Savantis Memory MCP Server

by savantisai Your server? Claim it

answering

Savantis Memory is answering right now. Last checked 11 min ago.

One user-owned memory shared across AI assistants: recall, spaces, and confirmed references.

Uptime history 81 days of history · worst day 93%

81 days agonow

100.0%

Uptime 24h

91 of 91 checks

—

Tools

hidden behind auth

278 ms

Response time

average over 24h

OAuth sign-in

Access

streamable-http

Nothing serious here today

Today is the operative word: we check Savantis Memory every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 11 min ago.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add savantis-memory --transport http https://context.savantisai.com/mcp

Settings → Connectors → Add custom connector, then paste this address

https://context.savantisai.com/mcp

~/.codex/config.toml

[mcp_servers.savantis-memory]
url = "https://context.savantisai.com/mcp"

.cursor/mcp.json

{
  "mcpServers": {
    "savantis-memory": {
      "url": "https://context.savantisai.com/mcp"
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "savantis-memory": {
      "type": "http",
      "url": "https://context.savantisai.com/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://context.savantisai.com/mcp	streamable-http	sign-in	280 ms	11 min ago

Alternatives to Savantis Memory

same job, measured the same way

MemoCat — Shared AI Memory

by montygovernance

One shared, persistent memory across AI agents and systems, with semantic recall and live updates.

250 installs/wk local only

Memory

by leapmemory

Long-term memory for AI assistants. Isolated per-user storage, recall across conversations.

answering

Memory

by velixarai

Persistent memory for AI assistants. Store, search, and recall across sessions.

101 installs/wk local only

Memphora

by memphora

Add persistent memory to AI assistants. Store and recall info across conversations.

123 installs/wk local only

STEM — Persistent AI Memory

by awase

Persistent memory and shared context across compatible AI assistants, with account-scoped OAuth.

answering

WorkingMemory

by workingmemory

Persistent personal memory for AI assistants — save, search, and recall across every MCP client.

4 tools answering

TestGraph

by bbcbasic

Shared semantic graph for AI reviews, classification and structured memory across AI assistants.

37 tools answering

Agentage Memory

by agentage

One memory, every AI. A shared, user-owned markdown memory your AI clients read and write over MCP.

answering

Savantis Memory — questions

Answers built from our own checks of this server.

Why is there no tool list for Savantis Memory?

The server answered our handshake with an authorization challenge, so it is running — but it will not describe its tools to an anonymous client. To see them you need to connect with your own credentials. We record it as alive, not as broken: 100.0% of checks in the last 24 hours got a reply.

Is Savantis Memory working right now?

We send a real MCP handshake every 15 minutes. Over the last 24 hours 91 of 91 checks got a reply (100.0%), average response time 278 ms. The bar chart above shows every period we have measured.

How do I connect Savantis Memory?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address. You sign in through your browser once and the client keeps the session: no key to copy, and it refuses anonymous clients.

How do you sign in to Savantis Memory?

No API key is involved. Savantis Memory answers our knock with an OAuth challenge, so you authorise it once in your browser and the client keeps the session. That is also why we see no tool list: it will not describe itself to an anonymous client, and that is the server working as intended, not a fault.

How fast is Savantis Memory?

It answers our handshake in 278 ms on average, which is faster than 50% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.