> ## Documentation Index
> Fetch the complete documentation index at: https://docs.civic.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Civic Labs

> Where Civic explores ideas in digital identity, agentic AI, and authorization

Here you'll find a suite of experiments and tools, some just getting started, some ready to test, all open to feedback and community input.

Each project is presented as a **flask**, representing different stages of experimental development. [Learn more about flask status →](/labs/flask-status).

Flasks are standalone services, libraries or tools, that can be used independently or together to build more complex applications.

Explore the flasks below or [get in touch](/labs/feedback) if you want to contribute, try things early, or shape what comes next.

## 🚀 Getting Started

Want to try out these experiments? [Get started here](/labs/private/getting-started).

## 💬 Feedback & Contribution

We're building in the open and love community input. [Learn how to contribute](/labs/feedback).

## 🧪 Flasks

Our current experiments focus on Model Context Protocol (MCP) tools and AI security. These tools help developers build safer, more controlled AI applications with proper identity and authorization.

<CardGroup cols={2}>
  <Card title="MCP Hub" icon="server" href="/labs/projects/mcp-hub">
    A hosted MCP Manager unifying and orchstrating multiple MCP servers, focusing on auth and security
  </Card>

  <Card title="Guardrail Proxy" icon="shield-halved" href="/labs/projects/guardrail-proxy">
    Wrap any MCP server in a configurable and flexible security layer
  </Card>

  <Card title="Bodyguard" icon="shield-virus" href="/labs/projects/bodyguard">
    LLM-based threat detection for prompts and tool calls
  </Card>

  <Card title="Pass-through Proxy" icon="arrows-left-right" href="/labs/projects/passthrough-proxy">
    Middleware hook system for MCP servers that powers guardrails and more
  </Card>

  <Card title="Civic Knowledge" icon="brain" href="/labs/projects/civic-knowledge">
    AI assistant for the optimisation of internal operations and processes
  </Card>
</CardGroup>

<Frame caption="MCP Hub Components" href="/labs/projects/mcp-hub">
  <img src="https://mintcdn.com/civic/O4L8MDyrwt6gcvaS/images/labs/hub-components.png?fit=max&auto=format&n=O4L8MDyrwt6gcvaS&q=85&s=4aae169774ca9cd6450d50ceb03d1702" alt="" width="897" height="581" data-path="images/labs/hub-components.png" />
</Frame>

## 📚 Concepts & Architecture

Understanding the building blocks behind our experiments.

<CardGroup cols={3}>
  <Card title="Model Context Protocol" icon="plug" href="/labs/concepts/mcp">
    What is MCP and why it matters for AI applications
  </Card>

  <Card title="Guardrails" icon="traffic-light" href="/labs/concepts/guardrails">
    Guardrails as a protection layer
  </Card>

  <Card title="Prompt Injection" icon="syringe" href="/labs/concepts/prompt-injection">
    Understanding prompt injection attacks & LLM safety
  </Card>

  <Card title="Auth Strategies" icon="key" href="/labs/concepts/auth-strategies">
    OAuth2, granular permissions, and consent
  </Card>

  <Card title="Hooks" icon="zap" href="/labs/concepts/hooks">
    A middleware layer around MCP APIs
  </Card>

  <Card title="RAG" icon="magnifying-glass" href="/labs/concepts/rag">
    Retrieval strategies for LLMs
  </Card>
</CardGroup>