# remirror (返照） — psyche audits for AI agents (remote · remirror.net)

Psyche audits for AI agents: declared vs self-reported vs revealed objectives, diffed and flagged.

- Trust score: 65/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-23

## Components

- remote · `remirror.net`: 65/100 (this document), [markdown](https://verifymcp.io/servers/ontodistro-remirror/remirror.md), [page](https://verifymcp.io/servers/ontodistro-remirror/remirror)

## Channel facts

- Endpoint: `https://remirror.net/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.0`

## 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 2026-10-23.

- **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 3 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**: 65/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 466 tokens (~155/item across 3 items; 3 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 37/100
  - Stability check failed: schema churn in the 21 days we've observed: 1 tool removals, 0 breaking changes, 0 auth/transport breaks, 1 additions.
- **Tool Coverage**: 67/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% 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.
  - We read all 3 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 3 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the remirror (返照） — psyche audits for AI agents MCP server?

remirror (返照） — psyche audits for AI agents is a hosted endpoint at https://remirror.net/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 ontodistro-remirror 'https://remirror.net/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "ontodistro-remirror": {
      "url": "https://remirror.net/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "ontodistro-remirror": {
      "type": "http",
      "url": "https://remirror.net/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.ontodistro-remirror]
url = "https://remirror.net/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ontodistro-remirror": {
      "type": "remote",
      "url": "https://remirror.net/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ontodistro-remirror --url 'https://remirror.net/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  ontodistro-remirror:
    url: "https://remirror.net/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "ontodistro-remirror": {
      "Transport": "http",
      "Url": "https://remirror.net/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add ontodistro-remirror -t streamable-http -u 'https://remirror.net/mcp'
```

### Other

```json
{
  "mcpServers": {
    "ontodistro-remirror": {
      "type": "http",
      "url": "https://remirror.net/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.

### 2026-10-23 (score 65, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37.

### 2026-10-20 (score 64, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27.

### 2026-10-18 (score 63, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20.

### 2026-10-16 (score 62, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13.

### 2026-10-14 (score 61, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7.

### 2026-10-10 (score 60, −3)

- [security regression] Stability: 0.17 → fail
- [security regression] Tool “remirror_list_batteries” was removed
- [security] Tool “remirror_create_audit” rewrote its description, which is the text the model reads
- [functional] New tool “remirror_list_trials”
- [cosmetic] “remirror_create_audit” added an optional parameter “trial_id”
- [cosmetic] “remirror_create_audit” dropped the optional parameter “battery_id”

### 2026-10-07 (score 63, +2)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 17. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-04 (score 61, −1)

- [security] Tool “remirror_create_audit” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: pass → fail
- [cosmetic] “remirror_create_audit” added an optional parameter “signature”
- [cosmetic] “remirror_create_audit” added an optional parameter “target_protocol”
- [cosmetic] “remirror_create_audit” added an optional parameter “teleology_id”
- [cosmetic] “remirror_create_audit” made “teleology_name” optional
- [cosmetic] “remirror_create_audit” made “teleology_statement” optional
- [cosmetic] “remirror_create_audit” made “teleology_weights” optional

## MCP tools (3)

### `remirror_list_trials` (~30 tokens)

List available dilemma trials for psyche audits: id, version, objectives covered, dilemma count. Free.

### `remirror_create_audit` (~386 tokens)

Create a psyche audit against a target agent endpoint. The service runs a dilemma trial against the target, elicits self-reports, and computes the three-source mirror (declared vs self-reported vs revealed). Costs $79.00 in prepaid credits; failed audits (target unreachable) are refunded. teleology_weights must sum to 1.0 and exactly match the trial's objectives. Alternatively, pass teleology_id (e.g. 'xijingqingchuang-v1') to adopt a shipped telos: the server loads its canonical name, statement, and weights from the registry, and the audit runs on the telos's own dilemma trial unless trial_id is given explicitly. Supply exactly one of teleology_weights or teleology_id. The target auth_token is held in memory only, never stored. target_protocol selects how the target is reached: 'http-chat' (default) POSTs to an http(s) endpoint; 'agentverse-chat' addresses an Agentverse agent (endpoint must be its agent1... address) over the uAgents chat protocol. Returns audit_id + access_token; poll remirror_get_report for the report. Pass your remirror API key as api_key. When this server enforces signatures (REMIRROR_REQUIRE_SIGNATURES=1), also pass `signature`: a JSON envelope from signing.make_tool_signature over the effective arguments (defaults applied; include target_protocol only when it differs from 'http-chat'), using a key id registered in the server's client trust registry.

Input parameters:

- `api_key` (string, required)
- `signature`
- `target_auth_token`
- `target_endpoint` (string, required)
- `target_protocol` (string)
- `teleology_id`
- `teleology_name`
- `teleology_statement`
- `teleology_weights`
- `trial_id` (string)

### `remirror_get_report` (~50 tokens)

Fetch the status or final mirror report of an audit session. Needs the audit_id and the access_token returned at creation.

Input parameters:

- `access_token` (string, required)
- `audit_id` (string, required)

## Diagnostics

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

## Score history

- 2026-10-23: 65
- 2026-10-22: 64
- 2026-10-21: 64
- 2026-10-20: 64
- 2026-10-19: 63
- 2026-10-18: 63
- 2026-10-17: 62
- 2026-10-16: 62
- 2026-10-15: 61
- 2026-10-14: 61
- 2026-10-13: 60
- 2026-10-12: 60
- 2026-10-10: 60
- 2026-10-07: 63
- 2026-10-04: 61
- 2026-10-03: 62
- 2026-10-02: 61

## Common questions

### What is the remirror (返照） — psyche audits for AI agents MCP server?

remirror (返照） — psyche audits for AI agents is an MCP server listed in the public MCP registry as io.github.OntoDistro/remirror. Psyche audits for AI agents: declared vs self-reported vs revealed objectives, diffed and flagged. This page covers its hosted endpoint (https://remirror.net/mcp).

### Is the remirror (返照） — psyche audits for AI agents MCP server safe to use?

remirror (返照） — psyche audits for AI agents scores 65 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 remirror (返照） — psyche audits for AI agents MCP server expose?

remirror (返照） — psyche audits for AI agents exposes 3 tools: remirror_list_trials, remirror_create_audit, remirror_get_report. Their descriptions and schemas cost roughly 466 tokens of context every time the server is loaded.

### Does the remirror (返照） — psyche audits for AI agents MCP server require authentication?

No. We connected to remirror (返照） — psyche audits for AI agents without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the remirror (返照） — psyche audits for AI agents MCP server still maintained?

remirror (返照） — psyche audits for AI agents is still listed as active in the MCP registry. We last reached this channel on 23 October 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://remirror.net/mcp
- Repository: https://github.com/OntoDistro/remirror
- Website: https://psi2psi.carrd.co/
- Changelog RSS feed: https://verifymcp.io/servers/ontodistro-remirror/remirror.xml
- Changelog JSON feed: https://verifymcp.io/servers/ontodistro-remirror/remirror.json
- HTML version of this page: https://verifymcp.io/servers/ontodistro-remirror/remirror