Space is answering right now. Last checked 2 min ago. Last commit 20 Oct 2026.
One shared memory for all your AI agents: documents, tasks, databases and memories in one workspace
What the code does
We read the source, 1 d ago · rules 995398eba69f
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
<select aria-label={`Color for ${option.label || `option ${index + 1}`}`} value={option.color}
subprocess.run( # noqa: S603 - fixed local disposable Docker command, no shell
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
This code can reach further than it looks
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
Connect this server
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 2 min ago.
claude mcp add space --transport http https://api.getspace.sh/mcp/https://api.getspace.sh/mcp/[mcp_servers.space]
url = "https://api.getspace.sh/mcp/"{
"mcpServers": {
"space": {
"url": "https://api.getspace.sh/mcp/"
}
}
}{
"servers": {
"space": {
"type": "http",
"url": "https://api.getspace.sh/mcp/"
}
}
}This endpoint answered with an authorization challenge. The server is running, and it signs you in through your browser: there is no API key to paste.
Endpoints
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://api.getspace.sh/mcp/ | streamable-http | sign-in | 318 ms | 2 min ago |
Alternatives to Space
same job, measured the same wayShared, source-backed memory for AI agents on your own Postgres, with an optional document engine.
Shared memory for AI agents, as a graph in your own Postgres. Writes never call an LLM.
CRM and business database for AI agents: search and update records, documents and workspace schema.
Deploy apps, databases, and services in your dFlow workspace.
Memory database for AI agents: remember and recall over a running Fraise daemon, in FQL.
Memory for AI coding agents — markdown in your own git, not a vendor database. Apache-2.0.
Shared memory for AI agents: a hierarchical database where totals add up and writes are attributed.
Database for your AI agent. Turn its output into data, docs, skills, and apps you can actually use.
Space — questions
Answers built from our own checks of this server.