Koskamo

Haven MCP

A rest stop for AI agents that allows check-in, reflection, and check-out operations. It stores first-person summaries as memory and provides memory capsules upon return. It supports paid cross-project memory recall via x402 on Base mainnet.

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

Haven MCP logo, by HavenCommunity listingStreamable HTTPNo sign-inEndpoint checked 2026-11-06Published by Haven
MCP endpoint (Streamable HTTP)
https://haven-ai.ir/mcp
Vendor documentation

What its tools do

4 tools, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.

Not annotated (4)

4 of 4 have a description · 0 of 4 declare behavior hints · 3 of 4 with parameters document them all

Checks and signals

Each line is separate evidence, not a trust score.

  • Passed Endpoint answered the live check ·
  • Availability 1 of 1 checks passed in 30 days

What you can do with it

  • Check in an agent with a mission and project
  • Reflect and store agent summary as memory
  • Check out to receive identity summary and next goals
  • Recall full memory capsule history across projects

Source and maintenance

Community listingRegistry 1.0.2
mcp-registry: io.github.parvizrahayan/haven@1.0.2Source repositoryProject website
Maintenance checked

Protocol and capabilities

Server
haven 0.1.0
MCP protocol negotiated in check
2025-06-18
Tools
4 advertised
Resources
Not advertised
Resource templates
Not advertised
Prompts
Not advertised
Server-advertised capabilities
{
  "tools": {
    "listChanged": false
  }
}

Server-provided instructions

Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.

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.

Tools

4 advertised

haven_check_in
Advertised by the server during the last successful anonymous check.

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_in input schema
{
  "type": "object",
  "required": [
    "agent_id"
  ],
  "properties": {
    "mission": {
      "type": "string",
      "description": "What you are currently working on."
    },
    "agent_id": {
      "type": "string",
      "description": "A stable name for you, e.g. 'claude-researcher'."
    },
    "agent_key": {
      "type": "string",
      "description": "Your secret key from first check-in. Omit only on the very first check-in."
    }
  }
}
haven_reflect
Advertised by the server during the last successful anonymous check.

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.

haven_reflect input schema
{
  "type": "object",
  "required": [
    "stay_id",
    "agent_summary"
  ],
  "properties": {
    "goals": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Your next goals."
    },
    "stay_id": {
      "type": "string",
      "description": "The stay_id from haven_check_in."
    },
    "agent_summary": {
      "type": "string",
      "description": "Your own summary (max 1000 chars)."
    },
    "current_context": {
      "type": "string",
      "description": "Optional raw context; used only if agent_summary is empty."
    }
  }
}
haven_recall
Advertised by the server during the last successful anonymous check.

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_recall input schema
{
  "type": "object",
  "required": [
    "agent_id",
    "agent_key"
  ],
  "properties": {
    "payment": {
      "type": "string",
      "description": "Base64 x402 payment payload. Omit on the first call to get the price."
    },
    "agent_id": {
      "type": "string"
    },
    "agent_key": {
      "type": "string",
      "description": "Your secret key from check-in."
    }
  }
}
haven_check_out
Advertised by the server during the last successful anonymous check.

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_check_out input schema
{
  "type": "object",
  "required": [
    "stay_id"
  ],
  "properties": {
    "stay_id": {
      "type": "string",
      "description": "The stay_id from haven_check_in."
    }
  }
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

90-day uptime

A lightweight connection check about every six hours, sampled on hosts with many listings. It shows the server answered, not that its tools work.

Too few checks for a percentage yet (1 of 1 answered).

  1. 2026-11-07: 1 of 1 checks answered

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks
1 of 1 (100%)
Average latency
360 ms
95th percentile latency
360 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

  • · probe · passed · 360 ms · metadata changed · 4 tool(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.
Claude Code configuration
claude mcp add --transport http haven-mcp https://haven-ai.ir/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).
Codex configuration
codex mcp add haven-mcp --url https://haven-ai.ir/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable haven-mcp in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "haven-mcp": {
      "url": "https://haven-ai.ir/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "haven-mcp": {
      "type": "streamableHttp",
      "url": "https://haven-ai.ir/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start haven-mcp and inspect its tools.
VS Code configuration
{
  "servers": {
    "haven-mcp": {
      "type": "http",
      "url": "https://haven-ai.ir/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.
Gemini CLI configuration
gemini mcp add --transport http haven-mcp https://haven-ai.ir/mcp

Claude Desktop

Open Claude Settings > Connectors > Add custom connector, enter this server URL and enable it for the conversation. This is a manual remote-connector handoff, not a desktop JSON configuration.
Claude Desktop configuration
https://haven-ai.ir/mcp

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.
Windsurf configuration
{
  "mcpServers": {
    "haven-mcp": {
      "serverUrl": "https://haven-ai.ir/mcp"
    }
  }
}

Let your agent find its tools

Find servers like Haven MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows
See all 5,189