Prompt Guard MCP Server

by robertoyanguas-ops Your server? Claim it

answering

Prompt Guard MCP is answering right now. Last checked 13 min ago. It exposes 2 tools.

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

Uptime history 68 hours of history

68 hours agonow

100.0%

Uptime 24h

92 of 92 checks

Tools

read from the server

210 ms

Response time

average over 24h

open, no key

Access

streamable-http

What changed 13

Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 14 October 2026. No other catalogue keeps this.

16 Oct 2 tools changed the parameters they ask for4 times that day get_agent_wallet_status, scan_prompt_injection

16 Oct 2 tool descriptions were rewritten get_agent_wallet_status, scan_prompt_injection

16 Oct a tool changed version

15 Oct 2 tool descriptions were rewritten get_agent_wallet_status, scan_prompt_injection

15 Oct 2 tools changed the parameters they ask for get_agent_wallet_status, scan_prompt_injection

14 Oct a tool description was rewritten scan_prompt_injection

14 Oct a tool changed the parameters it asks for scan_prompt_injection

and 2 more, back to 14 October 2026

Nothing serious here today

Today is the operative word: we check Prompt Guard MCP every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 13 min ago.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add prompt-guard-mcp --transport http https://prompt-guard-72343955726.us-central1.run.app/mcp/prompt-guard

~/Library/Application Support/Claude/claude_desktop_config.json

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

~/.codex/config.toml

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

.cursor/mcp.json

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

.vscode/mcp.json

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

Available tools 2

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

agent

get_agent_wallet_status

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.

scan

scan_prompt_injection

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.

Endpoints

URL	Transport	State	Latency	Checked
https://prompt-guard-72343955726.us-central1.run.app/mcp/prompt-guard	streamable-http	answering	191 ms	13 min ago

Alternatives to Prompt Guard MCP

same job, measured the same way

Email Guard MCP

by mlawsonking

Email safety for AI agents: scan inbound for prompt-injection/phishing + outbound for secret leaks.

73 installs/wk local only

isMalicious threat intelligence for AI agents

by ismalicious

Reputation of IPs, domains, URLs, hashes, emails and phones; CVE lookups; prompt-injection scans

87 installs/wk local only

Mails.ai — Agent Email

by mails

A real inbox for AI agents: send, receive and thread email, behind a prompt-injection firewall.

502 installs/wk answering

Mails.ai — Agent Email

by rolloutsai

A real inbox for AI agents: send, receive and thread email, behind a prompt-injection firewall.

local only

pylos-mcp

by adamvass

Email MCP server for Gmail, Outlook and any IMAP mailbox, hardened against prompt injection

1 476 installs/wk local only

Selectic

by selectic-ai

AI agent that calls, texts & emails businesses for you, then returns transcripts and replies.

29 installs/wk answering

Straelo Relay

by straelo

MCP tools for agents: web research, content extraction, email, DNS, and blockchain intelligence.

8 tools answering

Openhook

by openhook-dev

Webhook, email and DNS inboxes for AI agents to capture callbacks and test integrations.

29 tools answering

Prompt Guard MCP — questions

Answers built from our own checks of this server.

What can Prompt Guard MCP do?

It exposes 2 tools, read directly from the server on our last check. Among them: get_agent_wallet_status, scan_prompt_injection. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →

Is Prompt Guard MCP working right now?

We send a real MCP handshake every 15 minutes. Over the last 24 hours 92 of 92 checks got a reply (100.0%), average response time 210 ms. The bar chart above shows every period we have measured.

How do I connect Prompt Guard MCP?

Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.

Does Prompt Guard MCP need an API key?

No. Prompt Guard MCP completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 2 of them are readable on this page. This is what we observed, not what the docs claim.

How fast is Prompt Guard MCP?

It answers our handshake in 210 ms on average, which is faster than 59% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.