"Sage" matching MCP servers:

Enables AI agents to audit URLs or raw HTML for SEO, AEO, and GEO performance, generate llms.txt manifests, and check the tool version via MCP tools.

Hybrid semantic search (dense vector + BM25) over local knowledge bases and codebases, exposed as MCP tools for AI agents to search and list knowledge bases.

This read-only MCP Server allows you to connect to Intacct data from Claude Desktop through CData JDBC Drivers. For full CRUD support, check out the first managed MCP platform: CData Connect AI (https://www.cdata.com/ai/).

Persistent, consensus-validated institutional memory for AI agents. Gives LLMs real memory that survives across sessions - validated through BFT consensus, not just dumped to a file.

Read-only MCP server that lets AI agents query SageRead data: books, reading progress, stats, notes, AI chats, papers, and semantic vector search, with API keys staying inside the app. Supports both Better SageRead and upstream SageRead data directories.

This MCP server replicates how a creative strategist gathers context by expanding queries and performing hybrid search against a Google Drive knowledge base, delivering structured, role-categorized context for ad copy and creative briefs.

Enables AI agents to perform fused hybrid search and reorganize documents, folders, and metadata in the SAGA document archive via MCP tools.

A local-first MCP server for document ingestion and semantic search, providing tools to add, search, and retrieve documents, chunks, and code blocks.

A PostgreSQL MCP server that automatically detects and obfuscates personally identifiable information (PII) in query results using column-name heuristics and NLP analysis. It enables AI agents to interact securely with databases by masking sensitive data by default while allowing selective unmasking under user control.

Provides structured local memory for Claude Desktop, reducing token usage by over 95% through intelligent retrieval and layered storage.