Socraticode MCP Server
MCP server for enterprise local codebase indexing, semantic search, and code dependency graphs.
MCP servers for web search, knowledge bases, document retrieval, and semantic search.
MCPpedia tracks 863 search MCP servers. 236 of them score at least 50 out of 100, and 160 clear 70 - about 19% of what has been published in this space. The remaining 627 are thinner: registry entries with no description, no published tool schema, or no commit in the last year. They are all still listed here, because knowing a server exists and is unmaintained is worth as much as knowing a good one exists.
Socraticode MCP Server leads the list at 95/100. Tavily MCP (95) and Modelcontextprotocol (94) follow. Every score is the same five weighted inputs: security (CVE scanning, tool-poisoning detection, and whether the server authenticates at all), maintenance (commit recency, release cadence, and download trend), documentation, client compatibility, and token efficiency - how much of your context window the tool definitions consume before you have asked anything.
10 of these servers are published by the vendor behind the underlying API rather than by a third party, which is usually the difference between an integration that tracks upstream changes and one that quietly stops working. 1 currently carry an open CVE; those are flagged on the server's own page with the advisory and its severity.
Also see: All Search servers, Best Productivity, Best Developer Tools, Best Data, Best Finance
Last updated
MCP server for enterprise local codebase indexing, semantic search, and code dependency graphs.
MCP server for advanced web search using Tavily
The official MCP server implementation for the Perplexity API Platform
Unified real-time search engine skill for AI agents.
An autonomous agent that conducts deep research on any data using any LLM providers
Up-to-date code docs for any prompt
Web search, URL discovery, scraping & extraction with agent-browser and search providers
Local Deep Research achieves ~95% on SimpleQA benchmark (tested with GPT-4.1-mini). Supports local and cloud LLMs (Ollama, Google, Anthropic, ...). Searches 10+ sources - arXiv, PubMed, web, and your private documents. Everything Local & Encrypted.
Pre-build reality check. Scans GitHub, HN, npm, PyPI, Product Hunt — returns 0-100 signal.
SEO analysis for sites you own: Google Search Console, GA4, PageSpeed, and full site audits.