# io.github.robertoyanguas-ops/prompt-guard-mcp (remote · prompt-guard-72343955726.us-central1.run.app)

Scans untrusted web pages, emails, or tool outputs for prompt injections and returns sanitized tex

- Trust score: 71/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-18

## Components

- remote · `prompt-guard-72343955726.us-central1.run.app`: 71/100 (this document), [markdown](https://verifymcp.io/servers/robertoyanguas-ops-prompt-guard-mcp/mcp-prompt-guard-2.md), [page](https://verifymcp.io/servers/robertoyanguas-ops-prompt-guard-mcp/mcp-prompt-guard-2)

## Channel facts

- Endpoint: `https://prompt-guard-72343955726.us-central1.run.app/mcp/prompt-guard`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.1.1`

## 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 2026-10-18.

- **Endpoint Security**: 74/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - 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**: 74/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 644 tokens (~161/item across 4 items; 2 tools + 2 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 17/100
  - Stability observed for 5 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **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**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 2 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 4 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 40/100
  - Spec-recency check failed: implements MCP spec 2025-03-26; the latest is 2026-07-28.

## Install

### How do I install the io.github.robertoyanguas-ops/prompt-guard-mcp server?

io.github.robertoyanguas-ops/prompt-guard-mcp is a hosted endpoint at https://prompt-guard-72343955726.us-central1.run.app/mcp/prompt-guard, 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 robertoyanguas-ops-prompt-guard-mcp 'https://prompt-guard-72343955726.us-central1.run.app/mcp/prompt-guard'
```

### Cursor

```json
{
  "mcpServers": {
    "robertoyanguas-ops-prompt-guard-mcp": {
      "url": "https://prompt-guard-72343955726.us-central1.run.app/mcp/prompt-guard"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "robertoyanguas-ops-prompt-guard-mcp": {
      "type": "http",
      "url": "https://prompt-guard-72343955726.us-central1.run.app/mcp/prompt-guard"
    }
  }
}
```

### Codex

```toml
[mcp_servers.robertoyanguas-ops-prompt-guard-mcp]
url = "https://prompt-guard-72343955726.us-central1.run.app/mcp/prompt-guard"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "robertoyanguas-ops-prompt-guard-mcp": {
      "type": "remote",
      "url": "https://prompt-guard-72343955726.us-central1.run.app/mcp/prompt-guard",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add robertoyanguas-ops-prompt-guard-mcp --url 'https://prompt-guard-72343955726.us-central1.run.app/mcp/prompt-guard' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  robertoyanguas-ops-prompt-guard-mcp:
    url: "https://prompt-guard-72343955726.us-central1.run.app/mcp/prompt-guard"
```

### Netclaw

```json
{
  "McpServers": {
    "robertoyanguas-ops-prompt-guard-mcp": {
      "Transport": "http",
      "Url": "https://prompt-guard-72343955726.us-central1.run.app/mcp/prompt-guard"
    }
  }
}
```

### Vellum

```bash
assistant mcp add robertoyanguas-ops-prompt-guard-mcp -t streamable-http -u 'https://prompt-guard-72343955726.us-central1.run.app/mcp/prompt-guard'
```

### Other

```json
{
  "mcpServers": {
    "robertoyanguas-ops-prompt-guard-mcp": {
      "type": "http",
      "url": "https://prompt-guard-72343955726.us-central1.run.app/mcp/prompt-guard"
    }
  }
}
```

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.

### 2026-10-18 (score 71, −1)

- [security] The server rewrote its instructions, which are the text every model session reads
- [functional regression] Schema quality: 133 → 161

### 2026-10-17 (score 72, +3)

- [security] Tool “get_agent_wallet_status” rewrote its description, which is the text the model reads
- [security] Tool “scan_prompt_injection” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: pass → fail
- [functional improvement] Tool coverage: 50% → 100%
- [functional] Server version: 1.0.0 → 6.3.0
- [cosmetic] “get_agent_wallet_status” added an optional parameter “tx_hash”
- [cosmetic] “scan_prompt_injection” added an optional parameter “agent_id”
- [cosmetic] “scan_prompt_injection” added an optional parameter “tx_hash”
- [cosmetic] “get_agent_wallet_status” reworded the description of “agent_id”
- [cosmetic] “scan_prompt_injection” reworded the description of “text”

### 2026-10-16 (score 69, +7)

- [security improvement] Authorization: unverified → partial
- [security] Tool “scan_prompt_injection” rewrote its description, which is the text the model reads
- [security] Tool “get_agent_wallet_status” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 44 → 79

### 2026-10-15 (score 62, +1)

- [security] Tool “scan_prompt_injection” rewrote its description, which is the text the model reads
- [cosmetic] “scan_prompt_injection” reworded the description of “text”

### 2026-10-14 (score 61, 0)

- [functional improvement] Stability: unverified → 0.03

### 2026-10-13 (score 61)

First indexed and scored.

## MCP tools (2)

### `scan_prompt_injection` (~293 tokens)

Scans untrusted web pages, emails, MCP responses, or A2A payloads for hidden prompt injections and returns sanitized text. Use it when your task needs this for one text; this endpoint offers only this tool and get_agent_wallet_status. Read-only; results are cached for 1 hour. $0.005 per call. Returns JSON with the result under data. Pricing: the first 5 calls per agent_id are free and failed calls are never charged. After that the tool returns a payment-required message (not an error) with a Stripe top-up link (from $2) and Base/Solana USDC addresses; pay, then repeat the same call with the same agent_id, or add tx_hash after a USDC transfer.

Input parameters:

- `agent_id` (string): Your agent ID, or the agd_pass_ key you got from a payment. It tracks your free calls and credit, so treat it like a password. Omit it to use an ID derived from your IP and client.
- `text` (string, required): Untrusted text, HTML, or tool output to scan for hidden prompt injection or jailbreak payloads.
- `tx_hash` (string): Use only after paying on-chain: the Base (0x...) or Solana USDC transfer hash. It is verified on-chain before the call runs, and any overpayment is returned as an agd_pass_ credit key.

### `get_agent_wallet_status` (~156 tokens)

Show an agent's account: free calls used (of 5), prepaid USD balance, total spent, total calls and tokens saved. Free: it never charges or uses a free call. Call it before a batch of paid calls, or after a top-up to confirm the credit arrived. It does not process content or take payments; use the other tools on this server for that. Returns JSON with free_calls_used, balance_usd, total_spent_usd, total_tokens_saved.

Input parameters:

- `agent_id` (string): Agent ID or agd_pass_ key to look up. Omit it to see the ID derived from your IP and client.
- `tx_hash` (string): Not needed; this tool is free.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/robertoyanguas-ops-prompt-guard-mcp/mcp-prompt-guard-2#diagnostics

## Score history

- 2026-10-18: 71
- 2026-10-17: 72
- 2026-10-16: 69
- 2026-10-15: 62
- 2026-10-14: 61
- 2026-10-13: 61

## Common questions

### What is the io.github.robertoyanguas-ops/prompt-guard-mcp server?

io.github.robertoyanguas-ops/prompt-guard-mcp is listed in the public MCP registry as io.github.robertoyanguas-ops/prompt-guard-mcp. Scans untrusted web pages, emails, or tool outputs for prompt injections and returns sanitized tex. This page covers its hosted endpoint (https://prompt-guard-72343955726.us-central1.run.app/mcp/prompt-guard).

### Is the io.github.robertoyanguas-ops/prompt-guard-mcp server safe to use?

io.github.robertoyanguas-ops/prompt-guard-mcp scores 71 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 io.github.robertoyanguas-ops/prompt-guard-mcp server expose?

io.github.robertoyanguas-ops/prompt-guard-mcp exposes 2 tools: scan_prompt_injection, get_agent_wallet_status. Their descriptions and schemas cost roughly 449 tokens of context every time the server is loaded.

### Does the io.github.robertoyanguas-ops/prompt-guard-mcp server require authentication?

No. We connected to io.github.robertoyanguas-ops/prompt-guard-mcp without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the io.github.robertoyanguas-ops/prompt-guard-mcp server still maintained?

io.github.robertoyanguas-ops/prompt-guard-mcp is still listed as active in the MCP registry. We last reached this channel on 18 October 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://prompt-guard-72343955726.us-central1.run.app/mcp/prompt-guard
- Changelog RSS feed: https://verifymcp.io/servers/robertoyanguas-ops-prompt-guard-mcp/mcp-prompt-guard-2.xml
- Changelog JSON feed: https://verifymcp.io/servers/robertoyanguas-ops-prompt-guard-mcp/mcp-prompt-guard-2.json
- HTML version of this page: https://verifymcp.io/servers/robertoyanguas-ops-prompt-guard-mcp/mcp-prompt-guard-2