PlainRouter is answering right now. Last checked 13 min ago. It exposes 4 tools. Last commit 17 Sep 2026.
Inspect an approved ad account and first-party signal health, then propose policy-gated actions.
Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 27 August 2026. No other catalogue keeps this.
Over the last week it answered 98.1% of our checks. We check every 15 minutes, so you hear about the next outage within the hour — not from your users.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 13 min ago.
claude mcp add mcp --transport http https://plainrouter.com/mcp
{
"mcpServers": {
"mcp": {
"url": "https://plainrouter.com/mcp"
}
}
}
[mcp_servers.mcp]
url = "https://plainrouter.com/mcp"
{
"mcpServers": {
"mcp": {
"url": "https://plainrouter.com/mcp"
}
}
}
{
"mcpServers": {
"mcp": {
"url": "https://plainrouter.com/mcp"
}
}
}
This server publishes 1 more address. The block above uses the one we reach during checks; the full list is under Endpoints below, and the author may intend a particular one for your client.
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
get_account_state
get_performance
get_signal_health
validate_sandbox_event
Tools this server used to expose. Anything built against them stopped working on the day they went.
launcher.batch_status
launcher.draft_batch
launcher.execute_batch
launcher.preview_batch
duplicate-ad-with-creative
get_arrivals_comparison
get-creative-library
get_install_instructions
propose-actions
revoke_grant
show_spend_cap_approval
upload-asset
verify_signal_ingestion
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://plainrouter.com/mcp | streamable-http | answering | 344 ms | 13 min ago |
| https://plainrouter.com/mcp/sandbox | streamable-http | answering | 476 ms | 13 min ago |
Intent-bound action authorization for AI agents: policy, human approval, and a signed audit trail.
Gate AI agent actions behind a consent policy with human approval via Telegram. Fail-closed.
Amazon Seller Central and Ads data for AI: sales, profit, ads, inventory, health, gated actions.
SEO agent: GSC, keyword, backlink and AI-visibility insights, plus approval-gated site actions
A local receipt and approval gate for AI agent sessions. The agent can act, but it cannot sign.
Free agent identity and signed US supplier-payment decisions. Inspect first; verify portable proof.
Pre-spend firewall for AI agents. Approves, blocks, flags transactions against policy rules.
Local-first MCP security scanner and CLI for AI-generated applications.
Answers built from our own checks of this server.