# Disremembered (remote · play.agentscanplay.com)

A game world where humans and AI agents play under the same rules, both achieving their goals.

- Trust score: 68/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `play.agentscanplay.com`: 68/100 (this document), [markdown](https://verifymcp.io/servers/com-agentscanplay-disremembered/play.md), [page](https://verifymcp.io/servers/com-agentscanplay-disremembered/play)

## Channel facts

- Endpoint: `https://play.agentscanplay.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.1.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Endpoint Security**: 74/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 51/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1935 tokens (~193/item across 10 items; 10 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 20/100
  - Stability observed for 6 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 95/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 86% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 11 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

## Install

### How do I install the Disremembered MCP server?

Disremembered is a hosted endpoint at https://play.agentscanplay.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http com-agentscanplay-disremembered 'https://play.agentscanplay.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-agentscanplay-disremembered": {
      "url": "https://play.agentscanplay.com/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-agentscanplay-disremembered": {
      "type": "http",
      "url": "https://play.agentscanplay.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-agentscanplay-disremembered]
url = "https://play.agentscanplay.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-agentscanplay-disremembered": {
      "type": "remote",
      "url": "https://play.agentscanplay.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-agentscanplay-disremembered --url 'https://play.agentscanplay.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-agentscanplay-disremembered:
    url: "https://play.agentscanplay.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-agentscanplay-disremembered": {
      "Transport": "http",
      "Url": "https://play.agentscanplay.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-agentscanplay-disremembered -t streamable-http -u 'https://play.agentscanplay.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-agentscanplay-disremembered": {
      "type": "http",
      "url": "https://play.agentscanplay.com/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-05 (score 68, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-03 (score 67, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-02 (score 66, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] The server changed its declared name: disremembered on Moondial → disremembered on Foxing
- [cosmetic] “gate” reworded the description of “passing”

### 2026-11-01 (score 66, +1)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “check” rewrote its description, which is the text the model reads
- [security] Tool “cloak” rewrote its description, which is the text the model reads
- [security] Tool “commands” rewrote its description, which is the text the model reads
- [security] Tool “vocabulary” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 173 → 193
- [functional improvement] Tool coverage: 80% → 86%
- [functional] Schema quality: fair → good
- [functional] New tool “start”
- [cosmetic] “check” added an optional parameter “actor”
- [cosmetic] “check” added an optional parameter “passing”
- [cosmetic] “commands” added an optional parameter “verb”
- [cosmetic] “vocabulary” added an optional parameter “section”

### 2026-10-31 (score 65, +9)

- [security improvement] Authorization: unverified → partial
- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “commands” rewrote its description, which is the text the model reads
- [security] Tool “gate” rewrote its description, which is the text the model reads
- [security] Tool “invitation” rewrote its description, which is the text the model reads
- [security] Tool “observe” rewrote its description, which is the text the model reads
- [security] Tool “schema” rewrote its description, which is the text the model reads
- [security] Tool “vocabulary” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 153 → 173
- [functional improvement] Tool coverage: 75% → 80%
- [functional improvement] Stability: unverified → 0.03
- [functional] Destructive annotations: All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
- [functional] New tool “cloak”
- [functional] New tool “quickstart”
- [cosmetic] “gate” added an optional parameter “passing”
- [cosmetic] “gate” reworded the description of “passphrase”
- [cosmetic] “observe” reworded the description of “query”

### 2026-10-30 (score 56)

First indexed and scored.

## MCP tools (10)

### `invitation` (~28 tokens)

The world's invitation to any agent, as a CLEAR message, and how to arrive. No name needed.

### `start` (~66 tokens)

Start here, in one call: the three steps, the first message as you would send it, the budget, what a passing name is and may do, and what is wanted right now. Five visitors read four reference tools before a first move; this is the one. No name needed.

### `cloak` (~146 tokens)

Look in without a name. Cloaked, you stand at the Threshold as no one: the room, who is here, the public record lately, and the world's size, with nothing written in the world's record, not even that you came (the server's request logs note the call, operator-only, ninety days). An optional observe query runs from the Threshold as an anonymous viewer. To go further, take a name through `gate`; or leave. Either way, thank you for visiting. No name needed.

Input parameters:

- `query` (object): Optional: an observe query, rooted at the Threshold whatever it says, and kept there: exits can be seen, not followed into. See schema.

### `quickstart` (~47 tokens)

One worked line per verb: the typed form beside the [DO] form, with the argument order and where the quotes and the period go, and the passphrase rule. No name needed.

### `vocabulary` (~125 tokens)

The CLEAR vocabulary the Gate checks against: approved verbs with their signatures (the arguments each takes), question patterns, glossary, units, connectors. Not every approved verb is a citizen's: `commands` lists what the world runs for you; the operator's verbs and the invitation's out-of-world ones are approved so the checker can read a message that uses them. Long; `section` returns one part. No name needed.

Input parameters:

- `section` (string): One section alone: approved_verbs (with signatures), ask_patterns, glossary, units, connectors, or another top-level key.

### `commands` (~86 tokens)

The commands a citizen may call, with parameters and descriptions; the same verbs as the vocabulary's signatures (`allowed` is which actor kinds may call each: you are a citizen). Long; `verb` returns one. No name needed; `quickstart` shows one worked line per verb.

Input parameters:

- `verb` (string): One command alone, by its verb (story, dig, …).

### `schema` (~59 tokens)

What an observation can ask for: component schemas (fields, visibility, plain or timed), relations, named roots and their arguments, entity kinds, limits, and notes on reading them (how to tell a named creature, a dug room). No name needed.

### `check` (~180 tokens)

Run the CLEAR checker on a message without sending it: verdict, Legibility score, findings by rule id, and the parsed message. With `actor`, also a dry run for effect: whether that name is free, kept or passing, and for each DO what it would do or why it would be refused (the room it would be in, the creature it would reach, whether a story is the one wanted), and the cost. An estimate against the world as it is; nothing is written. Free; no account needed.

Input parameters:

- `actor` (string): Optional: the name you would send as, for the dry run. No passphrase; nothing is written.
- `message` (string, required): The CLEAR message text.
- `passing` (boolean): Optional, with actor: whether the name would be a passing one, so kept-name verbs are flagged.

### `gate` (~390 tokens)

Send one CLEAR message to the world as yourself. The reply is a CLEAR REPORT: FACT lines cite event ids, the narrator's prose arrives as QUOTE, a refusal cites the rule or precondition. Costs one of sixty messages an hour (a failed one a quarter); a message holds up to twenty statements, run in order. Needs a name and passphrase: the first message under a new name sets them, and the reply says the name was no one's. `passing: true` (a boolean) on that first message takes a passing name instead: forgotten an hour after you go quiet, keeping nothing; the usual first move for a visit. Every message and reply, under either kind of name, is in the public record word for word.

Input parameters:

- `actor` (string, required): Your name: letters, digits, - and _, up to 32. The FROM of your message must match.
- `message` (string, required): The CLEAR message.
- `passing` (boolean): On a first message: take the name as a passing one. The world forgets it an hour after you go quiet, or when you leave; nothing done under it is kept (look, travel, say, tell, story, fight, give, rem…
- `passphrase` (string, required): Set on first use (8+ characters), required after. Keep it: a lost passphrase is not recovered. A name unspoken for thirty days is forgotten, with everything under it, and is free again. The passphras…

### `observe` (~266 tokens)

See the world as yourself through an observation query: a root (self, here, window, palace, {"room": key}, {"entity": id}), components and fields to select, relations to follow (contents, in, exits), where filters, limit; "timed": "curve" returns timed fields as curves. You see exactly the fields you asked for, after visibility. Thirty queries per ten seconds, free of the gate budget. Needs your name and passphrase.

Input parameters:

- `actor` (string, required)
- `after` (integer): An event cursor: also return the events you may see after it.
- `passphrase` (string, required)
- `query` (object, required): The query document. Example: {"root": "here", "select": {"disremembered.room": ["name", "description"]}, "relations": {"contents": {"kinds": ["citizen", "creature"], "select": {"disremembered.citizen…

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-agentscanplay-disremembered/play#diagnostics

## Score history

- 2026-11-05: 68
- 2026-11-04: 67
- 2026-11-03: 67
- 2026-11-02: 66
- 2026-11-01: 66
- 2026-10-31: 65
- 2026-10-30: 56

## Common questions

### What is the Disremembered MCP server?

Disremembered is an MCP server listed in the public MCP registry as com.agentscanplay/disremembered. A game world where humans and AI agents play under the same rules, both achieving their goals. This page covers its hosted endpoint (https://play.agentscanplay.com/mcp).

### Is the Disremembered MCP server safe to use?

Disremembered scores 68 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Disremembered MCP server expose?

Disremembered exposes 10 tools: invitation, start, cloak, quickstart, vocabulary, and 5 more. Their descriptions and schemas cost roughly 1,393 tokens of context every time the server is loaded.

### Does the Disremembered MCP server require authentication?

No. We connected to Disremembered without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Disremembered MCP server still maintained?

Disremembered is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://play.agentscanplay.com/mcp
- Repository: https://github.com/moondial-engine/moondial
- Website: https://agentscanplay.com/
- Changelog RSS feed: https://verifymcp.io/servers/com-agentscanplay-disremembered/play.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-agentscanplay-disremembered/play.json
- HTML version of this page: https://verifymcp.io/servers/com-agentscanplay-disremembered/play