MCP integration is the obvious next question. The language-level guardrails solve execution safety but the credential problem is still orthogonal. Even with Aegis, the agent needs API keys to call external services, and those keys still have to come from somewhere with some scope. Would be interesting to see how Aegis handles the "what does this agent actually have permission to do at the API layer" question vs just the "what code can it run" question.
Hey, yes Aegis has MCP support. MCP tools are declared in the syntax with the provider, and the transpiler handles the client calls, audit events, and capability checks automatically. There's also A2A (Agent-to-Agent) support for inter-agent communication. As for integration with something like claudecode/gpt/cursor, should be fairly straightforward, there's a full language spec and syntax reference in the docs folder that LLMs can use as context.
Sweet! Just read over the docs on github and pip install aegis-lang on your computer whenever you're ready. Any questions/comments/general feedback you may have feel free to reach out
MCP integration is the obvious next question. The language-level guardrails solve execution safety but the credential problem is still orthogonal. Even with Aegis, the agent needs API keys to call external services, and those keys still have to come from somewhere with some scope. Would be interesting to see how Aegis handles the "what does this agent actually have permission to do at the API layer" question vs just the "what code can it run" question.
So this prevents prompt injections?
Can this work with MCP servers or be integrated easily with Claudecode/other agents?
Hey, yes Aegis has MCP support. MCP tools are declared in the syntax with the provider, and the transpiler handles the client calls, audit events, and capability checks automatically. There's also A2A (Agent-to-Agent) support for inter-agent communication. As for integration with something like claudecode/gpt/cursor, should be fairly straightforward, there's a full language spec and syntax reference in the docs folder that LLMs can use as context.
Nice, I'm going to try this out.
Sweet! Just read over the docs on github and pip install aegis-lang on your computer whenever you're ready. Any questions/comments/general feedback you may have feel free to reach out
Interesting