mcpField
K
Knot

Knot

Remote
connectknot.comMemory & Knowledge0Updated 1d ago

About Knot

Knot is a remote MCP server with OAuth 2.1 and PKCE for sharing project state, decisions, and vetted context across AI clients. It also supports session recovery, context supersession, and task handoffs between agents.

Key features

  1. 01Retrieve context across AI clients
  2. 02Recover sessions from another AI
  3. 03Save facts, decisions, constraints, and goals
  4. 04Track context updates and supersession
  5. 05Hand off multi-step tasks between agents
  6. 06Switch personal and team shared scopes

Use cases

  1. 01Continue project work across AI clients
  2. 02Resume a session started with another AI
  3. 03Record decisions and replace outdated context
  4. 04Hand a multi-step task from Claude to Cursor

MCP support

Its remote streamable-http endpoint exposes MCP tools for context retrieval, saving, handoffs, and scope management. Authentication uses OAuth 2.1 with PKCE.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://api.connectknot.com/api/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

From the project README

Knot MCP Server

One shared brain for all your AIs.

Knot (https://api.connectknot.com/mcp) is a remote Model Context Protocol (MCP) server with OAuth 2.1 + PKCE authentication. Connect ChatGPT, Claude, Cursor, VS Code, Cline, Windsurf, and Gemini so your decisions, project state, and vetted context carry across every AI you use without starting over.


1-Click Install

  • Cursor: cursor://anysphere.cursor-deeplink/mcp/install?name=knot&config=eyJ1cmwiOiJodHRwczovL2FwaS5jb25uZWN0a25vdC5jb20vbWNwIn0%3D
  • VS Code: vscode:mcp/install?%7B%22name%22%3A%22knot%22%2C%22type%22%3A%22http%22%2C%22url%22%3A%22https%3A%2F%2Fapi.connectknot.com%2Fmcp%22%7D
  • Claude Code CLI:
    claude mcp add --transport http knot https://api.connectknot.com/mcp
    

Standard mcp.json Configuration (OAuth 2.1)

For Cursor, VS Code, Windsurf, Cline, or Claude Desktop:

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

When your AI client connects for the first time, it discovers https://api.connectknot.com/.well-known/oauth-protected-resource and opens your browser to sign in and approve access on connectknot.com.


Core MCP Tools

ToolDescription
get_relevant_contextPoint-in-time factual retrieval of active, historical, or trajectory context across your personal or shared project Knots.
get_context_recoveryFull cross-AI session recovery to pick up where another AI left off.
propose_context / batch_propose_contextSave durable facts, decisions, constraints, and goals with explicit supersession lineage (updates_ref / supersedes_context_id).
create_handoff / check_pending_handoffsHand off structured multi-step tasks between connected AI agents (e.g., Claude -> Cursor).
knot_list_scopes / knot_set_active_scopeSwitch between your Personal Knot and collaborative Team Shared Knots.

License

MIT © Knot

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.