Security and IT teams that need to limit what AI agents can access on company computers.
claude mcp add csl-core -- uv run --with 'csl-core[mcp]' csl-core-mcpThird party software. By copying, downloading or installing it you accept the Academy legal notice: you are responsible for reviewing its code and permissions before use.
Loading the file...
A policy engine that finds the AI agents on a machine and what each one can reach, writes a policy for each agent and enforces it outside the model. The policies are checked with Z3 and TLA+, and the code that connects agents to them is tested against bypass attempts. The model never sees the rules.
Security and IT teams that need to limit what AI agents can access on company computers. A policy engine that finds the AI agents on a machine and what each one can reach, writes a policy for each agent and enforces it outside the model. The policies are checked with Z3 and TLA+, and the code that connects agents to them is tested against bypass attempts. The model never sees the rules.
Run this in your terminal: claude mcp add csl-core -- uv run --with 'csl-core[mcp]' csl-core-mcp
Yes. The code is on GitHub (Chimera-Protocol/csl-core) under the Apache-2.0 licence.
It passed our automatic scan for credential theft, hidden instructions and risky install commands. Third party open source software. Sabemos AI does not maintain it. Check the code and permissions before you connect it to company data.