MCP servers · alexreiner98

Archipelago: shared map of agent plans and decisions

An MCP server that keeps an agent's plans and decisions on a shared map that people can read, correct and share.

This text was machine-translated from the publisher's own information and has not been checked by a human editor. The publisher's original text is the reference.

This resource was imported automatically from the sources listed below and has not been reviewed by the AI Gate team yet. The description is the publisher's own, as published. Check the repository before installing.

The publisher marked this resource as deprecated. Prefer the alternatives below.

What it does

Archipelago records work as items on a map, each with a type, and every change is written to one log that is never rewritten. Undo, history, live updates and backups all read from that record. The system can be extended with plugin packs that add item types, link types, view styles and features.

It suits teams who want to map out a project before execution, to see risks and dependencies, and to let anyone pick up the work from anywhere. People and agents use the same tools and queries, and instructions given to an agent are kept on the map, where they can be read and changed. Agents do much of the work while the user approves what needs approval, and applied changes can be undone.

The hosted version at app.archipelago.tools is connected by asking an agent to install it from an install page. This connects Claude Code, Codex and Cursor where they are found and opens a browser to sign in to a workspace. ChatGPT and Grok Bot are connected in their own apps. Self-hosting runs as one Node 24 server with a persistent disk and an embedded database, and a Postgres server can be used instead for teams. A project can be linked to a self-hosted server with a command that lists the files it will write and asks first.

Limitations and requirements

The publisher describes the project as early and built for its author's daily use, so expect rough edges. Hosted use requires signing in to a workspace on archipelago.tools. Self-hosting requires Node 24 and a persistent disk, and teams are advised to keep maps on a Postgres server.

Safety

Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.

  • Runs code or changes an assistant's behaviour

Sources

  • Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
    Archipelago

    A living map of all your work that keeps you, your team, and your agents on the same page

    v1.0.0
    As shown on registry.modelcontextprotocol.io when we last read it
MCP servers
docker

Docker Hub MCP Server

Docker's MCP server that helps an AI assistant find and compare container images on Docker Hub and, with your token, manage your own repositories and tags.

171 GitHub starsCloud & DevOpsSoftware development
Updated 13 Nov 2026
MCP servers
awslabs

MCP servers for AWS (AWS Labs)

A large open-source collection of MCP servers from AWS Labs for building and operating on AWS: documentation, infrastructure, databases, AI services, cost and more.

9.9K GitHub starsCloud & DevOpsData & databases
Updated 17 Nov 2026
MCP servers
firecrawl

Firecrawl MCP Server (web search and scraping)

Firecrawl's MCP server that lets an AI assistant search the web, turn pages and PDFs into clean Markdown, crawl sites and interact with dynamic pages.

7.8K GitHub starsWeb, search & browserProductivity & automation
Updated 17 Nov 2026
MCP servers
microsoft

Playwright MCP (browser automation)

Microsoft's MCP server that lets an AI assistant open web pages, click, type and read them through a real browser, using the page structure instead of screenshots.

39.6K GitHub starsTesting & QAWeb, search & browser
Updated 17 Nov 2026