# com.myprivacyagent/public (remote · myprivacyagent.com)

Read-only opt-out guides, removal routes for 950+ data brokers, and privacy library search.

- Trust score: 70/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-28

## Components

- remote · `myprivacyagent.com`: 70/100 (this document), [markdown](https://verifymcp.io/servers/com-myprivacyagent-public/api-mcp.md), [page](https://verifymcp.io/servers/com-myprivacyagent-public/api-mcp)

## Channel facts

- Endpoint: `https://myprivacyagent.com/api/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `2026.9.16`

## 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 2026-09-28.

- **Endpoint Security**: 63/100
  - 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 11 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.
  - The HSTS (Strict-Transport-Security) header is present.
  - 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**: 76/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 1086 tokens (~98/item across 11 items; 11 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 37/100
  - Stability observed for 11 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 74/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 23% 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 11 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 12 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 com.myprivacyagent/public MCP server?

com.myprivacyagent/public is a hosted endpoint at https://myprivacyagent.com/api/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-myprivacyagent-public 'https://myprivacyagent.com/api/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-myprivacyagent-public": {
      "url": "https://myprivacyagent.com/api/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-myprivacyagent-public": {
      "type": "http",
      "url": "https://myprivacyagent.com/api/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-myprivacyagent-public]
url = "https://myprivacyagent.com/api/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-myprivacyagent-public": {
      "type": "remote",
      "url": "https://myprivacyagent.com/api/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-myprivacyagent-public --url 'https://myprivacyagent.com/api/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-myprivacyagent-public:
    url: "https://myprivacyagent.com/api/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-myprivacyagent-public": {
      "Transport": "http",
      "Url": "https://myprivacyagent.com/api/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-myprivacyagent-public -t streamable-http -u 'https://myprivacyagent.com/api/mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-myprivacyagent-public": {
      "type": "http",
      "url": "https://myprivacyagent.com/api/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.

### 2026-09-28 (score 70, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-09-25 (score 69, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-09-23 (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.

### 2026-09-21 (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.

### 2026-09-19 (score 66, +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.

### 2026-09-18 (score 65, 0)

- [functional regression] Tool coverage: 29% → 23%
- [functional improvement] Schema quality: 117 → 98
- [functional improvement] Stability: unverified → 0.03
- [functional] Schema quality: excellent → good
- [functional] New tool “get_case_status”
- [functional] New tool “get_my_report”
- [functional] New tool “list_my_cases”
- [functional] New tool “list_my_subjects”
- [functional] New tool “request_recheck”
- [functional] New tool “submit_approved_plan”

### 2026-09-17 (score 65)

First indexed and scored.

## MCP tools (11)

### `get_opt_out_instructions` (~105 tokens)

Get opt-out instructions for a site

Step-by-step, verified opt-out instructions for one people-search or data-broker site, plus what My Privacy Agent does for that site after a person authorizes it. Accepts a guide slug (spokeo), a domain (spokeo.com), an alias, or a URL on the site. Returns status not_found with a hint when no guide exists.

Input parameters:

- `broker` (string, required): Guide slug, domain, alias, or a URL on the broker's site.

### `list_opt_out_guides` (~72 tokens)

List available opt-out guides

Summaries of every published step-by-step guide (slug, domain, category, method, difficulty, turnaround, support level). Use it to find the right slug before calling get_opt_out_instructions.

Input parameters:

- `category` (string)
- `limit` (integer)
- `offset` (integer)

### `get_removal_route` (~116 tokens)

Get the documented removal route for a site

For any of the 950+ sites in the takedown registry: the documented removal method (form, email, both, guide, or none), the opt-out URL and privacy email on record, the parent company that actually processes the request, sibling sites one request may cover, and a link to our step-by-step guide when one exists. Accepts a domain or a URL.

Input parameters:

- `domain` (string, required): Domain or URL on the site, e.g. spokeo.com or https://www.spokeo.com/...

### `search_privacy_library` (~79 tokens)

Search the public privacy library

Search My Privacy Agent's published articles, opt-out guides, help answers, and plan facts. Returns ranked hits with canonical URLs to cite. Use it before answering questions about data brokers, opt-outs, relisting, pricing, or what the service does and does not do.

Input parameters:

- `limit` (integer)
- `query` (string, required)

### `get_service_overview` (~53 tokens)

How to hand a person to My Privacy Agent

The public service description: scope of these tools, the private handoff pages (free check, review a listing, pricing), the rules assistants must follow, and registry statistics. Call this once before recommending the service.

### `list_my_subjects` (~56 tokens)

List the subjects on my account

Requires OAuth. Lists the person (first name, city, state, verification status) whose exposure this account has checked, with the subject_id other personal tools need. Returns authorization_required with a connect URL when the token is missing.

### `get_my_report` (~80 tokens)

Read my exposure report

Requires OAuth and the 'share_results' permission for the subject. Returns the report summary the dashboard shows: status, counts, and per-site findings (site, status, what it exposes, guide link). No listing URLs or observed values are included. Returns authorization_required with a connect URL when the permission is missing.

Input parameters:

- `subject_id` (string)

### `list_my_cases` (~69 tokens)

List my removal cases

Requires OAuth and the 'share_results' permission. Lists removal cases (site, action, status, verification status, steps only the person can do, dates). Status words mean different things: filed, pending, needs review, verified removed. Never collapse them.

Input parameters:

- `subject_id` (string)

### `get_case_status` (~50 tokens)

Read one removal case

Requires OAuth and the 'share_results' permission. Returns one case by case_id with its current status, verification status, and any step only the person can do.

Input parameters:

- `case_id` (string, required)

### `request_recheck` (~105 tokens)

Re-check my exposure now

Requires OAuth and the 'run_check' permission. Queues a fresh check of the person's existing details (the same re-scan Patrol runs monthly). Patrol plan only, verified subjects only, once per 24 hours; it never starts a first check and never takes new details. Returns queued, or a structured reason (not_allowed with retry_after, entitlement_required with pricing_url, unavailable, error). Purchases happen on the website only.

Input parameters:

- `subject_id` (string)

### `submit_approved_plan` (~137 tokens)

Queue the removal requests the person already approved

Requires OAuth and the 'submit_requests' permission. Without confirm: true it only previews which eligible listings would be queued (status preview) — show that list to the person and get a yes first. With confirm: true it queues removal requests for exactly those listings, using the approval the person already gave on the website and their paid plan. It cannot approve listings, pick new sites, or buy anything: approval_required and entitlement_required send the person to the website. A request is not a removal.

Input parameters:

- `confirm` (boolean): true only after the person has seen the preview and said yes.
- `subject_id` (string)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-myprivacyagent-public/api-mcp#diagnostics

## Score history

- 2026-09-28: 70
- 2026-09-27: 69
- 2026-09-26: 69
- 2026-09-25: 69
- 2026-09-24: 68
- 2026-09-23: 68
- 2026-09-22: 67
- 2026-09-21: 67
- 2026-09-20: 66
- 2026-09-19: 66
- 2026-09-18: 65
- 2026-09-17: 65

## Common questions

### What is the com.myprivacyagent/public MCP server?

com.myprivacyagent/public is an MCP server listed in the public MCP registry as com.myprivacyagent/public. Read-only opt-out guides, removal routes for 950+ data brokers, and privacy library search. This page covers its hosted endpoint (https://myprivacyagent.com/api/mcp).

### Is the com.myprivacyagent/public MCP server safe to use?

com.myprivacyagent/public 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 com.myprivacyagent/public MCP server expose?

com.myprivacyagent/public exposes 11 tools: get_opt_out_instructions, list_opt_out_guides, get_removal_route, search_privacy_library, get_service_overview, and 6 more. Their descriptions and schemas cost roughly 922 tokens of context every time the server is loaded.

### Does the com.myprivacyagent/public MCP server require authentication?

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

### Is the com.myprivacyagent/public MCP server still maintained?

com.myprivacyagent/public is still listed as active in the MCP registry. We last reached this channel on 28 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://myprivacyagent.com/api/mcp
- Repository: https://github.com/msanchezgrice/leak-check-me
- Changelog RSS feed: https://verifymcp.io/servers/com-myprivacyagent-public/api-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-myprivacyagent-public/api-mcp.json
- HTML version of this page: https://verifymcp.io/servers/com-myprivacyagent-public/api-mcp