Denied

Runtime Authorizations for Agents

[Pietro Valfrè @p_valfre]

https://t.co/hszgykeT6N

[Pietro Valfrè @p_valfre]

mcp is cool, but auth for mcp is cooler.

proud of providing it via FastMCP and @whataboutyou_ai

[Pietro Valfrè @p_valfre]

@ttommitt breaking down why we’re building @whataboutyou_ai

[Denied @denieddotdev]

🤝 Cloudflare Remote MCP with Eunomia Authorization

Combining Eunomia’s authorization with @Cloudflare Remote MCP enables contextual access to resources & tools within your remote server. Define who can access what based on their role and context.

This integration provides:
- Contextual access control for tools & resources
- Secure authentication with Cloudflare's OAuth
- Scalable solution for remote MCP servers

Explore the example:
🔗 https://t.co/27ezKLE3es

[Denied @denieddotdev]

GH example: https://t.co/1OOGcxyQxO

[Denied @denieddotdev]

🔐Role-based security meets RAG with Eunomia!

We built a system where different analysts only access information relevant to their roles - financial fraud specialists see financial data, media crime analysts get media insights, and directors access everything.

No more oversharing sensitive data. Security by design!

Built with @langchain and @huggingface datasets, Eunomia makes implementing secure RAG systems straightforward and reliable.

[Pietro Valfrè @p_valfre]

@whataboutyou_ai is the OS layer you need to tame Excessive Agency.

Excessive Agency is the vulnerability that enables damaging actions to be performed in response to unexpected, ambiguous outputs from an LLM, regardless of what is causing the LLM to malfunction.

[Denied @denieddotdev]

➡️➡️ https://t.co/Q6YJhTPFSG

[Denied @denieddotdev]

AI Agents with Parental Control using Eunomia + HumanLayer 👮‍♀️ 🚸 🚨

We're kicking off our authorization examples series with built-in parental control for any agent your children might interact with.

LLM-powered products designed for learning, play, and interaction with children are on the rise. Discussing history with a virtual teacher who answers any question is certainly more engaging than sitting through three hours of pre-made slides.

However, allowing children unrestricted interaction with AI agents has limitations. In child-focused AI products, authorizations are often necessary, and Eunomia is designed to help.

To enhance this, we integrated human checks, allowing parents to decide whether their children can access specific content. We used @humanlayer_dev for this.

Find the example link in the comments, built with @langchain , web search via @tavilyai and authorization powered by Eunomia from @whataboutyou_ai

[Pietro Valfrè @p_valfre]

We believe in this future.

The catalyst to reach it will be a layer that enables developers to control, with dynamic policies, what their agents can actually do.

This layer is called Eunomia, and is out now: https://t.co/qWd8rxQpxC

4/4

[Pietro Valfrè @p_valfre]

One way to let enterprise buy in this, is to integrate a proper Authz solution, such as @whataboutyou_ai

Curious to hear your thoughts @dsp_

[Pietro Valfrè @p_valfre]

I’m betting everything on that.

Agency = Authorisation in enterprise applications.

At @whataboutyou_ai we’re building the layer to control those authorisations.

@garrytan @dessaigne @sdianahu we just applied for X25. Hope to talk soon.

[Denied @denieddotdev]

We had a fantastic time at AI Tinkerers in Zurich!

Grateful to @generalcatalyst for co-hosting and to ETH Student Project House for providing such inspiring events.

Exciting projects, brilliant minds, and AI innovations, we’re already looking forward to the next one!

[Denied @denieddotdev]

@p_valfre @dsp_ Yepp, and we’re doing it from the EU!

[Pietro Valfrè @p_valfre]

I’m building in the AI space because of the amount of talented people who decided to do the same. 

We’re so grateful for those brilliant minds such as @dsp_ or @ClementDelangue who are indirectly shaping @whataboutyou_ai trajectory with their work!

[Denied @denieddotdev]

We're excited to announce the integration of MCP servers with Eunomia's server!

We believe this will save developers hours and headaches by streamlining access to data sources while enabling dynamic and granular DAG policies.

https://t.co/3pj2EsFOKW

[Denied @denieddotdev]

@AnthropicAI’s MCP + @whataboutyou_ai Eunomia = Standard and lightweight Data Governance. 

[Link to blog post in the comment]