AISentinel MCP
An open-source MCP server providing security, control, and observability for AI agents. It runs as a policy enforcement layer in front of tool calls, evaluating YAML policies to block risks like prompt injection and data exfiltration, while logging decisions for audit trails compatible with the AI Trust Index.
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 1 GitHub star
What you can do with it
- Enforce pre-tool policy enforcement for AI agents
- Provide JSONL audit trails for agent decisions
- Protect against indirect prompt injection attacks
- Monitor and control agent runtime security
Source and maintenance
- Last repository push
- Latest release
- v1.0.7
- Maintenance checked
Packages and installation
Source-provided package data. Koskamo has not executed or live-probed this package.
https://github.com/Kabzhanov/AISentinel/releases/download/v1.0.6/aisentinel-sidecar-v1.0.6.mcpb
{
"transport": "stdio",
"fileSha256": "dfa85b72d14f11c295ae7d6f4ac60a3705198aa2c7954e01111a2e78d38a0c38",
"identifier": "https://github.com/Kabzhanov/AISentinel/releases/download/v1.0.6/aisentinel-sidecar-v1.0.6.mcpb",
"runtimeHint": "aisentinel-sidecar",
"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 AISentinel MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.