"How to improve memory or retention like GPT models" matching MCP servers:

A minimal MCP server with get_weather and create_ticket tools, used for testing MCP servers across protocol, unit, eval, transport, and auth layers.

MCP server that provides OpenRouter model pricing data, enabling price lookups, trending/cheapest lists, and model searches without an API key.

Enables Claude to write in your personal style by learning from your local documents. It provides statistical style context for natural language rewriting, all without any data leaving your machine.

Exposes baby-gpt's tools (shell, filesystem, search, memory, GitHub integration, etc.) to Claude Desktop or Cursor, enabling natural language interaction with these capabilities.

An MCP server that enables Claude Code and Claude Desktop to generate and edit images using OpenAI's gpt-image-2 model, with results saved to disk.

Enables Codex to send text tasks to ChatGPT web, await responses, continue conversations, choose reasoning effort, and manage projects through MCP tools on macOS.

An MCP server for image generation, editing, and analysis using OpenAI's gpt-image-1 model, with specialized templates for YouTube thumbnails, blog headers, social media, and more.

Wraps the gpt-researcher tool as an MCP server, enabling automated web research, information summarization, and structured report generation via natural language queries.

Enables AI-powered web research using OpenAI's GPT-5.1 with built-in web search capabilities, returning comprehensive results with citations and source references.

MCP sidecar for Hermes Agent exposing operator tools (cron, skills, config, workspace) with tiered read-only/operator/owner modes and dry-run by default for safe local development.

Provides Claude Co-work with MCP tools to search and record organizational memory, including search, read, query, ingest, remember, sync, and status operations.

MCP server that adds a generate_image tool to Claude Code and other MCP hosts, using OpenAI's gpt-image-2 to create and save PNG images locally.

Generates and edits images using OpenAI image models via MCP tools.

Enables MCP-compatible clients to score the retention quality of the first three seconds of shortform video hooks using deterministic, zero-dependency Python tooling.

Enables GPT to interact with Todoist tasks and projects through direct API calls or a local SQLite mirror. Supports reading task data via SQL queries, creating/updating/deleting tasks and projects, and synchronizing data between Todoist and the local mirror.

Enables MCP clients to score the retention quality of the first three seconds of shortform video hooks using audio/video telemetry and transcript input, returning deterministic JSON results for viral hook optimization.

Standalone MCP server and CLI for generating images via ChatGPT backend, with reliable exact file paths and multi-account login support.

Enables Claude Code to delegate web research and image generation to ChatGPT via Playwright browser automation, allowing token-efficient search and visual design iteration without manual screenshots.

A different approach from typical persistent-memory MCPs. Instead of a local SQLite + embeddings store, the memory lives as plain files in a .ai-memory/ directory you commit to your repo (facts.jsonl, decisions/\*.md, gotchas.md). Git is the sync layer — what one Claude/Cursor/Cline learns about a repo, the next session (or a teammate's agent) picks up automatically. 5 MCP tools: get_rep

Enables Claude Desktop and compatible agents to search, read, add, update, and delete a locally stored, user-curated memory using hybrid retrieval with reranking and Qdrant. All processing runs locally without cloud services or API keys.