mcpcost

io.github.robertoyanguas-ops/prompt-guard-mcp

prompt-guard-mcp

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

alive probed 2026-10-15 · HTTP 200

2tools
283tokens in Claude Opus 5.5
313tokens in Claude Code
0.1 %of a 200k context window
146o200k_base estimate
158 msto initialize
56 msto list tools
Endpoint
https://prompt-guard-72343955726.us-central1.run.app/mcp/prompt-guard (streamable-http)
Host
prompt-guard-72343955726.us-central1.run.app
Protocol
2025-03-26
Reports itself as
prompt-guard-mcp 1.0.0
Capabilities
prompts, resources, tools
Instructions
none
Claude count
Claude Opus 5.5, measured 2026-10-14. Counted again when the tool definitions change. Method.
Registry
active, updated 2026-10-13 · registry entry
Reachable
3 of the last 3 probes

Most expensive tools

ToolTokens (o200k)Share of this server
scan_prompt_injection10270 %
get_agent_wallet_status4430 %

History

We add a row when the result changes. A server with no change keeps its last row.

ProbedResultInitToolsClaudeo200k
2026-10-15 11:07alive183 ms2283146
2026-10-14 19:20alive3.5 s2283146
2026-10-13 11:26alive158 ms2270135

Badge and feed

mcpcost: alive

[![mcpcost](https://mcpcost.ulehla.dev/badge/io.github.robertoyanguas-ops/prompt-guard-mcp.svg)](https://mcpcost.ulehla.dev/s/io.github.robertoyanguas-ops/prompt-guard-mcp)

An entry for every probe that changed the result, the tool count or the token cost: Atom feed. Add it to a feed reader or a Slack RSS app to hear when the server stops answering or its tool set grows.