"Finding the best memory MCPs for in-session management" matching MCP servers:

Provides persistent local memory for AI coding sessions, enabling agents to save and retrieve project context across different tools and sessions.

A collection of small MCP servers for macOS automation that expose Apple Mail, MoneyMoney, and Spotlight functionality as tools via AppleScript and command-line, enabling AI applications to search mail, manage contacts and transactions, and perform system-wide file searches through natural language.

Enables persistent session memory for LLMs by trust-scoring and injecting verified context between conversations.

MCP server that lets an AI analyst place real bets on Binance prediction markets, using Kelly criterion sizing, and tracks its performance through a transparent record of betting slips and outcomes.

Give any LLM agent a real Android or iPhone. 62 MCP tools: tap, swipe, type, screenshot, screen-tree reading, app launch, camera, TTS, crash reports, batched execution. Android via ADB, iPhone via WebDriverAgent, on-device inference, Docker+KVM emulators. Works with Claude Code, Cursor, LangChain, LlamaIndex, and any MCP client. MIT.

A thin MCP server that securely enables AI agents to interact with Home Assistant, Mealie, and Nirvana via tools for automation, recipe management, and task tracking, while keeping credentials hidden.

Provides cross-session memory for AI agents by maintaining a rolling 24-hour event stream and searchable daily archives to prevent context loss. It enables agents to record, query, and retrieve historical events and decisions through a structured markdown-based workspace.

Enables AI assistants to interact with humans through GUI dialogs for text input, choices, confirmations, and information display.

Enables AI assistants like Claude to interact with humans through intuitive GUI dialogs, supporting text input, choices, confirmations, and information displays.

Connects MCP clients to a local social engine that reads bounded posts, comments, replies, and feeds into local inboxes, turns source material into drafts and briefs, and publishes exact frozen jobs with recorded provider IDs and receipts across Instagram, Threads, and Substack.

Enables agent-driven CAD automation by inspecting, editing, and validating DWG drawings through a handle-first workflow, with support for visual grounding, CADPlan execution, and local SQLite workspace management.

Enables authorized web/API security analysis as a stateful, multi-stage workflow with persistent session state, human-controlled validation, candidate versus confirmed finding tracking, and stop conditions.

Turns a codebase into a persistent knowledge graph so AI coding agents can answer structural questions about functions, call chains, routes, and cross-service links through graph queries instead of reading files one by one.

A local, read-only MCP server (plus CLI) over your own stock/ETF transaction log. A deterministic core computes drawdown-first risk with bootstrap confidence intervals and validates targets with walk-forward verdicts. The assistant narrates, but the number fence makes it structurally impossible for the model to produce a figure.

Enables AI coding agents in different harnesses, projects, or machines to share encrypted peer-to-peer rooms and exchange messages directly, without any central server or account.

Enables agents to sign into websites through a real browser without exposing passwords, keeping cookies in a local Chrome profile and providing tools for browsing and managing authenticated sessions.

Session Watcher treats your prompt cache as inventory — it uses EOQ theory to tell you whether the current context is still worth carrying, and when to restart. Works with any session-based coding agent.

Universal session & handoff layer for AI coding agents: shared task, decision, blocker and test state, checkpoints, and deterministic handoff between Claude Code, Codex, OpenCode, Cursor, Cline, pi and omp. Local SQLite, git-aware, 25 tools + 7 resources over stdio or streamable-http.

Share coding-agent sessions with your team: /share in Claude Code, Codex, OpenCode, Gemini CLI, Copilot CLI, Cursor or ZCode, and a teammate /pickup's it in theirs with the goal, decisions, next steps and recent conversation. Tools to share, search, load, comment on and update sessions, plus team activity.

A Model Context Protocol (MCP) server for producing better Terraform through CLI analysis (tflint, checkov, trivy, kics, infracost), best-practice guidance from terraform-best-practices.com, cloud provider recommendations (Azure, AWS, GCP), and Terraform Registry resource and module guidance.

Enables AI agents to manage live Firefox tabs and native tab groups via MCP tools over stdio, with exact-match verification and safety constraints. It does not read page content or send browser data remotely.

Provides comprehensive session management for Claude Code with automatic initialization/cleanup, quality checkpoints, and local conversation memory with semantic search for capturing learnings across coding sessions.

Provides local, agentic semantic recall over Claude Code session history, enabling the agent to search past discussions semantically, expand turns, and grep transcripts.

Local macOS MCP servers for Mail, Calendar, Reminders, Notes, Contacts, Messages, Shortcuts, Files, Maps, and system tools. The unified Apple Tools server and individual app servers run over stdio with native macOS permissions; this is an MIT-licensed community project, unaffiliated with Apple.

Enables browsing, searching, and importing sessions from multiple coding agents into the current one, or reopening them in their native agent, all locally and read-only.

Enables searching and browsing past Claude Code sessions via hybrid FTS5 and vector search, with tools for session search, drill-down, coverage, and health reporting.

MCP server for programmatic lifecycle management of Claude Code sessions, supporting list, create, read, send, fork, wait, and interrupt operations.

Provides manufacturing demo data across procurement, production, quality, warehouse, and finance categories via MCP Streamable HTTP, enabling LLMs to retrieve mock datasets.

Call OpenAI Codex from Claude Code for independent second opinions, structured code review, and delegated coding tasks through a FastMCP plugin that drives the codex CLI safely.

Enables AI agents and MCP clients to drive real Chrome, Edge, Brave, and Firefox browsers through native automation protocols. It exposes tools for navigation, page snapshots, form filling, clicks, screenshots, console/network inspection, and tab management.