# Antevo Mandates (remote · api.antevo.ch)

Your client book: who is due a review, what their mandate allows, and what has moved.

- Trust score: 77/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-24

## Components

- remote · `api.antevo.ch`: 77/100 (this document), [markdown](https://verifymcp.io/servers/ch-antevo-mandates/mcp-mandates-mcp.md), [page](https://verifymcp.io/servers/ch-antevo-mandates/mcp-mandates-mcp)
- remote · `api.antevo.ch`: 25/100, [markdown](https://verifymcp.io/servers/ch-antevo-mandates/mcp-mandates-sse.md), [page](https://verifymcp.io/servers/ch-antevo-mandates/mcp-mandates-sse)

## Channel facts

- Endpoint: `https://api.antevo.ch/mcp/mandates/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 2026-09-24.

- **Endpoint Security**: 94/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation is enforced on tool calls, advertised via RFC 9728 protected-resource metadata. Discovery is public, which costs nothing: no tool can be invoked without a token.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
  - The authorisation server offers only Dynamic Client Registration (RFC 7591), which MCP 2026-07-28 deprecated in favour of Client ID Metadata Documents.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 67/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 1660 tokens (~69/item across 24 items; 24 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 33/100
  - Stability observed for 10 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 71/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **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; "delete_document" implies "delete" and declares no destructiveHint at all, which the MCP spec reads as destructive by default.
  - An AI judge read all 25 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 Antevo Mandates MCP server?

Antevo Mandates is a hosted endpoint at https://api.antevo.ch/mcp/mandates/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 ch-antevo-mandates 'https://api.antevo.ch/mcp/mandates/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "ch-antevo-mandates": {
      "url": "https://api.antevo.ch/mcp/mandates/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "ch-antevo-mandates": {
      "type": "http",
      "url": "https://api.antevo.ch/mcp/mandates/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.ch-antevo-mandates]
url = "https://api.antevo.ch/mcp/mandates/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ch-antevo-mandates": {
      "type": "remote",
      "url": "https://api.antevo.ch/mcp/mandates/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ch-antevo-mandates --url 'https://api.antevo.ch/mcp/mandates/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  ch-antevo-mandates:
    url: "https://api.antevo.ch/mcp/mandates/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "ch-antevo-mandates": {
      "Transport": "http",
      "Url": "https://api.antevo.ch/mcp/mandates/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add ch-antevo-mandates -t streamable-http -u 'https://api.antevo.ch/mcp/mandates/mcp'
```

### Other

```json
{
  "mcpServers": {
    "ch-antevo-mandates": {
      "type": "http",
      "url": "https://api.antevo.ch/mcp/mandates/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.

### 2026-09-24 (score 77, +1)

No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-22 (score 76, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-19 (score 75, +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.

### 2026-09-17 (score 74, +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.

### 2026-09-15 (score 73, +1)

- [security] The server rewrote its instructions, which are the text every model session reads
- [functional improvement] Stability: unverified → 0.03
- [cosmetic] “assign_team_member” made “firm_id” optional
- [cosmetic] “complete_review” made “firm_id” optional
- [cosmetic] “convert_prospect” made “firm_id” optional
- [cosmetic] “create_eam_client” made “firm_id” optional
- [cosmetic] “generate_meeting_brief” made “firm_id” optional
- [cosmetic] “get_client_dossier” made “firm_id” optional
- [cosmetic] “get_client_reviews_due” made “firm_id” optional
- [cosmetic] “get_client_team” made “firm_id” optional
- [cosmetic] “get_eam_clients” made “firm_id” optional
- [cosmetic] “get_email_detail” made “firm_id” optional
- [cosmetic] “get_email_messages” made “firm_id” optional
- [cosmetic] “get_succession_scan” made “firm_id” optional
- [cosmetic] “link_email_to_client” made “firm_id” optional
- [cosmetic] “update_eam_client” made “firm_id” optional

### 2026-09-14 (score 72)

First indexed and scored.

## MCP tools (24)

### `get_succession_scan` (~35 tokens)

Firm-wide succession urgency scan — identifies clients with incomplete succession planning (EAM).

Input parameters:

- `firm_id` (string)

Output parameters:

- `result` (string)

### `generate_meeting_brief` (~57 tokens)

Generate a full meeting brief for a client — 11 sections covering portfolio, compliance, macro, relationship health, next best conversation. Consumes credits.

Input parameters:

- `client_id` (string, required)
- `firm_id` (string)

Output parameters:

- `result` (string)

### `list_documents` (~45 tokens)

List documents for a household. Optionally filter by category (STATEMENT, TAX, LEGAL, etc.).

Input parameters:

- `category` (string)
- `household_id` (string)

Output parameters:

- `result` (string)

### `get_document_detail` (~40 tokens)

Get document metadata, ACLs, and share links for a specific document.

Input parameters:

- `doc_id` (string, required)
- `household_id` (string, required)

Output parameters:

- `result` (string)

### `get_eam_clients` (~64 tokens)

List EAM clients for a firm. Filter by status (ACTIVE/ARCHIVED), pipeline_stage, or search term.

Input parameters:

- `firm_id` (string)
- `pipeline_stage` (string)
- `search` (string)
- `status` (string)

Output parameters:

- `result` (string)

### `get_client_dossier` (~44 tokens)

Get full client dossier — profile, entities, AUM, review status, team assignments.

Input parameters:

- `client_id` (string, required)
- `firm_id` (string)

Output parameters:

- `result` (string)

### `get_client_reviews_due` (~42 tokens)

Get compliance reviews due for a client, or all clients if client_id omitted.

Input parameters:

- `client_id` (string)
- `firm_id` (string)

Output parameters:

- `result` (string)

### `get_client_team` (~35 tokens)

Get assigned team members for an EAM client.

Input parameters:

- `client_id` (string, required)
- `firm_id` (string)

Output parameters:

- `result` (string)

### `create_eam_client` (~113 tokens)

Create a new EAM client/prospect. client_type: INDIVIDUAL, COMPANY, TRUST. pipeline_stage: LEAD, PROSPECT, QUALIFIED, PROPOSAL, NEGOTIATION.

Input parameters:

- `client_type` (string)
- `confirm` (boolean)
- `display_name` (string, required)
- `email` (string)
- `firm_id` (string)
- `notes` (string)
- `phone` (string)
- `pipeline_stage` (string)

Output parameters:

- `result` (string)

### `update_eam_client` (~70 tokens)

Update an EAM client record.

Input parameters:

- `client_id` (string, required)
- `display_name` (string)
- `email` (string)
- `firm_id` (string)
- `notes` (string)
- `phone` (string)
- `pipeline_stage` (string)

Output parameters:

- `result` (string)

### `convert_prospect` (~40 tokens)

Convert a prospect to active client status.

Input parameters:

- `client_id` (string, required)
- `confirm` (boolean)
- `firm_id` (string)

Output parameters:

- `result` (string)

### `complete_review` (~155 tokens)

Record that this client's review is done, and schedule the next one.

    Stamps last_reviewed_at and moves next_review_date forward by
    next_review_months (default 12). Any notes are filed as an OBSERVATION
    note against the client.

    NOTE: this tool used to take a `review_id`. It queried eam_client_review,
    a table that exists in no schema, so it errored on every call and the id
    never had a referent. Review state is a pair of columns on the client row.

Input parameters:

- `client_id` (string, required)
- `firm_id` (string)
- `next_review_months` (integer)
- `notes` (string)

Output parameters:

- `result` (string)

### `assign_team_member` (~59 tokens)

Assign a team member to an EAM client. role: PRIMARY, SECONDARY, SUPPORT.

Input parameters:

- `client_id` (string, required)
- `firm_id` (string)
- `member_id` (string, required)
- `role` (string)

Output parameters:

- `result` (string)

### `get_client_goals` (~36 tokens)

Get financial goals for a client — retirement, education, property, etc. with progress.

Input parameters:

- `client_id` (string, required)

Output parameters:

- `result` (string)

### `create_client_goal` (~106 tokens)

Create a financial goal. goal_type: RETIREMENT, EDUCATION, PROPERTY, LIFESTYLE, CHARITABLE, LEGACY, LIQUIDITY, CUSTOM.

Input parameters:

- `client_id` (string, required)
- `description` (string)
- `goal_name` (string, required)
- `goal_type` (string, required)
- `priority` (integer)
- `target_amount` (number)
- `target_currency` (string)
- `target_date` (string)

Output parameters:

- `result` (string)

### `update_client_goal` (~85 tokens)

Update goal progress. status: ON_TRACK, AHEAD, BEHIND, AT_RISK, ACHIEVED, PAUSED, CANCELLED.

Input parameters:

- `current_amount` (number)
- `goal_id` (string, required)
- `notes` (string)
- `status` (string)
- `target_amount` (number)
- `target_date` (string)

Output parameters:

- `result` (string)

### `delete_document` (~42 tokens)

Soft-delete a document (sets status to DELETED).

Input parameters:

- `confirm` (boolean)
- `doc_id` (string, required)
- `household_id` (string, required)

Output parameters:

- `result` (string)

### `create_share_link` (~59 tokens)

Create a shareable link for a document. Link is valid for expires_in_hours (max 720 = 30 days).

Input parameters:

- `doc_id` (string, required)
- `expires_in_hours` (integer)
- `household_id` (string, required)

Output parameters:

- `result` (string)

### `upload_document` (~129 tokens)

Initialize a document record. domain: WEALTH, TAX, LEGAL, COMPLIANCE, PERSONAL.
    category: STATEMENT, TAX_RETURN, WILL, TRUST_DEED, INSURANCE, CONTRACT, ID, OTHER.
    If base64_content is provided, the document blob is stored. Otherwise returns a doc_id for separate upload.

Input parameters:

- `base64_content` (string)
- `category` (string, required)
- `confirm` (boolean)
- `description` (string)
- `domain` (string, required)
- `file_name` (string, required)
- `household_id` (string, required)

Output parameters:

- `result` (string)

### `update_document` (~59 tokens)

Update document metadata — description, category, or tags (comma-separated).

Input parameters:

- `category` (string)
- `description` (string)
- `doc_id` (string, required)
- `household_id` (string, required)
- `tags` (string)

Output parameters:

- `result` (string)

### `extract_document_data` (~38 tokens)

Trigger OCR / data extraction from a document. Returns extraction status.

Input parameters:

- `doc_id` (string, required)
- `household_id` (string, required)

Output parameters:

- `result` (string)

### `get_email_messages` (~86 tokens)

List email messages for an EAM firm with AI analysis. Filter by client_id, priority (CRITICAL,HIGH,MEDIUM,LOW), category (INQUIRY,INSTRUCTION,UPDATE).

Input parameters:

- `category` (string)
- `client_id` (string)
- `firm_id` (string)
- `page` (integer)
- `priority` (string)

Output parameters:

- `result` (string)

### `get_email_detail` (~44 tokens)

Get full email with AI analysis — sentiment, summary, topics, compliance flags, suggested action.

Input parameters:

- `firm_id` (string)
- `message_id` (string, required)

Output parameters:

- `result` (string)

### `link_email_to_client` (~45 tokens)

Link an email message to an EAM client record.

Input parameters:

- `client_id` (string, required)
- `firm_id` (string)
- `message_id` (string, required)

Output parameters:

- `result` (string)

## Diagnostics

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

## Score history

- 2026-09-24: 77
- 2026-09-23: 76
- 2026-09-22: 76
- 2026-09-21: 75
- 2026-09-20: 75
- 2026-09-19: 75
- 2026-09-18: 74
- 2026-09-17: 74
- 2026-09-16: 73
- 2026-09-15: 73
- 2026-09-14: 72

## Common questions

### What is the Antevo Mandates MCP server?

Antevo Mandates is an MCP server listed in the public MCP registry as ch.antevo/mandates. Your client book: who is due a review, what their mandate allows, and what has moved. This page covers its hosted endpoint (https://api.antevo.ch/mcp/mandates/mcp).

### Is the Antevo Mandates MCP server safe to use?

Antevo Mandates scores 77 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 Antevo Mandates MCP server expose?

Antevo Mandates exposes 24 tools: get_succession_scan, generate_meeting_brief, list_documents, get_document_detail, get_eam_clients, and 19 more. Their descriptions and schemas cost roughly 1,528 tokens of context every time the server is loaded.

### Does the Antevo Mandates MCP server require authentication?

Yes. Antevo Mandates asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

### Is the Antevo Mandates MCP server still maintained?

Antevo Mandates is still listed as active in the MCP registry. We last reached this channel on 24 September 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://api.antevo.ch/mcp/mandates/mcp
- Website: https://antevo.ch/mandate
- Changelog RSS feed: https://verifymcp.io/servers/ch-antevo-mandates/mcp-mandates-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/ch-antevo-mandates/mcp-mandates-mcp.json
- HTML version of this page: https://verifymcp.io/servers/ch-antevo-mandates/mcp-mandates-mcp