io.github.mlawsonking/agent-firewall-mcp
agent-firewall
Input/output safety for AI agents: known-pattern injection and obfuscation scan, URL/IP, secrets.
alive probed 2026-10-19
5tools
≈ 650tokens, estimate
≈ 0.3 %of Claude's 200k window
0.5×the median server
438 msto initialize
28 msto list tools
- Run it
- npx -y agent-firewall-mcp@1.3.0 (stdio, probed in a container with the network off)
- Host
- npmjs.com
- Reports itself as
- agent-firewall 1.3.0
- Capabilities
- tools
- Instructions
- none
- 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.
- Repository
- https://github.com/mlawsonking/MCP
- Registry
- active, updated 2026-08-10 · 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_content | 146 | 22 % |
| check_url | 136 | 21 % |
| check_password | 127 | 20 % |
| scan_secrets | 124 | 19 % |
| check_ip | 117 | 18 % |
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.