Skillget

daedra

mcp
Guvenlik Denetimi
Uyari
Health Uyari
  • License — License: MIT
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Low visibility — Only 9 GitHub stars
Code Gecti
  • Code scan — Scanned 7 files during light audit, no dangerous patterns found
Permissions Gecti
  • Permissions — No dangerous permissions requested
Purpose
This tool is a self-contained web search MCP server written in pure Rust. It provides an automatic fallback chain across multiple search engines and websites, allowing AI models and CLI tools to search the web from any IP address without requiring external dependencies or mandatory API keys.

Security Assessment
Overall Risk: Low. The tool inherently makes external network requests to perform web searches and fetch webpage contents, which is its primary function. It does not request dangerous local system permissions, and the automated code scan found no dangerous patterns, hardcoded secrets, or hidden shell execution. Users should be aware that search queries will be sent to various external third-party services (like Wikipedia, GitHub, Bing, etc.), but this is completely expected behavior for a search tool.

Quality Assessment
The project is high quality. It is actively maintained, with its most recent push occurring today. It uses the standard, permissive MIT license and utilizes Continuous Integration (CI). The only notable warning is its low community visibility; with only 9 GitHub stars, the tool is very new and has not yet been widely adopted or heavily vetted by a large user base. However, the codebase is clean and written in a memory-safe language.

Verdict
Safe to use, though keep in mind its low community visibility means it has not yet been battle-tested by a wide audience.
SUMMARY

Self-contained web search MCP server. Exhaustive backends with automatic fallback. Pure Rust. Works from any IP.

README.md

daedra

Daedra

Self-contained web search MCP server. Rust. 7 backends. Works from any IP.
No API keys required. No Docker. No Python.

Crates.io
CI
License: MIT

Daedra is a self-contained web search MCP server written in Rust. Multiple search backends with automatic fallback. Works from any IP — datacenter, VPS, residential. No API keys required for basic search.

Why Daedra?

Every major search engine (Google, Bing, DuckDuckGo, Brave) blocks datacenter/VPS IPs with CAPTCHAs since 2025. Daedra solves this with a multi-backend fallback chain that automatically finds a backend that works:

Serper (API) → Tavily (API) → Bing → Wikipedia → StackOverflow → GitHub → DuckDuckGo

No Docker. No Python. No SearXNG. Pure Rust. Daedra IS the search infrastructure.

Install

cargo install daedra

Search backends

Backend Type API Key Works from VPS?
Serper.dev Google JSON API SERPER_API_KEY Yes
Tavily AI-optimized API TAVILY_API_KEY Yes
Bing HTML scraping None Sometimes (CAPTCHA risk)
Wikipedia OpenSearch API None Always
StackExchange Public API None Always
GitHub Public API None / GITHUB_TOKEN Always
DuckDuckGo HTML scraping None Rarely (blocked since mid-2025)

Backends are tried in order. First one that returns results wins.

Usage

MCP Server (for Claude, Cursor, pawan, etc.)

{
  "mcpServers": {
    "daedra": {
      "command": "daedra",
      "args": ["serve", "--transport", "stdio", "--quiet"]
    }
  }
}

CLI

# Search
daedra search "rust async runtime" --num-results 5

# Fetch a webpage as Markdown
daedra fetch https://rust-lang.org

# Check backend health
daedra check

# Server info
daedra info

As a Rust library

use daedra::tools::SearchProvider;
use daedra::types::SearchArgs;

#[tokio::main]
async fn main() -> anyhow::Result<()> {
    let provider = SearchProvider::auto();
    let args = SearchArgs {
        query: "rust programming".to_string(),
        options: None,
    };
    let results = provider.search(&args).await?;
    for r in &results.data {
        println!("{} — {}", r.title, r.url);
    }
    Ok(())
}

MCP Tools

web_search

Search the web with automatic backend fallback.

{
  "query": "search terms",
  "options": {
    "region": "wt-wt",
    "safe_search": "MODERATE",
    "num_results": 10,
    "time_range": "w"
  }
}

Aliases: search_duckduckgo (backward compat)

visit_page

Fetch and extract web page content as Markdown.

{
  "url": "https://example.com",
  "selector": "article.main",
  "include_images": false
}

Architecture

Daedra
├── SearchProvider (fallback chain)
│   ├── SerperBackend      (Google via API)
│   ├── TavilyBackend      (AI-optimized API)
│   ├── BingBackend         (HTML scraping)
│   ├── WikipediaBackend    (OpenSearch API)
│   ├── StackExchangeBackend (Public API)
│   ├── GitHubBackend       (Public API)
│   └── SearchClient        (DuckDuckGo HTML)
├── FetchClient (HTML → Markdown)
├── SearchCache (moka async cache)
├── MCP Server
│   ├── STDIO transport (JSON-RPC)
│   └── SSE transport (Axum HTTP)
└── CLI (clap)

Configuration

# Optional API keys (improves result quality)
export SERPER_API_KEY=...     # Google results via Serper
export TAVILY_API_KEY=...     # AI-optimized search
export GITHUB_TOKEN=...       # Higher GitHub API rate limit

# Logging
export RUST_LOG=daedra=info

Ecosystem

Project What
pawan CLI coding agent that uses daedra for web search via MCP
ares Agentic retrieval-enhanced server
eruka Context intelligence engine

Built by DIRMACS.

License

MIT

Yorumlar (0)

Sonuc bulunamadi