presearch-search-api-mcp
Verified Safeby NosytLabs
Overview
Connects AI assistants to the Presearch decentralized search engine for privacy-focused web search, scraping, and content analysis.
Installation
npx presearch-mcp-serverEnvironment Variables
- PRESEARCH_API_KEY
- PRESEARCH_NODE_API_KEY
Security Notes
The server utilizes robust input validation via Zod schemas and correctly fetches API keys from environment variables (`PRESEARCH_API_KEY`, `PRESEARCH_NODE_API_KEY`). Network requests include rate limiting and retry logic. However, the `puppeteer` dependency, used for PDF generation in the `site_export` tool, can introduce significant resource consumption and potential security vulnerabilities (e.g., RCE, DoS) if not run within a tightly sandboxed and containerized environment. While `docker-compose.yml` suggests containerization, advanced sandboxing is not explicitly configured in the provided code snippets. Cookie management in `contentFetcher` is for session persistence but presents a potential data leakage risk if used improperly or if a malicious site exploits it. No explicit use of `eval` or intentional obfuscation was found.
Similar Servers
mcp-omnisearch
A Model Context Protocol (MCP) server that provides unified access to multiple search providers, AI tools, and content processing/enhancement features through a single interface.
opensearch-mcp-server-py
Enables AI assistants and Large Language Models (LLMs) to interact with OpenSearch clusters by providing a standardized Model Context Protocol (MCP) interface for operations like searching, retrieving mappings, and managing shards.
mcp-server
Provides a Model Context Protocol (MCP) server for integrating comprehensive search and data extraction via SerpApi.
scrapegraph-mcp
Provides a Model Context Protocol (MCP) server that integrates with ScrapeGraph AI, enabling language models to perform advanced AI-powered web scraping and structured data extraction across single pages, multiple pages, and search results.