scripts/deps
└─ README.md
Clone the repository:
git clone [your-repo-link-here]
Install dependencies:
npm install
Set up environment variables: Create a .env.local file in the project root:
# Required
GEMINI_API_KEY="your_gemini_key"
# Recommended defaults
GEMINI_MODEL=gemini-2.5-flash
GEMINI_MAX_OUTPUT_TOKENS=65536
CONCURRENCY_LIMIT=5
# Gemini tools (enable as needed)
ENABLE_GEMINI_GOOGLE_SEARCH=true
ENABLE_GEMINI_CODE_EXECUTION=false
ENABLE_GEMINI_FUNCTIONS=false
Build the project:
npm run build
To run deep-research as an MCP tool, start the MCP server:
node --env-file .env.local dist/mcp-server.js
You can then invoke the deep-research tool from any MCP-compatible agent using the following parameters:
query (string, required): The research query.depth (number, optional, 1-5): Research depth (default: moderate).breadth (number, optional, 1-5): Research breadth (default: moderate).existingLearnings (string[], optional): Pre-existing research findings to guide research.Example MCP Tool Arguments (JSON shape):
{
"name": "deep-research",
"arguments": {
"query": "State of multi-agent research agents in 2025",
"depth": 3,
"breadth": 3,
"existingLearnings": [
"Tool use improves grounding",
"Batching reduces latency"
]
}
}
const mcp = new ModelContextProtocolClient(); // Assuming MCP client is initialized
async function invokeDeepResearchTool() {
try {
const result = await mcp.invoke("deep-research", {
query: "Explain the principles of blockchain technology",
depth: 2,
breadth: 4
});
if (result.isError) {
console.error("MCP Tool Error:", result.content[0].text);
} else {
console.log("Research Report:\n", result.content[0].text);
console.log("Sources:\n", result.metadata.sources);
}
} catch (error) {
console.error("MCP Invoke Error:", error);
}
}
invokeDeepResearchTool();
To run deep-research directly from the command line:
npm run start "your research query"
Example:
npm run start "what are latest developments in ai research agents"
For interactive testing and debugging of the MCP server, use the MCP Inspector:
npx @modelcontextprotocol/inspector node --env-file .env.local dist/mcp-server.js
GEMINI_API_KEY to the MCP server process; model and tool flags via env.CONCURRENCY_LIMIT to balance speed vs rate limits.GEMINI_API_KEY — requiredGEMINI_MODEL — defaults to gemini-2.5-flashGEMINI_MAX_OUTPUT_TOKENS — defaults to 65536CONCURRENCY_LIMIT — defaults to 5ENABLE_GEMINI_GOOGLE_SEARCH — enable Google Search Grounding toolENABLE_GEMINI_CODE_EXECUTION — enable code execution toolENABLE_GEMINI_FUNCTIONS — enable function callingOptional providers (planned/behind flags): Exa/Tavily can be integrated later; Firecrawl is not required for the current pipeline.
git clone https://github.com/ssdeanx/deep-research-mcp-server
cd deep-research-mcp-server
npm i && npm run build
Create .env.local (see Setup)
Run as MCP server (Inspector)
npx @modelcontextprotocol/inspector node --env-file .env.local dist/mcp-server.js
npm run start "state of multi-agent research agents in 2025"
# Abstract
Concise overview of the research goal, scope, method, and key findings.
# Table of Contents
...
# Introduction
Context and framing.
# Body
Evidence-backed sections with citations.
# Methodology
How sources were found and analyzed.
# Limitations
Assumptions and risks.
# Key Learnings
Bulleted insights and takeaways.
# References
Normalized citations to visited URLs.
npm run build and tsc --noEmit must pass.README.md and .env.example when changing env/config.ENABLE_EXA_PRIMARY), Google grounding for augmentation.GEMINI_API_KEY is set in .env.local and processes are started with --env-file .env.local.ENABLE_GEMINI_GOOGLE_SEARCH, ENABLE_GEMINI_CODE_EXECUTION, ENABLE_GEMINI_FUNCTIONS.CONCURRENCY_LIMIT (e.g., 3) or rerun with fewer simultaneous queries.GEMINI_MAX_OUTPUT_TOKENS.MIT License - Free and Open Source. Use it freely!
✨ Highlights of the latest changes. See also Roadmap.
Performance:
Your AI-Powered Research Assistant. Conduct iterative, deep research using Google Gemini 2.5 Flash with Google Search Grounding and URL context. No web-scraping dependency is required.
工具
尚無工具清單。遠端伺服器會在首次健康檢查後取得工具清單。
常見問題
在本頁複製適用於 Cursor、Claude Desktop、Claude Code 或 VS Code 的 stdio 設定。它使用發布者的安裝方式,而不是 PlugMCP 代理伺服器。
這筆記錄未列出必要的環境變數。
Deep Research 透過 stdio 在本機執行。
上次檢查時間:2026-10-27。 Your AI-Powered Research Assistant. Conduct iterative, deep research using Google Gemini 2.5 Flash with Google Search Grounding and URL context. No web-scraping dependency is required.