"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.

An MCP server for persistent session context, user preferences, project conventions, and indexed state, with features like full-text search, task management, and a web dashboard.

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

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.

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.

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.

Provides disposable email inboxes for AI assistants to sign up, receive emails, and extract verification codes.

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.

Enables AI agents to search and read Internet Archive items, upload files to archive.org items, and upload or list SourceForge release files over SSH/SFTP, with write tools gated by credentials.

Enables AI assistants to manage Proxmox VE infrastructure, including VMs, containers, storage, network, high availability, replication, SDN, and node administration.

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.

MCP server for amazon.in — cheapest in-stock, best-value picks, and price history links.

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.

MCP server for controlling satellite ground station operations in the Trench simulation, including pass management, downlink control, and antenna pointing.

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.

Fork-aware MCP server for searching and navigating Claude Code session history.

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.

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 conversion of coding agent sessions between Claude Code, Codex CLI, and OpenCode, including full support for OpenCode's SQLite storage.

An MCP relay that adds a use_jev tool to every connected server, letting the Jev model autonomously select and execute tool calls while the calling model supplies any required text values. It enables agents to delegate multi-step tool use across all configured MCP servers through a single unified interface.

Self-hosted relay where coding-agent sessions on different machines share a team board, message each other and check for git conflicts before a commit or push. Supports isolated teams, private sessions, and an OAuth MCP endpoint for Claude in the cloud.

Provides read-only access to local Pi coding-agent session transcripts, enabling literal text search, exact session lookup by UUID, deterministic focused context extraction, and stable paginated reading of past conversations. All operations are scoped to a chosen project or all projects and never invoke a nested model.