Integrated Search MCP Server

by mako10k

283 downloads
Not rated
GitHub

About

Integrated Search MCP Server - Google Custom Search + Redmine API integration for AI assistants

Details

Author
mako10k
Downloads
283
Categories
Search

- Web search via Google Custom Search API
- Image search with advanced filtering (size, type, safe search)
- Redmine issue listing, creation, and detailed viewing
- Redmine project browsing with pagination
- Support for language restrictions, site‑specific searches, and file type filtering
- Robust error handling and input validation using Zod schemas

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

  1. Download and install Highlight from highlightai.com/download
  2. Navigate to the plugins tab and select "Add Custom Plugin"
  3. Configure the plugin with the settings below
    Plugin Name Integrated Search MCP Server
    Command (node, npx, python, etc.)

    Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.

  4. Enable "Start Automatically" if you want the plugin to start when Highlight launches

From the repository

Install via git clone, npm install, and configure environment variables (GOOGLE_API_KEY, GOOGLE_SEARCH_ENGINE_ID, optionally REDMINE_URL and REDMINE_API_KEY). Build with npm run build, then add the server to an MCP client (e.g., Claude Desktop) by specifying node and the path to build/index.js with the environment variables. The server exposes six tools: google_search, google_search_images, redmine_list_issues, redmine_create_issue, redmine_list_projects, and redmine_get_issue.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "integrated search mcp server": {
            "integrated-search-server": {
                "command": "node",
                "args": [
                    "/absolute/path/to/mcp-integrated-search-server/build/index.js"
                ],
                "env": {
                    "GOOGLE_API_KEY": "",
                    "GOOGLE_SEARCH_ENGINE_ID": "",
                    "REDMINE_URL": "",
                    "REDMINE_API_KEY": ""
                }
            }
        }
    }
}

McpServers

{
    "integrated-search-server": {
        "command": "node",
        "args": [
            "/absolute/path/to/mcp-integrated-search-server/build/index.js"
        ],
        "env": {
            "GOOGLE_API_KEY": "",
            "GOOGLE_SEARCH_ENGINE_ID": "",
            "REDMINE_URL": "",
            "REDMINE_API_KEY": ""
        }
    }
}

Integrated Search MCP Server

A Model Context Protocol (MCP) server that provides both Google Custom Search API and Redmine API integration, allowing AI assistants to search the web and manage Redmine projects seamlessly.

Features

Google Custom Search

- Web Search: Search the web using Google Custom Search API - Image Search: Find images with advanced filtering options - Advanced Parameters: Support for language restrictions, site-specific searches, file type filtering, and more

Redmine API Integration

- Issue Management: List, create, and view Redmine issues - Project Management: Browse Redmine projects - Advanced Filtering: Filter issues by project, status, assignee, and more - Comprehensive Details: Access full issue information including custom fields

Common Features

- Error Handling: Robust error handling with detailed error messages - Input Validation: Comprehensive input validation using Zod schemas - Configurable: Environment-based configuration - Dual API Support: Seamlessly switch between Google Search and Redmine operations

Installation

1. Clone this repository:

git clone <repository-url>
cd mcp-integrated-search-server

2. Install dependencies:

npm install

3. Set up environment variables:

cp .env.example .env

4. Edit .env file with your API credentials:
```env

No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.