Security & Testing

myprivacyagent.com

Provides tools to find and execute opt-out and removal instructions for people-search and data-broker sites to protect privacy.

1 endpoint11 known toolsFirst detected September 21, 2026Last detected September 21, 2026

ENDPOINT 1

https://myprivacyagent.com/api/mcp

No auth detected

MCP server metadata

Name: my-privacy-agent-public
Version: 2026.9.16

Capabilities

tools.listChanged

Server instructions

Public, read-only reference tools from My Privacy Agent (myprivacyagent.com): opt-out guides for people-search and data-broker sites, the documented removal route for 950+ sites, and a search over the public library. These tools never look anyone up and hold no personal data. If the person wants their own exposure checked, send them to https://myprivacyagent.com/check; if they already found a listing, send them to https://myprivacyagent.com/remove-listing. Never put a person's name, address, phone, or email into a URL. Cite the guide URL when you use its steps. A request is not a removal: do not say a listing is removed until a recheck shows it. Do not create accounts, start checkout, or file requests on a person's behalf.

Known tools 11

get_opt_out_instructions

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.

Inferred read-only

list_opt_out_guides

Summaries of every published step-by-step guide (slug, domain, category, method, difficulty, turnaround, support level).

Inferred read-only

get_removal_route

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.

Potential side effects

search_privacy_library

Search My Privacy Agent's published articles, opt-out guides, help answers, and plan facts.

Inferred read-only

get_service_overview

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.

Inferred read-only

list_my_subjects

Requires OAuth.

Inferred read-only

get_my_report

Requires OAuth and the 'share_results' permission for the subject.

Inferred read-only

list_my_cases

Requires OAuth and the 'share_results' permission.

Inferred read-only

get_case_status

Requires OAuth and the 'share_results' permission.

Inferred read-only

request_recheck

Requires OAuth and the 'run_check' permission.

Inferred read-only

submit_approved_plan

Requires OAuth and the 'submit_requests' permission.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.my-privacy-agent-public]
url = "https://myprivacyagent.com/api/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "my-privacy-agent-public": {
      "type": "http",
      "url": "https://myprivacyagent.com/api/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: my-privacy-agent-public
Remote MCP URL: https://myprivacyagent.com/api/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "my-privacy-agent-public": {
      "url": "https://myprivacyagent.com/api/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "my-privacy-agent-public": {
      "type": "http",
      "url": "https://myprivacyagent.com/api/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "my-privacy-agent-public",
  "transport": "streamable-http",
  "url": "https://myprivacyagent.com/api/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Loading Trust v2 evidence…

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.