# ai-agent-firewall

> ai-agent-firewall, an MCP server by fidacy.com, listed from the official MCP registry. Indexed, not reviewed: facts and our own checks, no score or ranking. Every agent action watched, every money-moving one gated, every verdict independently verifiable.

- Canonical: https://www.anchorterminal.com/tools/fidacy-ai-agent-firewall
- Markdown: https://www.anchorterminal.com/tools/fidacy-ai-agent-firewall.md (~450 tokens)
- Slim: https://www.anchorterminal.com/tools/fidacy-ai-agent-firewall.min.md (~380 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/tools/fidacy-ai-agent-firewall.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- Updated: 2026-10-05

# ai-agent-firewall

> Indexed, not reviewed: facts from the official MCP registry and our own checks. No score, grade or rank, and not in the rankings until the panel reviews it. How the index works: https://www.anchorterminal.com/indexed/

- Kind: MCP server, by fidacy.com (https://fidacy.com)
- Listed because: It's published in the registry under fidacy.com, a namespace the registry only gives to whoever proves they control that domain.
- What the official MCP registry says: Every agent action watched, every money-moving one gated, every verdict independently verifiable.

## Facts

- MCP registry: `com.fidacy/ai-agent-firewall` 0.7.1
- Package: npm `@fidacy/mcp` (stdio)
- Source: https://github.com/lucaslubi/fidacy-mcp
- npm downloads a week: 405
- GitHub stars: 1
- Registry entry updated: 2026-07-29

- JSON: https://www.anchorterminal.com/api/v1/tools/fidacy-ai-agent-firewall.json
- Being indexed says nothing about quality, and nobody can pay for it. Ask for a review: https://www.anchorterminal.com/builders/#claiming