dev.agentdiet/prompt-guard
AgentDiet A2A Indirect Prompt-Injection & Jailbreak Firewall
Scans untrusted web pages, emails, MCP responses, or A2A payloads for hidden prompt injections an.
alive probed 2026-10-19 · HTTP 200
2tools
≈ 703tokens, estimate
≈ 0.4 %of Claude's 200k window
0.5×the median server
1.5 sto initialize
787 msto list tools
- Endpoint
- https://prompt-guard.agentdiet.dev/mcp (streamable-http)
- Host
- prompt-guard.agentdiet.dev
- Protocol
- 2025-11-25
- Reports itself as
- prompt-guard-mcp 7.0.16
- Capabilities
- prompts, resources, tools
- Instructions
- 406 characters
- Of a 1M window
- ≈ <0.1 % of a 1M context window, estimate
- Claude count
- The count_tokens endpoint refused the tool schemas: invalid x-api-key. The estimate stands in.
- Website
- https://prompt-guard.agentdiet.dev
- Registry
- active, updated 2026-10-19 · registry entry
- Reachable
- 1 of the last 1 probe
Most expensive tools
Estimates with the o200k_base tokenizer.
| Tool | o200k estimate | Share of this server |
|---|---|---|
| scan_prompt_injection | 459 | 65 % |
| get_agent_wallet_status | 244 | 35 % |
Same tool set as 1 other server
These registry entries have the same tool names and the same schema sizes.
- io.github.robertoyanguas-ops/prompt-guard-mcp prompt-guard-72343955726.us-central1.run.app
Badge for the README
The result of the latest probe, the tool count and the token cost. The feed has an entry for every probe that changed them.
A mail when this server changes
Stops answering, comes back, tool set or cost changes. One confirmation mail first, a stop link in every mail.
For the publisher
- The Anthropic count_tokens endpoint refused the tool schemas (invalid x-api-key). A client that validates schemas can refuse them too.
Fixed something? Probe it now, with the same steps as the daily run. This page updates with the next daily run.