An MCP memory server for coding agents

Sirro exposes tools for saving, listing, retrieving, and composing reusable assets through a remote MCP connection.

Why coding agents need memory

Valuable work often dies in chat logs. Coding agents forget decisions, code, and reusable components between sessions and projects, so developers rebuild work that already exists.

How Sirro solves it

Save assets deliberately. Choose the code, component, animation, prompt, pattern, or link worth keeping and give it a clear name.
Retrieve across projects and agents. Ask a connected coding agent for the saved asset by name from another repository or session.
MCP native. Sirro exposes save, retrieve, list, compose, and update tools through its remote MCP server.

Remote MCP config

Add the remote Sirro MCP server. Your coding client opens Sirro so you can sign in and allow access to a library.

{
  "mcpServers": {
    "sirro": {
      "url": "https://www.sirro.dev/mcp"
    }
  }
}

Sirro closed beta

Sirro is currently in closed beta. Open the beta access page.

Frequently asked questions

What does the Sirro MCP memory server store?

Sirro stores deliberately saved code, components, animations, prompts, patterns, and links in a library outside the current repository.

Which MCP tools does Sirro provide?

Sirro provides tools to save, retrieve, list, compose, update, and open library assets. Kits and recipes can group named assets for reuse.

How does authentication work for the remote MCP server?

The coding client opens Sirro in the browser. The user signs in, approves the connection, and selects which library the connection may access.

Is the Sirro MCP server tied to one repository?

No. The library lives outside repositories. A permitted connection can use the same saved assets while the agent works in different projects.

Sirro home, Shared memory for Cursor, Memory for Claude Code across projects, Persistent memory for Codex, External memory for AI coding agents, Shared context for coding agents.