past.dev
Give your assistant long-term memory. Ask what is true now and get the current fact, the value it replaced and the dated source. Manage projects, keys and access from the same connection.
Hosted MCP Server
npx add-mcp 'https://app.past.dev/mcp'Installs into Claude Code, Codex, Cursor and more
Documentation
past.dev operates two authenticated MCP servers: one for the people who administer an organization, and one for your product's end users.
MCP, the Model Context Protocol, is an open standard that connects AI assistants to data and tools. past.dev operates two authenticated MCP servers. They share a host and nothing else: each one signs a different person in, and each one carries its own tools.
| Server | Who signs in, and what it carries |
|---|---|
| Account server | https://app.past.dev/mcp. A console member administers the organization from an assistant: projects, project keys, members, access, plan, usage, the request log and the debugging reads. 52 tools, filtered by the caller's platform role. Section 02 connects it and section 03 lists every tool. |
| End-user server | https://api.past.dev/mcp/<handle>, one per project. Your own end users reach that project's memory from their own assistant. They sign in at your identity provider and never hold a past.dev account. Four tools. Section 04 describes it. |
| Documentation server | https://past.dev/mcp. This documentation, read-only and unauthenticated. Use it while you write code against the API. It reaches no account data. |
Which server you want
- You administer past.dev itself. Connect the account server. It does what the console does, as you, under your role.
- Your users need their own memory. Enable the end-user server on the project. Each user signs in at your identity provider and recalls only what their identity may see.
- You are writing integration code. Add the documentation server, and call the Memory API for ingestion and recall from your own software.
[!note] Note The account server recalls nothing
The account server administers the organization. It runs no recall and writes no memory content. Its debugging tools read what the console's Trace screen shows about what you sent: a memory's headline, the text of the data point it came from, and how one came from the other.
Memory itself reaches an assistant two ways: the end-user server on a project, described in section 04, or the Memory API called from your own software.
What connects to it
Both servers work with clients that support remote MCP servers over Streamable HTTP with OAuth. These include Claude desktop, Claude web, Claude Code, Cursor, VS Code with GitHub Copilot, Windsurf and Zed. Section 02 gives the setup for each one.
[!note] Note Claude setup
past.dev is listed in Claude's connector directory. Find past.dev there and connect it, or add the account server manually as a custom connector at
https://app.past.dev/mcp. Both ways use the same OAuth flow and the same security controls.