io.github.lucaslubi/fidacy-mcp
fidacy-ai-agent-firewall
AI Agent Firewall. Enforce signed authority before consequential actions. Free API key required.
alive probed 2026-10-14
12tools
3.5ktokens in Claude Opus 5.5
3.7ktokens in Claude Code
1.8 %of a 200k context window
2.1ko200k_base estimate
234 msto initialize
42 msto list tools
- Run it
- npx -y @fidacy/mcp@0.19.0 (stdio, probed in a container with the network off)
- Host
- npmjs.com
- Reports itself as
- fidacy-ai-agent-firewall 0.19.0
- Capabilities
- tools
- Instructions
- 1 822 characters
- Claude count
- Claude Opus 5.5, measured 2026-10-14. Counted again when the tool definitions change. Method.
- Repository
- https://github.com/lucaslubi/fidacy-mcp
- Registry
- active, updated 2026-09-05 · registry entry
- Reachable
- 1 of the last 1 probe
Most expensive tools
| Tool | Tokens (o200k) | Share of this server |
|---|---|---|
| request_payment | 352 | 17 % |
| assess_action | 351 | 17 % |
| anchor_artifact | 343 | 17 % |
| list_decisions | 142 | 7 % |
| spend_summary | 141 | 7 % |
Badge and feed
[](https://mcpcost.ulehla.dev/s/io.github.lucaslubi/fidacy-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.