Mcp server with local RAG on pdf and word documents and web search
Config is the same across clients — only the file and path differ.
{
"mcpServers": {
"my-mcp-example": {
"env": {
"EMBEDD_KEY": "",
"EMBEDD_MODEL": "text-embedding-nomic-embed-text-v2-moe",
"GUTHUB_TOKEN": "github_pat_yyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyy",
"EMBEDD_ENDPOINT": "http://localhost:1234/v1/",
"WEB_SEARCH_ENGINES": "DuckDuckGo,Firecraw, Baidu",
"WEB_SEARCH_FirecrawApiKey": "fc-xxxxxxxxxxxxxxxxxxxxxxxxxx",
"WEB_SEARCH_duckduckgoRegion": "en-en"
},
"command": "C:\\path_to_exe_file\\SampleMcpServer.exe"
}
}
}Are you the author?
Add this badge to your README to show your security score and help users find safe servers.
This is a sample server that demonstrates how to implement an MCP (Model Context Protocol) server using .NET.
No automated test available for this server. Check the GitHub README for setup instructions.
Five weighted categories — click any category to see the underlying evidence.
No known CVEs.
No package registry to scan.
Click any tool to inspect its schema.
Be the first to review
Have you used this server?
Share your experience — it helps other developers decide.
Sign in to write a review.
Others in search
Web and local search using Brave Search API
The official MCP server implementation for the Perplexity API Platform
Production ready MCP server with real-time search, extract, map & crawl.
Context7 Platform -- Up-to-date code documentation for LLMs and AI code editors
MCP Security Weekly
Get CVE alerts and security updates for SampleMcpServer and similar servers.
Start a conversation
Ask a question, share a tip, or report an issue.
Sign in to join the discussion.
This is a sample server that demonstrates how to implement an MCP (Model Context Protocol) server using .NET.
random_number: Generate random numberscalc: Perform calculation: add, subtract, multiply, divide, power, square rootfile_operations: Read, write, and list filesinternet_search: Search the web with DuckDuckGo, Firecraw and Baidugithub_search: Search GitHub repositories and coderag: Retrieve information from local files with FAISS: pdf, docx, xlsx, pptx, other textFaissVectorStore (as InMemoryVectorStore) on GitHub Gist
Build the project:
dotnet build
Run the server:
dotnet run
Connect your MCP client to this server using the stdio transport.
Example configuration in LM Studio (mcp.json):
{
"mcpServers": {
"my-mcp-example": {
"command": "C:\\path_to_exe_file\\SampleMcpServer.exe",
"env": {
"WEB_SEARCH_ENGINES": "DuckDuckGo,Firecraw, Baidu",
"WEB_SEARCH_FirecrawApiKey": "fc-xxxxxxxxxxxxxxxxxxxxxxxxxx",
"WEB_SEARCH_duckduckgoRegion": "en-en",
"GUTHUB_TOKEN": "github_pat_yyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyy",
"EMBEDD_ENDPOINT": "http://localhost:1234/v1/",
"EMBEDD_MODEL": "text-embedding-nomic-embed-text-v2-moe",
"EMBEDD_KEY": ""
}
}
}
}
This project is licensed under the MIT License.