"CNN" matching MCP servers:

An MCP server for reading, rendering, and searching PDF files, specifically optimized for LLMs to extract text, tables, and technical diagrams. It enables metadata retrieval, multi-format text extraction, and page-to-image rendering using PyMuPDF.

Maintains a self-updating JSON index of repository files, functions, and descriptions so agents can query relevant files instead of grepping the tree.

A local stdio MCP server that lets MCP-capable AI agents browse, search, upload, download, preview and maintain files on FTP and SFTP servers within a controlled root boundary. It keeps credentials out of the model context via OS credential storage, supports read-only modes and write gating, and stages large downloads locally with size and SHA-256 verification.

TheWeave is a markdown-native memory architecture for Claude and any MCP-aware agent. Your agent's memory lives as plain .md files you own: a 5-verb MCP core over the vault, query-driven PageRank retrieval, bi-temporal facts (valid_from / valid_until), and a persona-as-vault model. No database and no embeddings server. The files are the memory, inspectable in your editor and versionable in git.