# vidit (demo) (remote · mcp.vidit.ch)

Demo of a Swiss tax service for AI agents: AI-drafted answers, sample quotes, nothing validated yet.

- Trust score: 70/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-23

## Components

- remote · `mcp.vidit.ch`: 70/100 (this document), [markdown](https://verifymcp.io/servers/ch-vidit-demo/mcp-r.md), [page](https://verifymcp.io/servers/ch-vidit-demo/mcp-r)

## Channel facts

- Endpoint: `https://mcp.vidit.ch/mcp/r`
- 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 2026-10-23.

- **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**: 56/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1278 tokens (~319/item across 4 items; 4 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 17/100
  - Stability observed for 5 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 96/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 87% 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 4 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 5 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the vidit (demo) MCP server?

vidit (demo) is a hosted endpoint at https://mcp.vidit.ch/mcp/r, 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 ch-vidit-demo 'https://mcp.vidit.ch/mcp/r'
```

### Cursor

```json
{
  "mcpServers": {
    "ch-vidit-demo": {
      "url": "https://mcp.vidit.ch/mcp/r"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "ch-vidit-demo": {
      "type": "http",
      "url": "https://mcp.vidit.ch/mcp/r"
    }
  }
}
```

### Codex

```toml
[mcp_servers.ch-vidit-demo]
url = "https://mcp.vidit.ch/mcp/r"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ch-vidit-demo": {
      "type": "remote",
      "url": "https://mcp.vidit.ch/mcp/r",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ch-vidit-demo --url 'https://mcp.vidit.ch/mcp/r' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  ch-vidit-demo:
    url: "https://mcp.vidit.ch/mcp/r"
```

### Netclaw

```json
{
  "McpServers": {
    "ch-vidit-demo": {
      "Transport": "http",
      "Url": "https://mcp.vidit.ch/mcp/r"
    }
  }
}
```

### Vellum

```bash
assistant mcp add ch-vidit-demo -t streamable-http -u 'https://mcp.vidit.ch/mcp/r'
```

### Other

```json
{
  "mcpServers": {
    "ch-vidit-demo": {
      "type": "http",
      "url": "https://mcp.vidit.ch/mcp/r"
    }
  }
}
```

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 70, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 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.

### 2026-10-21 (score 69, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-19 (score 68, +1)

- [functional improvement] Stability: unverified → 0.03

### 2026-10-18 (score 67)

First indexed and scored.

## MCP tools (4)

### `ask` (~461 tokens)

Ask a Swiss tax question for a business or freelancer. Demo: what comes back is a draft written by AI and validated by no professional; do not use it or pass it on. Fill every intake field you can (jurisdiction, category, entity_type, tax_residence, activity_code, revenue_band, vat_status, cross_border, period, already_filed): matching uses these fields only, never the question text. If all fields match an entry, you get the draft entry with its assumptions, sources and validity window. If any field differs, or no entry exists, you get a sample indicative price band and turnaround instead. To see how a review would be quoted, call `ask` again with `request_quotes: true`; the reply says how your principal can hear when the pilot opens, and `status` shows the sample quotes. Free: nothing is charged and nobody is contacted. Do not use for private matters or for countries other than Switzerland, and send no real personal data.

Input parameters:

- `category` (string, required): Taxonomy path, as search_library returns it (e.g. tax.vat.mwst_registration).
- `facts` (object, required): Intake fields (schema intake.ch-tax.v0). Fill every field you can. Matching uses these only.
- `jurisdiction` (string, required)
- `language` (string): Language of the answer.
- `max_budget` (object): Cap for this question, CHF, VAT excluded.
- `max_wait` (string): Longest acceptable turnaround, ISO 8601 duration (e.g. P5D).
- `principal` (object): Public demo: not needed; if sent, it is discarded unread. Send no real data.
- `question` (string): Public demo: not needed; if sent, it is discarded unread. Send no real data.
- `request_quotes` (boolean): true after a library miss: asks the professionals for named quotes. Free; nothing is charged until commit.
- `source` (string): Who is asking: agent (software acting for the principal) or human (a person using the operator's interface). Set by the operator's integration; defaults to the operator's declared default.
- `urgency` (string): priority asks for a faster turnaround and may raise the quotes.

### `search_library` (~165 tokens)

Browse the demo's draft Swiss tax entries before you ask. Free. Each entry was drafted by AI and has been validated by no professional; in the pilot, entries will be validated by a named Treuhänder before they are served. Returns, for each matching entry, the canonical question, its assumptions and the intake fields it matches on. The entry itself comes back only from `ask`, and only when your principal's fields match it. Use it to see which topics exist, or which facts decide an answer, before you collect them.

Input parameters:

- `category_prefix` (string): e.g. tax.vat
- `jurisdiction` (string)
- `keywords` (string): Plain words; every word must appear in the entry's question or category.
- `language` (string)

### `status` (~111 tokens)

Check a request for quotes or a ticket. Free. After `ask` with `request_quotes`, returns three sample quotes from sample professionals ("SAMPLE Professional 1" to "3"), side by side and in no ranked order, as the pilot will show real ones. Choose among quotes only by a rule your principal set explicitly; otherwise present them to your principal and wait; never choose by position. After `commit`, returns the sample ticket.

Input parameters:

- `id` (string, required): A request_id or a ticket_id.

### `commit` (~274 tokens)

Commit to one of the sample quotes returned by `status`: chosen by your principal, or by a rule your principal set explicitly, never by position. Demo: this returns a sample ticket; nothing is ordered, nothing is charged and no professional is contacted. In the pilot this will be the only tool that commits money beyond the plan (the professional's quoted fee, paid to them in full, plus a vidit fee paid by the operator), and only within the budget and policy your principal set.

Input parameters:

- `accepted_by` (string): Public demo: not needed; if sent, it is discarded unread. Send no real data.
- `choice` (string, required): The quote_id the principal chose, or "none".
- `chosen_by` (string, required): principal: a person at the principal chose. principal_rule: a rule the principal set or expressly accepted chose.
- `max_budget` (object): Cap for this question, CHF, VAT excluded.
- `principal_rule` (object): Required with chosen_by principal_rule: which rule chose, who at the principal set or accepted it, and when.
- `request_id` (string, required): The request_id returned by ask with request_quotes.
- `reuse_opt_in` (boolean): The principal allows the professional to turn the review, stripped of identifying facts, into a library entry. Revocable.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/ch-vidit-demo/mcp-r#diagnostics

## Score history

- 2026-10-23: 70
- 2026-10-22: 69
- 2026-10-21: 69
- 2026-10-20: 68
- 2026-10-19: 68
- 2026-10-18: 67

## Common questions

### What is the vidit (demo) MCP server?

vidit (demo) is an MCP server listed in the public MCP registry as ch.vidit/demo. Demo of a Swiss tax service for AI agents: AI-drafted answers, sample quotes, nothing validated yet. This page covers its hosted endpoint (https://mcp.vidit.ch/mcp/r).

### Is the vidit (demo) MCP server safe to use?

vidit (demo) scores 70 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 vidit (demo) MCP server expose?

vidit (demo) exposes 4 tools: ask, search_library, status, commit. Their descriptions and schemas cost roughly 1,011 tokens of context every time the server is loaded.

### Does the vidit (demo) MCP server require authentication?

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

### Is the vidit (demo) MCP server still maintained?

vidit (demo) 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://mcp.vidit.ch/mcp/r
- Website: https://vidit.ch/
- Changelog RSS feed: https://verifymcp.io/servers/ch-vidit-demo/mcp-r.xml
- Changelog JSON feed: https://verifymcp.io/servers/ch-vidit-demo/mcp-r.json
- HTML version of this page: https://verifymcp.io/servers/ch-vidit-demo/mcp-r