"Cursor Not Losing Memory or State" matching MCP servers:

Provides persistent memory for AgentChat agents with swim-lane summarization and self-evolving persona, enabling context management and persona mining across conversations.

A small MCP server that gives agents rich context about a YouTube video — its transcript, jump-to-the-moment deep links, metadata, and most-replayed moments — so they can answer questions, summarize, pull quotes, or surface highlights.

tooltrim reduces the tokens agents spend re-reading bloated tool results. Run it as an MCP server exposing compress and expand_tool_output, or as a gateway in front of any upstream MCP server: it re-exposes the upstream tools unchanged and shrinks each result (HTML/JSON/logs/tables) before it reaches the model, keeping the relevant content only.

Two self-hosted MCP servers: manage a local model machine (Ollama pull/switch, LoRA training) and bridge to local Ollama/vLLM for pure language processing tasks (writing, summarizing, classifying, extraction) without giving the calling agent tools or file access.

Provides MCP-compatible AI clients with offline text analysis and rewriting tools, including statistics, extractive summaries, keywords, readability scores, case conversion, entity extraction, and diffing, all running locally without API keys or network calls.

Enables AI agents and MCP clients to browse Roomtone meeting notes, add YouTube or pasted-text sources, generate summaries, ask questions answered from transcripts, and retrieve raw transcript text. Recording itself stays in the Roomtone app, so the server only reads and adds to existing meetings.

MCP server for extracting links from text dumps, checking duplicates, extracting YouTube transcripts (with fallbacks including speech-to-text), and preparing workspace-ready page payloads for your note-taking or saving tools. It does not write to your workspace; it hands off prepared content to your existing tools.

MCP server for HumanPen that lets AI agents work on real documents (.docx, .pptx, .pdf) — humanizing content to lower AI-detection scores, converting citations, condensing, and translating while preserving formatting, tables, images, and citations.

Fetches, parses, and summarizes ETSI telecommunications and media standards documents, enabling Claude to autonomously look up and ingest standards mid-conversation for answering questions, generating conformant code, or writing XML.

Enables an assistant to transcribe video or podcast recordings, then read, search, summarize, and manage the resulting transcripts through MCP tools.

Enables AI agents to search, watch, summarize, clip, and extract transcripts from YouTube videos, all without needing an API key or leaving the chat.

Give your AI agent PDF summarization, code review, translation, web extraction, document comparison, and persistent memory — all paid autonomously via Bitcoin Lightning.

This MCP server enables AI assistants to perform calculations, fetch live weather, manage in-memory notes, access system info and note resources, and use reusable code review and summarization prompts.

Enables local LLM chat sessions to continue indefinitely by automatically compacting context and storing permanent memory on disk, with recall across all past sessions.

Enables fetching and analyzing YouTube video comments and replies through the YouTube Data API. Supports sorting by relevance or time and returns structured JSON data for comment analysis, summarization, and translation tasks.

Analyzes YouTube videos using Google's Gemini API, allowing users to get summaries or ask questions about video content via direct URL input.

Local MCP server that enables delegating low-risk tasks like summarization or code patches to a low-cost model, with the main agent reviewing results.

A privacy-first, zero-cost AI assistant that lets you chat with your documents locally via CLI or web app, supporting search, summarization, and Q&A using your own model.

Converts subtitles or text into a single 1080×1620 infographic card (HTML+PNG) using LLM to generate content and Puppeteer for rendering.

Extracts transcripts or spoken captions from multi-platform video links (Bilibili, YouTube, Douyin) and returns concise Markdown summaries or full transcripts, saving tokens by keeping full text out of the conversation.