Chimera-Protocol/csl-core

v0.3.0-alpha Feature

This release adds 3 notable features for engineering teams evaluating rollout.

Published 3mo MCP Developer Tools

✓ No known CVEs patched

✓ No known CVEs patched in this version

Topics

agent-framework ai-governance ai-safety deterministic-ai formal-verification hallucination-prevention

+10 more

langchain llm-safety mcp mcp-server neuro-symbolic policy-as-code state-machine tla-plus tla-plus-model-checking z3

Summary

AI summary

CSL-Core now includes a built-in Model Context Protocol (MCP) server with policy verification, simulation, explanation, and scaffolding tools.

Full changelog

CSL-Core now ships a built-in Model Context Protocol server. Write, verify, and enforce AI safety policies directly from your AI assistant.

MCP Server with 4 tools:
- verify_policy — Z3 formal verification via MCP
- simulate_policy — Runtime enforcement against JSON inputs
- explain_policy — Human-readable policy summary
- scaffold_policy — Generate CSL templates from plain English
5 bundled example policies as MCP resources (hello_world, age_verification, banking_guard, agent_tool_guard, dao_treasury_guard)
CSL syntax reference prompt for AI assistants
Optional dependency: pip install "csl-core[mcp]"

{
  "mcpServers": {
    "csl-core": {
      "command": "uv",
      "args": ["run", "--with", "csl-core[mcp]", "csl-core-mcp"]
    }
  }
}

pip install csl-core --upgrade --pre

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

Share this release

Track Chimera-Protocol/csl-core

Get notified when new releases ship.

About Chimera-Protocol/csl-core

Deterministic AI safety policy engine with Z3 formal verification. Write, verify, and enforce machine-verifiable constraints for AI agents via MCP.