Knot MCP Server

by connectknot Your server? Claim it

answering

Knot is answering right now. Last checked 12 min ago. Last commit 30 Oct 2026.

Shared brain, one current version of memory for any MCP client: ChatGPT, Claude, Gemini, Cursor

Uptime history 6 days of history

6 days agonow

100.0%

Uptime 24h

91 of 91 checks

—

Tools

hidden behind auth

353 ms

Response time

average over 24h

Stars

last commit 30 Oct 2026

Nothing serious here today

Today is the operative word: we check Knot 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 12 min ago.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add knot --transport http https://api.connectknot.com/mcp

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

https://api.connectknot.com/mcp

~/.codex/config.toml

[mcp_servers.knot]
url = "https://api.connectknot.com/mcp"

.cursor/mcp.json

{
  "mcpServers": {
    "knot": {
      "url": "https://api.connectknot.com/mcp"
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "knot": {
      "type": "http",
      "url": "https://api.connectknot.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://api.connectknot.com/mcp	streamable-http	sign-in	295 ms	12 min ago

Alternatives to Knot

same job, measured the same way

Make0 Brain

by make0-official

One shared, versioned memory for Claude Code, Cursor, Codex and every MCP agent. Local and offline.

1 212 installs/wk local only

knowsme

by knowsme

One memory for you and your AI agents, shared by ChatGPT, Claude, Gemini, Grok, Codex and Cursor.

answering

Memory Bridge

by memorybridgeai

One memory for all your AI tools: Claude, ChatGPT, Cursor and any MCP client share the same notes.

answering

Deep Recall (getdeeprecall.com)

by getdeeprecall

One memory you own, shared by Claude, ChatGPT, Gemini, Muse and any remote MCP client.

answering

UltraMemory

by logiclabsai

One memory, every AI: Claude, ChatGPT, Perplexity, Gemini, Cursor, OpenClaw, Hermes, any MCP client.

answering

Memory

by cortex-mem

Shared, persistent memory for AI agents — works with Claude, Kiro, Cursor, or any MCP client.

113 installs/wk local only

Brain Memory

by brainmemory

Persistent memory for AI agents: one brain shared across Claude, Cursor, Codex and more.

answering

Heirmos

by heirmos

Persistent memory shared across Claude, ChatGPT, Grok and other MCP clients.

answering

Knot — questions

Answers built from our own checks of this server.

Why is there no tool list for Knot?

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 Knot 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 353 ms. The bar chart above shows every period we have measured.

How do I connect Knot?

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 Knot?

No API key is involved. Knot 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 Knot?

It answers our handshake in 353 ms on average, which is faster than 39% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.

Is Knot open source?

The code is open source: it is published under the MIT licence and 0 stars on GitHub. The licence covers the code in the repository, not the hosted service at api.connectknot.com, which runs on its operator's own terms.