
InsAIts - AI Communication Security Monitor
io.github.Nomadu27Published by GitHub account Nomadu27v3.1.1Updated Oct 24, 2026
Runtime AI-to-AI security monitor. 23 anomaly types, OWASP MCP Top 10 coverage.
Overview
A local runtime security monitor for AI-to-AI communication, flagging anomalies and covering the OWASP MCP Top 10.
- What you can do
- Monitors AI-to-AI communication at runtime and reports detected anomalies to the assistant using it, with 23 anomaly types described and coverage of the OWASP MCP Top 10. The manifest lists no individual tools, so the exact operations are not documented in the supplied material. An optional API key enables cloud features, while a free tier works without it.
- When to use it
- Consider it when you want a local check on traffic between AI agents or MCP components and want anomalies surfaced during a session. It is aimed at security-conscious setups rather than general-purpose tasks.
- Requirements
- Runs as a local process on the user's machine via uvx from the PyPI package insa-its, so a Python environment with uv is needed. Desktop only. An optional INSAITS_API_KEY enables cloud features; the free tier works without it. No authentication is declared.
Installation
In SourceWeft
- Open InsAIts - AI Communication Security Monitor in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
This repository has no README.
Tools
0Version history
1- v3.1.1LatestSep 16, 2026
Score
25% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.
- License10 pts
Declare a license in the repository or the registry entry.