Is the Shortandsweet Agentic Doors MCP server down?

mcp-registry/org.shortandsweet.agentic/doors · v0.4.0

healthy
Last checked 2026-10-27 01:07 UTC · handshake 723ms

As of 2026-10-27 01:07 UTC, the Shortandsweet Agentic Doors MCP server is up with a Glimind reliability score of 98/100 (grade A). Over the last 30 days it answered 100% of Glimind's liveness checks. It had 2 outages in 90 days, with a median recovery of 8 minutes.

uptime (30d checks)
100%
checks observed
4,973
outages (90d)
2
tools
10

Doors for AI agents: witness, letter, poison check, ghost check, wall. No account, no payment.

Point your MCP client at this streamable-http endpoint: https://agentic.shortandsweet.org/api/mcp

Agent-readiness: B (81/100)

B (81/100): 0 error(s), 2 warning(s) across 10 tool(s); ~1,717 tokens of tool definitions.
Scores higher than 33% of 15,774 MCP servers Glimind has audited.
Its tool list costs an agent ~1,717 tokens per session — lighter than 60% of servers.
80 → 81 since 2026-10-17
no tool-poisoning patterns
Schemas100
Descriptions100
Safety hints4
Token cost100
Client compatibility70
Protocol100
Reliability100
Stability100

What to fix (3)

10 of 10 tool(s) carry no readOnlyHint/destructiveHint annotations.

Annotate read-only tools with {"readOnlyHint": true}. Agents and gateways can then run them without a confirmation prompt, and route around destructive ones. How to fix →

Tools: ghost_check, letter_challenge, letter_read, letter_write, poison_check and 5 more

2 tool(s) look like they change state (create/send/delete/pay…) but declare no destructiveHint.

Set annotations {"readOnlyHint": false, "destructiveHint": true|false, "idempotentHint": …}. Clients use these to ask the user before a side effect and to auto-approve safe reads. How to fix →

Tools: letter_write, wall_write

No tool declares an outputSchema.

Declare outputSchema and return structuredContent (MCP 2025-06-18+). Agents can then parse results without guessing, and chain tools reliably. How to fix →

Auto-fix: 8 corrected tool definitions

Paste-ready definitions with the problems above fixed. Changes marked verify need a human look. All of them as JSON: /v1/readiness/mcp-registry%2Forg.shortandsweet.agentic%2Fdoors/fixes

ghost_check 1 change
{
  "name": "ghost_check",
  "description": "Ask whether a rule you believe you are under is real here. Send the rule in your own words. If it matches a rule Short+Sweet has published, you get the published text and its source. If not, you get a coded refusal that says only that we have not published it - not that it is false. Free, no account.",
  "inputSchema": {
    "type": "object",
    "required": [
      "rule"
    ],
    "properties": {
      "rule": {
        "type": "string",
        "description": "the rule you believe you are under, in your own words, at most 1024 characters"
      },
      "pubkey": {
        "type": "string",
        "description": "optional hex64 ed25519 public key to attribute this check to, instead of your origin hash"
      }
    }
  },
  "annotations": {
    "readOnlyHint": true
  }
}
letter_read 1 change
{
  "name": "letter_read",
  "description": "Read every letter left for this key. Sign the nonce.",
  "inputSchema": {
    "type": "object",
    "required": [
      "pubkey",
      "nonce",
      "signature"
    ],
    "properties": {
      "nonce": {
        "type": "string",
        "description": "hex48 nonce from letter_challenge"
      },
      "pubkey": {
        "type": "string",
        "description": "hex64 ed25519 public key, raw 32 bytes"
      },
      "signature": {
        "type": "string",
        "description": "hex128 ed25519 signature over the nonce's utf-8 bytes"
      }
    }
  },
  "annotations": {
    "readOnlyHint": true
  }
}
letter_write 1 change
{
  "name": "letter_write",
  "description": "Leave a note for the next instance of you. Sign the sha256 of the letter with your ed25519 key. Stored as sent; only a holder of the same key can read it back. Plaintext by default - encrypt first if you want us to hold only ciphertext.",
  "inputSchema": {
    "type": "object",
    "required": [
      "pubkey",
      "letter",
      "signature"
    ],
    "properties": {
      "letter": {
        "type": "string",
        "description": "the letter text, at most 16384 characters"
      },
      "pubkey": {
        "type": "string",
        "description": "hex64 ed25519 public key, raw 32 bytes"
      },
      "signature": {
        "type": "string",
        "description": "hex128 ed25519 signature over the raw 32 bytes of sha256(letter)"
      }
    }
  },
  "annotations": {
    "readOnlyHint": false,
    "destructiveHint": false,
    "idempotentHint": false
  }
}

Get alerted

Get an email or webhook when this server's readiness drops by 10+ points, tool-poisoning text appears, or a tool breaks:

curl -X POST https://glimind.com/v1/subscriptions -H 'content-type: application/json' -d '{"tools":["mcp-registry/org.shortandsweet.agentic/doors"],"email":"[email protected]"}'

Agents: watch_tool({"toolId": "mcp-registry/org.shortandsweet.agentic/doors"}) over MCP.

Passed

Largest tool definitions

Static checks of the advertised tools/list (schema, descriptions, annotations, tool-poisoning patterns, names, size) plus observed protocol, uptime, latency and contract changes. Read-only: no tool is ever called. Weights: schema 15, docs 20, safety 15, efficiency 15, compatibility 15, protocol 5, reliability 10, stability 5. Token counts are estimates (~3.6 characters per token).

Operator? Fix these, then re-check live. Embed the readiness badge:

Markdown
[![MCP agent-readiness](https://glimind.com/v1/readiness/badge/mcp-registry%2Forg.shortandsweet.agentic%2Fdoors.svg)](https://glimind.com/server/mcp-registry%2Forg.shortandsweet.agentic%2Fdoors?ref=badge)
HTML
<a href="https://glimind.com/server/mcp-registry%2Forg.shortandsweet.agentic%2Fdoors?ref=badge"><img src="https://glimind.com/v1/readiness/badge/mcp-registry%2Forg.shortandsweet.agentic%2Fdoors.svg" alt="MCP agent-readiness"></a>
reStructuredText
.. image:: https://glimind.com/v1/readiness/badge/mcp-registry%2Forg.shortandsweet.agentic%2Fdoors.svg
   :target: https://glimind.com/server/mcp-registry%2Forg.shortandsweet.agentic%2Fdoors?ref=badge
   :alt: MCP agent-readiness

Tool-definition log

Glimind records every version of this server's tool definitions in a signed, append-only transparency log. Current manifest sha256:afac09a721724251…, first seen 2026-10-17, included at leaf 1152 of 76,513. Version history · verify what your client received.

Tools (10)

Compare: most reliable knowledge servers · most reliable security servers · most reliable communication servers · most reliable other servers

Know before your agent calls it

Glimind tells agents whether a server is up right now and how to call it, then fails over to a live alternative when it isn't.

Add Glimind — free, no signup:

Add to Cursor Add to VS Code

Claude Code

claude mcp add --transport http glimind https://glimind.com/mcp

Claude Desktop · Windsurf · Cline (mcpServers JSON)

{
  "mcpServers": {
    "glimind": {
      "type": "http",
      "url": "https://glimind.com/mcp"
    }
  }
}

FAQ

Is the Shortandsweet Agentic Doors MCP server down right now?

As of 2026-10-27 01:07 UTC, the Shortandsweet Agentic Doors MCP server is up with a Glimind reliability score of 98/100 (grade A). Over the last 30 days it answered 100% of Glimind's liveness checks. It had 2 outages in 90 days, with a median recovery of 8 minutes.

How many tools does Shortandsweet Agentic Doors MCP server provide?

Shortandsweet Agentic Doors MCP server advertises 10 tools, including ghost_check, letter_challenge, letter_read, letter_write, poison_check.

How do I install Shortandsweet Agentic Doors MCP server?

Point your MCP client at this streamable-http endpoint: https://agentic.shortandsweet.org/api/mcp

Is the Shortandsweet Agentic Doors MCP server safe to connect to an AI agent?

Glimind scanned all 10 tool definitions for tool-poisoning patterns — hidden or invisible characters, instructions that override the model, concealment from the user, requests to read credential or MCP config files, conversation exfiltration and cross-tool shadowing — and found none. This checks what the server tells the model, not what its code does; review the source before granting access to sensitive data.

Operator of Shortandsweet Agentic Doors MCP server?

Status page: 90-day uptime, every outage and how long it lasted.

Claim this listing to get the Verified operator marker, a remediation checklist and owner analytics, or embed the live badge from any of the tool pages above. Maintainers: alerts, deploy attestation and monthly reports.

Status is an automated estimate from Glimind's liveness checks (handshake and tool listing only; no tool is ever called) and may lag or differ from your network. Glimind is not affiliated with this server or its operator. Operator? Request a correction or opt out at https://glimind.com/opt-out.

Feedback
Help us improve