広告掲載
MCP.so
ログイン

Developer Research MCP Server

@ali-nr

リポジトリ

基本情報

カテゴリ

データと分析

トランスポート

stdio

作者

ali-nr

Developer Research MCP Server について

MCP server for developer research tasks

Developer Research MCP Server の設定

標準の設定はありません

このサーバーの README には解析可能な MCP 設定ブロックが含まれていません。インストール手順はリポジトリをご確認ください。

リポジトリ

Developer Research MCP Server のツール

ツール一覧はまだありません

この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is Developer Research MCP Server?

A Model Context Protocol (MCP) server that provides structured web search capabilities for AI agents and development tools. It initially uses OpenRouter for its search functionality and is built with an extensible architecture to support additional research providers in the future.

How to use Developer Research MCP Server?

Install Node.js v18+, clone the repository, run npm install and npm build, then configure environment variables (e.g., OPENROUTER_API_KEY) in a .env file. The server communicates over stdio and can be integrated into clients like Roo Code by adding its configuration to .roo/mcp.json.

Key features of Developer Research MCP Server

  • Web search via providers like OpenRouter.
  • Optimized for technical and software development content.
  • Extensible architecture for multiple research providers.
  • Reliable error handling and retry mechanisms.
  • Returns structured JSON results.

Use cases of Developer Research MCP Server

  • AI agents performing real-time web searches for technical queries.
  • Developers retrieving up-to-date documentation or code examples.
  • Integrating web research into automated development workflows.
  • Querying focused technical or development-oriented search results.

よくある質問

1

What tools does this server provide?

It provides one tool: `search_web`, which performs a web search and returns results in a structured JSON format.

2

What parameters does the search_web tool accept?

It accepts a required `query` string, an optional `num_results` (1–10, default 5), and an optional `focus` (values: "technical", "development", or "general", default "technical").

3

How do I add a new research provider?

The modular architecture allows adding providers by implementing a common interface; each provider becomes a distinct module independent of others.

4

What environment variables are required?

`OPENROUTER_API_KEY` is required for the OpenRouter provider. `OPENROUTER_API_URL` is optional and defaults to `https://openrouter.ai/api/v1`.

5

How is the server installed and configured?

Clone the repo, run `npm install` and `npm build`, create a `.env` file with your API key, then point the client (e.g., Roo Code) to the built `index.js` with the environment loaded.

コメント

「データと分析」の他のコンテンツ

Subtext

Subtext by Fullstory

Session replay, built for agents. Subtext is agentic session review: it captures production sessions of your app and connects them to your coding agent — Claude Code, Cursor, Codex, Devin, your own harness — so it can

9

Batru

Batru

Real, calibrated win-rate predictions, pick recommendations, counters, synergy and tier lists for Dota 2, Deadlock and Marvel Rivals, from production models trained on ~20M matches. Free hosted endpoint (Streamable HTTP)

Draxlr

Vivek

Draxlr is a remote MCP server that connects AI assistants to your SQL databases. Explore schemas, run read-only queries, and work with your saved queries and dashboards over MCP. Hosted at https://api.draxlr.com with OAu

AI Website Auditor

Armstrong Holdco LLC

Check whether ChatGPT, Claude, Perplexity and Gemini recommend a business, right from your AI agent. Get a 0 to 100 AI visibility score with a per-engine breakdown, the competitor named in your place, a full site audit,

TikTok MCP Server

HasData

Hosted TikTok MCP server for AI agents: read public profiles, account videos, comments and replies, or search videos and creators. Structured JSON for creator research and content analysis.

3
広告掲載