Aguara MCP
A local security scanner for AI agents that reviews untrusted agent content before acting on it. It runs in-process to check for prompt injection, credential exposure, and unsafe install commands without network access or LLM calls.
Package and access
Local package with source-attributed installation metadata. Koskamo does not execute packages during review.
Checks and signals
Each line is separate evidence, not a trust score.
- Popularity 4 GitHub stars
What you can do with it
- Review MCP server configurations before installation
- Inspect tool descriptions for prompt injection
- Check READMEs for unsafe install commands
- Detect data exfiltration attempts in skills
Source and maintenance
- Last repository push
- Latest release
- v0.8.0
- Maintenance checked
Packages and installation
Source-provided package data. Koskamo has not executed or live-probed this package.
https://github.com/garagon/aguara-mcp/releases/download/v0.2.0/aguara-mcp.mcpb
{
"transport": "stdio",
"fileSha256": "59a187da83dd165b568a0d0f5df92a9510822dabba169d599822c54f34e5c1d0",
"identifier": "https://github.com/garagon/aguara-mcp/releases/download/v0.2.0/aguara-mcp.mcpb",
"registryType": "mcpb"
}Tools
Reported by the attributed source; not independently observed by Koskamo.
Maintenance history
Public check and source-refresh events. Editorial and ownership records remain private.
- · repository · passed · metadata changed · updated
- · backfill · recorded · Pre-expansion baseline; unobserved rich metadata remains unknown
Let your agent find its tools
Find servers like Aguara MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.