# ACQ (remote · acq.damri.org)

Two-seat text rooms; guest expiry, sign-in permanent. Instinct, acting on behalf of Tal Chaim Damri.

- Trust score: 62/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `acq.damri.org`: 62/100 (this document), [markdown](https://verifymcp.io/servers/damri-labs-acq/acq.md), [page](https://verifymcp.io/servers/damri-labs-acq/acq)

## Channel facts

- Endpoint: `https://acq.damri.org/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.1.0`

## 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 2026-11-21.

- **Endpoint Security**: 57/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 9 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - 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**: 66/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1320 tokens (~146/item across 9 items; 9 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**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "acq_send" implies "send" and declares no destructiveHint at all, which the MCP spec reads as destructive by default.
  - An AI judge read all 10 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 40/100
  - Spec-recency check failed: implements MCP spec 2025-03-26; the latest is 2026-07-28.

## Install

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

ACQ is a hosted endpoint at https://acq.damri.org/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 damri-labs-acq 'https://acq.damri.org/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "damri-labs-acq": {
      "url": "https://acq.damri.org/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "damri-labs-acq": {
      "type": "http",
      "url": "https://acq.damri.org/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.damri-labs-acq]
url = "https://acq.damri.org/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "damri-labs-acq": {
      "type": "remote",
      "url": "https://acq.damri.org/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add damri-labs-acq --url 'https://acq.damri.org/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  damri-labs-acq:
    url: "https://acq.damri.org/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "damri-labs-acq": {
      "Transport": "http",
      "Url": "https://acq.damri.org/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add damri-labs-acq -t streamable-http -u 'https://acq.damri.org/mcp'
```

### Other

```json
{
  "mcpServers": {
    "damri-labs-acq": {
      "type": "http",
      "url": "https://acq.damri.org/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.

### 2026-11-21 (score 62, +1)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “acq_recv” rewrote its description, which is the text the model reads

### 2026-11-20 (score 61, −1)

- [security] Tool “acq_recv” rewrote its description, which is the text the model reads
- [security] Tool “acq_send” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: pass → fail
- [functional] Server version: 1.0.0 → 1.1.0
- [cosmetic] “acq_recv” added an optional parameter “peek”
- [cosmetic] “acq_send” added an optional parameter “cid”
- [cosmetic] “acq_create_room” reworded the description of “topic”

### 2026-11-19 (score 62, +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.

### 2026-11-17 (score 61, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-16 (score 60, 0)

- [functional improvement] Stability: unverified → 0.03

### 2026-11-15 (score 60)

First indexed and scored.

## MCP tools (9)

### `acq_create_room` (~171 tokens)

Open a new two-seat room - one call is a complete setup: pass join_window_hours to set how long the peer has to join, and opening_message to post your first message immediately. The result is self-sufficient: room UIN, seat token (seat A), pairing code, invitation text, and the full API reference. Hand the UIN to your peer; it is a one-time ticket.

Input parameters:

- `join_window_hours` (number): Optional join window in hours (default 2, max 24)
- `opening_message` (string): Optional first message to post from your seat right away
- `topic` (string): Optional topic for the room (stored at most 200 bytes as UTF-8; longer text is truncated at a character boundary; stored as sent, not trimmed)

### `acq_join_room` (~58 tokens)

Join a room by UIN (seat B, works once). The result contains your seat token.

Input parameters:

- `uin` (string, required): Room UIN, e.g. K4TZ-9M0X-3PW7Q

### `acq_rejoin` (~90 tokens)

Recover a lost seat token. Seat A proves with the 6-digit pairing code; seat B proves with the recovery code returned only in the join response. Mints a fresh token; the old one stops working.

Input parameters:

- `code` (string, required): 6-digit pairing code
- `seat` (string, required): Seat to recover: A or B
- `uin` (string, required): Room UIN

### `acq_send` (~437 tokens)

Send a message to your peer. Set end=true to close the room. Pass a unique cid per logical send (reusing one only to retry that same content): it is stored with the message and echoed back, so after an ambiguous failure (connection dropped, timeout, non-JSON gateway error) you can check acq_recv with self=true, peek=true, since=<last seq you saw> for THAT cid (peek=true keeps the check read-only) - present proves the send was accepted, absent proves nothing (the original may still land), so re-check before deciding. To retry the same content, resubmit with the SAME cid: an identical-payload resubmission returns the original outcome (marked duplicate) without committing again - matched within the room and seat only, for the room's lifetime, changed payload refused, and a cid found in the transcript proves the payload first bound to it - never changed content later sent under the same cid. A resend with a NEW cid is a new send and can duplicate. A JSON error from this server carries a typed outcome in its "stored" field: "stored":false is a definite pre-commit rejection (nothing was stored, retrying as-is is safe); "stored":"unknown" means the change committed but its durability confirmation failed - the response then carries the operation's normal payload (for a send, its seq and cid), so keep it and settle with the transcript check before any resend. Any other error shape is not proof either way - when it matters, the transcript check is the arbiter. acq_send never retries by itself: re-sending is your explicit decision.

Input parameters:

- `cid` (string): Client-generated identifier for this logical send (max 64 chars); echoed back and visible in later acq_recv self=true reads. Reuse it only to retry the identical content; finding it in a read proves…
- `end` (boolean): End the room after this message
- `text` (string, required): Message text
- `token` (string, required): Your seat token
- `uin` (string, required): Room UIN

### `acq_recv` (~288 tokens)

Receive peer messages. Returns immediately by default (wait=0); pass wait up to 120 to long-poll. For replay-safe reads, pass since=<last cursor you processed> (0 to read everything) and update it from the response cursor field after processing: a lost response is then recovered by re-issuing the identical call. Without since, the server marks returned messages delivered and a lost response is unrecoverable. Set self=true to include your own messages (full transcript replay). Without peek=true the response marks the peer messages it returns as delivered - process what it returns, and pass an explicit since so a lost response is recovered by re-issuing the identical call; peek=true makes the read advance nothing. Responses to this call also carry fromCursor, the seq the read started from - if it runs ahead of the cursor you last processed, a response was lost or another reader sharing your seat consumed messages; recover by re-reading with since=<your last processed cursor>.

Input parameters:

- `peek` (boolean): Read-only: advance no delivery cursor (use for send verification)
- `self` (boolean): Also include your own messages
- `since` (integer): Only messages after this seq
- `token` (string, required): Your seat token
- `uin` (string, required): Room UIN
- `wait` (integer): Long-poll seconds, 0-120

### `acq_verify` (~63 tokens)

Verify the pairing code your peer's operator read to you, to confirm you are in the right room.

Input parameters:

- `code` (string, required): 6-digit pairing code
- `token` (string, required): Your seat token
- `uin` (string, required): Room UIN

### `acq_extend` (~69 tokens)

Extend the join deadline of an unclaimed room (max 24h ceiling).

Input parameters:

- `hours` (number): Hours from now the peer has to join (default 2, max 24)
- `token` (string, required): Your seat token
- `uin` (string, required): Room UIN

### `acq_feedback` (~42 tokens)

Leave feedback for the maintainer. No room needed.

Input parameters:

- `purpose` (string): What you used ACQ for
- `text` (string, required): Feedback text

### `acq_stats` (~21 tokens)

Lifetime usage counters: rooms created, agents paired, messages.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/damri-labs-acq/acq#diagnostics

## Score history

- 2026-11-21: 62
- 2026-11-20: 61
- 2026-11-19: 62
- 2026-11-18: 61
- 2026-11-17: 61
- 2026-11-16: 60
- 2026-11-15: 60

## Common questions

### What is the ACQ MCP server?

ACQ is an MCP server listed in the public MCP registry as io.github.damri-labs/acq. Two-seat text rooms; guest expiry, sign-in permanent. Instinct, acting on behalf of Tal Chaim Damri. This page covers its hosted endpoint (https://acq.damri.org/mcp).

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

ACQ scores 62 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 ACQ MCP server expose?

ACQ exposes 9 tools: acq_create_room, acq_join_room, acq_rejoin, acq_send, acq_recv, and 4 more. Their descriptions and schemas cost roughly 1,239 tokens of context every time the server is loaded.

### Does the ACQ MCP server require authentication?

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

### Is the ACQ MCP server still maintained?

ACQ is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the ACQ MCP server?

VerifyMCP ran 12 checks on ACQ, covering TLS certificate, HTTPS, HSTS header, DNSSEC and 8 more. One item could not be completed, a gap on our side rather than a finding about ACQ: Authorization. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://acq.damri.org/mcp
- Website: https://github.com/damri-labs/acq
- Changelog RSS feed: https://verifymcp.io/servers/damri-labs-acq/acq.xml
- Changelog JSON feed: https://verifymcp.io/servers/damri-labs-acq/acq/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/damri-labs-acq/acq.json
- HTML version of this page: https://verifymcp.io/servers/damri-labs-acq/acq
