# PlainRouter (remote · plainrouter.com)

Inspect an approved ad account and first-party signal health, then propose policy-gated actions.

- Trust score: 87/100 (high trust)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-20

## Components

- remote · `plainrouter.com`: 80/100, [markdown](https://verifymcp.io/servers/com-plainrouter-mcp/mcp-sandbox.md), [page](https://verifymcp.io/servers/com-plainrouter-mcp/mcp-sandbox)
- remote · `plainrouter.com`: 87/100 (this document), [markdown](https://verifymcp.io/servers/com-plainrouter-mcp/plainrouter.md), [page](https://verifymcp.io/servers/com-plainrouter-mcp/plainrouter)

## Channel facts

- Endpoint: `https://plainrouter.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.4.0`

## 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 2026-09-20.

- **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**: 86/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (excellent).
  - Tool/resource definitions use about 1143 tokens (~95/item across 12 items; 10 tools + 2 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 50/100
  - Stability check failed: schema churn in the 25 days we've observed: 4 tool removals, 0 breaking changes, 0 auth/transport breaks, 2 additions.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **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; "revoke_grant" implies "revoke" and declares no destructiveHint at all, which the MCP spec reads as destructive by default.
  - 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).
  - Supports UI / widget rendering.

## Install

### How do I install the PlainRouter MCP server?

PlainRouter is a hosted endpoint at https://plainrouter.com/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-plainrouter-mcp 'https://plainrouter.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-plainrouter-mcp": {
      "url": "https://plainrouter.com/mcp"
    }
  }
}
```

### VS Code

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

### Codex

```toml
[mcp_servers.com-plainrouter-mcp]
url = "https://plainrouter.com/mcp"
```

### opencode

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

### OpenClaw

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

### Hermes

```yaml
mcp_servers:
  com-plainrouter-mcp:
    url: "https://plainrouter.com/mcp"
```

### Netclaw

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

### Vellum

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

### Other

```json
{
  "mcpServers": {
    "com-plainrouter-mcp": {
      "type": "http",
      "url": "https://plainrouter.com/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.

### 2026-09-20 (score 87, +1)

- [functional regression] Schema quality: 82 → 95
- [cosmetic] “get-creative-library” added an optional parameter “account_id”
- [cosmetic] “upload-asset” added an optional parameter “account_id”
- [cosmetic] “propose-actions” added an optional parameter “account_id”
- [cosmetic] “get_signal_health” added an optional parameter “account_id”
- [cosmetic] “get_performance” added an optional parameter “account_id”
- [cosmetic] “get_account_state” added an optional parameter “account_id”
- [cosmetic] “duplicate-ad-with-creative” added an optional parameter “account_id”

### 2026-09-18 (score 86, +1)

No change was recorded against any check on this day. Stability & Change Management went from 40 to 43.

### 2026-09-17 (score 85, 0)

- [functional] MCP protocol: Implements a current MCP spec version (2026-07-28).
- [functional] MCP protocol version: 2025-11-25 → 2026-07-28
- [functional] Server version: 0.3.2 → 0.4.0

### 2026-09-16 (score 85, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37.

### 2026-09-14 (score 84, +1)

No change was recorded against any check on this day. Stability & Change Management went from 27 to 30.

### 2026-09-13 (score 83, 0)

- [security] Tool “get_performance” rewrote its description, which is the text the model reads

### 2026-09-12 (score 83, +1)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] The server changed its declared name: PlainRouter → Plainrouter
- [security] Tool “propose-actions” rewrote its description, which is the text the model reads
- [security] Tool “get_signal_health” rewrote its description, which is the text the model reads

### 2026-09-11 (score 82, −1)

- [functional] Destructive annotations: pass → 0
- [functional] New tool “revoke_grant”
- [cosmetic] “get_signal_health” added an optional parameter “days”

## MCP tools (10)

### `get_account_state` (~51 tokens)

Get Account State

Return the authorized advertising account, workspace, connection, Signal destination, and currently available read-only capabilities.

Input parameters:

- `account_id` (integer): Advertising account ID. Required when the workspace has more than one active account.

### `get_signal_health` (~96 tokens)

Get Signal Health

Diagnostic view of first-party event flow, Meta delivery outcomes, match quality, and reconciliation gaps from Plainrouter stored measurements. Not admissible evidence for spend-affecting proposals. Does not call the Marketing API.

Input parameters:

- `account_id` (integer): Advertising account ID. Required when the workspace has more than one active account.
- `days` (integer): Trailing window in days. One of 7, 30, 90.

### `get_performance` (~79 tokens)

Get Performance

Admissible proposal evidence comparing Meta-reported conversions with gateway-verified accepted conversions, plus the latest stored daily Meta spend and delivery metrics.

Input parameters:

- `account_id` (integer): Advertising account ID. Required when the workspace has more than one active account.
- `days` (integer): Number of reporting days to compare, from 1 to 90.

### `verify_signal_ingestion` (~51 tokens)

Verify Signal Ingestion

Verify server-side Signal ingestion by writing one idempotent, identity-free modeled event for the authorized workspace. This confirms ledger receipt but does not count as real arrival evidence or complete onboarding. No spend capability.

### `propose-actions` (~189 tokens)

Propose Actions

Propose a batch of budget, status, upload, or creative-duplication actions for the approved ad account. Budget and status proposals are recommendations only; their execution is disabled in this release. Supported JPEG/PNG uploads and paused ad copies require human approval and workspace policy checks. Suggest-only approval never executes them.

Input parameters:

- `account_id` (integer): Advertising account ID. Required when the workspace has more than one active account.
- `actions` (array, required): One to twenty-five typed action objects.
- `evidence` (array, required): One to three approved server-re-read evidence citations; action-bound sources require action_index.
- `idempotency_key` (string, required): Stable key reused when retrying the same proposal.
- `rationale` (string, required): Why this batch should be considered together.
- `target_source` (string, required): How the target was selected. Human-supplied establishes selection only, never current target state.

### `get-creative-library` (~101 tokens)

Get Creative Library

Return Meta image and video assets with the ads and last-30-day performance historically associated with each asset.

Input parameters:

- `account_id` (integer): Advertising account ID. Required when the workspace has more than one active account.
- `asset_type` (string): Limit results to images or videos. Defaults to all.
- `cursor` (string): Opaque Meta cursor returned by a previous call.
- `limit` (integer): Maximum assets returned per requested asset type.

### `upload-asset` (~184 tokens)

Upload Asset

Stage a JPEG/PNG image and submit a canonical upload action through the policy and approval gate.

Input parameters:

- `account_id` (integer): Advertising account ID. Required when the workspace has more than one active account.
- `asset_type` (string, required): The creative asset type. M2 supports images only.
- `content_base64` (string): Raw base64 content for image uploads. Do not use a data URI prefix.
- `filename` (string, required): Bare filename with a matching .jpg, .jpeg, or .png extension, such as spring-hero.jpg. Path separators are rejected: send a name, not a path. The asset is never written to a filesystem path built fro…
- `idempotency_key` (string, required): Stable key reused when retrying this upload proposal.
- `rationale` (string, required): Why this asset should be added to the creative library.

### `duplicate-ad-with-creative` (~142 tokens)

Duplicate Ad With Creative

Submit a canonical proposal to duplicate a source Meta ad with a different creative asset. Approved copies are always created PAUSED.

Input parameters:

- `account_id` (integer): Advertising account ID. Required when the workspace has more than one active account.
- `asset_id` (string, required): Asset ID returned by upload-asset or get-creative-library.
- `idempotency_key` (string, required): Stable key reused when retrying this duplicate proposal.
- `name_suffix` (string): Optional suffix for the copied ad name.
- `rationale` (string, required): Why this new creative variant should be created.
- `source_ad` (string, required): Numeric Meta ID of the ad to duplicate.

### `show_spend_cap_approval` (~26 tokens)

Show Spend Cap Approval

Render the static spend-cap approval preview card. Reads and writes nothing.

### `revoke_grant` (~56 tokens)

Revoke Grant

Revoke an active workspace grant. The caller must hold the revoke_grant scope in the same workspace or be the human delegator of the granted agent.

Input parameters:

- `grant_id` (string, required): The ULID of the grant to revoke.

## Diagnostics

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

## Score history

- 2026-09-20: 87
- 2026-09-19: 86
- 2026-09-18: 86
- 2026-09-17: 85
- 2026-09-16: 85
- 2026-09-15: 84
- 2026-09-14: 84
- 2026-09-13: 83
- 2026-09-12: 83
- 2026-09-11: 82
- 2026-09-10: 83
- 2026-09-09: 88
- 2026-09-08: 87
- 2026-09-07: 87
- 2026-09-06: 86
- 2026-09-05: 86
- 2026-09-04: 85
- 2026-09-03: 85
- 2026-09-02: 84
- 2026-09-01: 84
- 2026-08-31: 83
- 2026-08-30: 83
- 2026-08-29: 82
- 2026-08-28: 82
- 2026-08-27: 82
- 2026-08-26: 79

## Common questions

### What is the PlainRouter MCP server?

PlainRouter is an MCP server listed in the public MCP registry as com.plainrouter/mcp. Inspect an approved ad account and first-party signal health, then propose policy-gated actions. This page covers its hosted endpoint (https://plainrouter.com/mcp).

### Is the PlainRouter MCP server safe to use?

PlainRouter scores 87 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 PlainRouter MCP server expose?

PlainRouter exposes 10 tools: get_account_state, get_signal_health, get_performance, verify_signal_ingestion, propose-actions, and 5 more. Their descriptions and schemas cost roughly 975 tokens of context every time the server is loaded.

### Does the PlainRouter MCP server require authentication?

Yes. PlainRouter 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 PlainRouter MCP server still maintained?

PlainRouter is still listed as active in the MCP registry. We last reached this channel on 20 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://plainrouter.com/mcp
- Repository: https://github.com/plainrouter/sdk
- Website: https://plainrouter.com/
- Changelog RSS feed: https://verifymcp.io/servers/com-plainrouter-mcp/plainrouter.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-plainrouter-mcp/plainrouter.json
- HTML version of this page: https://verifymcp.io/servers/com-plainrouter-mcp/plainrouter