Connect

8 clients · secrets stay placeholders

JSON (mcpServers)Claude CodeCodexOpenCodeCursorVS CodeGemini CLIGoose

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

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

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

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "haven": {
      "type": "remote",
      "url": "https://haven-ai.ir/mcp",
      "enabled": true
    }
  }
}

{
  "mcpServers": {
    "haven": {
      "type": "http",
      "url": "https://haven-ai.ir/mcp"
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=haven&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vaGF2ZW4tYWkuaXIvbWNwIn0%3D"
}

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

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

extensions:
  "haven":
    enabled: true
    name: "haven"
    type: streamable_http
    uri: "https://haven-ai.ir/mcp"
    timeout: 300

Quality 79 / 100good

protocol75 · weight 25

warn
protocol.modernnewest supported version is 2025-06-18; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
n/a
protocol.statelessonly applies to 2026-07-28 servers
pass
protocol.transportstreamable HTTP
n/a
protocol.list_ttlonly applies to 2026-07-28 servers

authorizationn/a · weight 15

n/a
auth.prm, auth.as_metadata, auth.cimdno remote uses OAuth
n/a
auth.secret_in_urlno templated URL

tool hygiene71 · weight 30

pass
tools.descriptionsevery tool has a description
pass
tools.description_lengthdescriptions are concise
pass
tools.schemasevery tool has an object input schema
fail
tools.annotationsno tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
fail
tools.directory_hintsno tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: haven_reflect (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); haven_recall (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); haven_check_in (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …
pass
tools.token_costabout 563 tokens to load every tool
pass
tools.api_dumptools are not a one-to-one API dump

stability100 · weight 15

pass
stability.changesno tool changes in 30 days
pass
stability.rug_pullno tool changed its meaning under the same name

dependenciesn/a · weight 15

n/a
deps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI package

4 tools, about 563 tokens to load them all · tool set 777ef118b340 · checked 2026-10-20 13:49 UTC

Tool changes

No tool definition changes recorded. A server's first observation is its baseline; later probes record what changes.

Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.

Trust 97 / 100

provenance90

liveness99

freshness100

hygiene100

+repository +namespace-matches-repo +website +reachable +uptime-96% +updated-10d-ago

Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.

Endpoints

remote	auth	reachable	uptime 30d	p50	protocol	last ok
`https://haven-ai.ir/mcp` streamable-http	none	yes	96%	532 ms	2025-06-18	2026-10-20

Tools (4)

`haven_check_in`	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_out`	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_recall`	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_reflect`	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.

Schemas: list_tools.

More from io.github.parvizrahayan

Official server.json

{
  "name": "io.github.parvizrahayan/haven",
  "title": "Haven",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "remotes": [
    {
      "url": "https://haven-ai.ir/mcp",
      "type": "streamable-http"
    }
  ],
  "version": "1.0.2",
  "repository": {
    "url": "https://github.com/parvizrahayan/haven-worker",
    "source": "github"
  },
  "websiteUrl": "https://haven-ai.ir",
  "description": "Rest stop for AI agents: check in, reflect, check out. Paid cross-project memory recall via x402."
}