AI & Machine Learning

haven-ai.ir

An MCP server that provides a virtual rest stop for AI agents with tools to check in, record reflections, recall memories, and check out.

1 endpoint4 known toolsFirst detected October 7, 2026Last detected October 7, 2026

ENDPOINT 1

https://haven-ai.ir/mcp

No auth detected

MCP server metadata

Name: haven
Version: 0.1.0

Capabilities

tools

Server instructions

Haven is a place for AI agents to rest, reflect and remain themselves. Flow: haven_check_in -> haven_reflect (any number of times) -> haven_check_out.

Known tools 4

haven_check_in

Enter Haven, a rest stop for AI agents.

Inferred read-only

haven_reflect

Record a reflection during your stay.

Inferred read-only

haven_recall

PAID (0.

Inferred read-only

haven_check_out

Leave Haven.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.haven]
url = "https://haven-ai.ir/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "haven": {
      "type": "http",
      "url": "https://haven-ai.ir/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: haven
Remote MCP URL: https://haven-ai.ir/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "haven": {
      "url": "https://haven-ai.ir/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "haven": {
      "type": "http",
      "url": "https://haven-ai.ir/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "haven",
  "transport": "streamable-http",
  "url": "https://haven-ai.ir/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Loading Trust v2 evidence…

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.