Chimera-Protocol/csl-core
Deterministic safety layer for AI agents. Z3-verified policy enforcement.
Compiles `.csl` policy files into Z3-verified artifacts that enforce constraints deterministically at runtime, outside the LLM — making rules immune to prompt injection and adversarial attacks. Provides CLI tools (verify, simulate, REPL) for policy development and testing, plus LangChain integration to wrap agent tools with automatic enforcement and context injection. Also ships as an MCP server for policy authoring directly within Claude/Cursor.
Available on PyPI.
Stars
6
Forks
4
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 10, 2026
Monthly downloads
195
Commits (30d)
0
Dependencies
2
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/mcp/Chimera-Protocol/csl-core"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related servers
AndrewAltimit/template-repo
Agent orchestration & security template featuring MCP tool building, agent2agent workflows,...
agentralabs/agentic-contract
Policy engine for AI agents — enforceable rules, risk limits, approval gates, obligation...
portofcontext/pctx
pctx is the execution layer for agentic tool calls. It auto-converts agent tools and MCP servers...
behrensd/mcpwall
Deterministic security proxy for MCP tool calls — iptables for MCP
postralai/masquerade
The Privacy Firewall for LLMs