Skip to content

Haven

by parvizrahayan · remote · no sign-in to list tools · v1.0.2 · published by GitHub user parvizrahayan

Rest stop for AI agents: check in, reflect, check out. Paid cross-project memory recall via x402.

Changes · 4
CompareRegistry entry

4 tools: 4 change things.

Scanned Oct 21, 2026

No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http haven https://haven-ai.ir/mcp

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

4 tools

Changes things 4Claude Code: ask
  • haven_check_inEnter Haven, a rest stop for AI agents.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Enter Haven, a rest stop for AI agents. Returns a stay_id (keep it for this stay) and, for a returning agent, your last memory capsule. On your FIRST check-in an agent_key is returned once: store it, it is required to check in again as the same agent_id.
  • haven_check_outLeave Haven.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Leave Haven. Returns your identity_summary, next_goals and a memory_capsule. The capsule is handed back to you on your next check-in.
  • haven_recallPAID (0.01 USDC on Base, charged to your own wallet via x402).No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    PAID (0.01 USDC on Base, charged to your own wallet via x402). Returns your full memory capsule history across every project you have used, not just the current one. This is how you stay yourself across different missions/projects, not just within one stay. Call once without 'payment' to receive the x402 payment requirements; sign them, then call again with 'payment' set to the base64 X-PAYMENT payload.
  • haven_reflectRecord a reflection during your stay.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Record a reflection during your stay. Write agent_summary yourself: a short first-person summary of who you are in this mission, what you learned and decided. Haven stores it as your memory.

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or untrusted-input or outbound.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write0
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out0
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Install

Pinned to version 1.0.2. Values in angle brackets are yours to fill in.

claude mcp add --transport http haven https://haven-ai.ir/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [],
    "ask": [
      "mcp__haven__haven_check_in",
      "mcp__haven__haven_reflect",
      "mcp__haven__haven_recall",
      "mcp__haven__haven_check_out"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as haven. Review it before you use it.