> ## 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.

# Welcome to Civic

> The security layer for AI agents. Connect to 95+ MCP servers with guardrails, audit logs, and instant revocation.

Your agent can read every email. Can you prove it only read what it was supposed to?

Civic is the security layer for AI agents — a control plane that makes tool-using agents safe, auditable, and compliant. Connect your agent to 95+ MCP servers and stay in control of every tool call.

<CardGroup cols={2}>
  <Card title="Start in Civic Chat" icon="sparkles" href="https://app.civic.com">
    Zero setup. Configure, audit, and revoke from your control plane.
  </Card>

  <Card title="Integrate your agent" icon="plug" href="/civic/quickstart">
    Connect via HTTP — LangChain, Vercel AI SDK, Anthropic SDK, and more.
  </Card>
</CardGroup>

## Four Pillars

Civic is built on four pillars: **Connectivity** to 95+ MCP servers, **Auditability** of every tool call, **Guardrails** through 1,000 guardrail rules, and **Revocability** via instant revocation at any granularity. Together they form a security layer that sits between your agent and the tools it uses — so you stay in control without slowing anything down.

<div style={{margin: '24px 0', borderRadius: '12px', overflow: 'hidden', border: '1px solid rgba(124, 59, 237, 0.25)'}}>
  <div style={{display: 'flex', alignItems: 'center', justifyContent: 'center', gap: '12px', padding: '16px 24px', background: 'rgba(124, 59, 237, 0.06)', borderBottom: '1px solid rgba(124, 59, 237, 0.15)'}}>
    <span style={{padding: '6px 14px', borderRadius: '6px', background: 'rgba(124, 59, 237, 0.12)', fontSize: '13px', fontWeight: '600'}}>Your AI Agent</span>
    <span style={{color: '#7C3BED', fontSize: '18px'}}>→</span>
    <span style={{padding: '6px 14px', borderRadius: '6px', background: 'rgba(124, 59, 237, 0.28)', fontSize: '13px', fontWeight: '700', color: '#7C3BED'}}>Civic Hub</span>
    <span style={{color: '#7C3BED', fontSize: '18px'}}>→</span>
    <span style={{padding: '6px 14px', borderRadius: '6px', background: 'rgba(124, 59, 237, 0.12)', fontSize: '13px', fontWeight: '600'}}>95+ MCP Servers</span>
  </div>

  <div style={{display: 'grid', gridTemplateColumns: 'repeat(4, 1fr)'}}>
    <div style={{padding: '20px', borderRight: '1px solid rgba(124, 59, 237, 0.15)', textAlign: 'center'}}>
      <div style={{fontSize: '22px', marginBottom: '8px'}}>🔌</div>
      <div style={{fontWeight: '600', fontSize: '13px', marginBottom: '4px'}}>Connectivity</div>
      <div style={{fontSize: '12px', opacity: 0.5}}>95+ MCP servers</div>
    </div>

    <div style={{padding: '20px', borderRight: '1px solid rgba(124, 59, 237, 0.15)', textAlign: 'center'}}>
      <div style={{fontSize: '22px', marginBottom: '8px'}}>📊</div>
      <div style={{fontWeight: '600', fontSize: '13px', marginBottom: '4px'}}>Auditability</div>
      <div style={{fontSize: '12px', opacity: 0.5}}>Every call logged</div>
    </div>

    <div style={{padding: '20px', borderRight: '1px solid rgba(124, 59, 237, 0.15)', textAlign: 'center'}}>
      <div style={{fontSize: '22px', marginBottom: '8px'}}>🛡️</div>
      <div style={{fontWeight: '600', fontSize: '13px', marginBottom: '4px'}}>Guardrails</div>
      <div style={{fontSize: '12px', opacity: 0.5}}>1,000 guardrail rules</div>
    </div>

    <div style={{padding: '20px', textAlign: 'center'}}>
      <div style={{fontSize: '22px', marginBottom: '8px'}}>⚡</div>
      <div style={{fontWeight: '600', fontSize: '13px', marginBottom: '4px'}}>Revocability</div>
      <div style={{fontSize: '12px', opacity: 0.5}}>Instant revocation</div>
    </div>
  </div>
</div>

### Connectivity

Connect to **95+ MCP servers** — Google Workspace, Slack, GitHub, databases, CRMs, and more. Civic handles OAuth, secrets, and authentication so your agent never touches raw credentials.

<Card title="Browse all 95+ MCP servers" icon="server" href="/civic/reference/servers">
  Google Calendar, Gmail, Sheets, Drive, Docs, Slack, GitHub, PostgreSQL, HubSpot, and 76 more
</Card>

### Auditability

Every tool call is logged: tool name, parameters, response, timestamp, and agent identity. Query your audit log in plain English via Civic Chat.

* **Aggregated summary**: "Show me what my agent did this week"
* **Line-by-line detail**: "Show every tool call from yesterday with timestamps"
* **CSV export**: Up to 5,000 lines per export

### Guardrails

With **1,000 guardrail rules**, set precise controls per tool, per server, or per toolkit. OAuth scope enforcement ensures agents get least-privilege access. Secrets — OAuth tokens, API keys, Bearer tokens — are stored in Civic and never exposed to the agent layer.

<Card title="Guardrails" icon="shield" href="/civic/concepts/guardrails">
  Block specific tools, enforce read-only scopes, set parameter presets the agent cannot override
</Card>

### Revocability

Revoke access instantly at any granularity — a single tool, a server connection, or an entire toolkit. Revocation is available via Civic Chat and the UI, not the API. An agent cannot revoke its own constraints.

<Card title="Revocation" icon="x" href="/civic/concepts/revocation">
  Kill switch at any level — from one tool to the entire toolkit
</Card>

## What Civic Protects

<CardGroup cols={2}>
  <Card title="Secret Management" icon="key" href="/civic/concepts/secret-management">
    OAuth tokens, API keys, and Bearer tokens stored in Civic. The agent never sees them — only the Hub can use them to make tool calls.
  </Card>

  <Card title="Audit Trail" icon="list-check" href="/civic/concepts/audit">
    Complete log of every tool call. Queryable via Civic Chat. CSV export up to 5,000 lines. Retained \~30 days.
  </Card>

  <Card title="Guardrails" icon="shield-halved" href="/civic/concepts/guardrails">
    Block tools, enforce read-only access, preset parameters. Works at the tool, server, and toolkit level.
  </Card>

  <Card title="Prompt Injection Defense" icon="lock" href="/civic/concepts/prompt-injection">
    Toolkit locking prevents a compromised agent from switching contexts or removing its own guardrails.
  </Card>
</CardGroup>

## Your Control Plane: Civic Chat

Civic Chat at [app.civic.com](https://app.civic.com) is not a demo interface — it's your control plane. Three agent modes:

* **Configurator Agent**: Set up toolkits, guardrails, and secrets via natural language
* **Audit Agent**: Query logs, get summaries, export CSV
* **Revocation Agent**: Instantly revoke access at any granularity

The endpoint is separated from the AI agent layer by design. Your production agents cannot call it.

<Card title="Civic Chat — Your Control Plane" icon="terminal" href="/civic/quickstart/civic-chat">
  Configure, audit, and revoke without writing code
</Card>

## Integrate Your Agent

Connect any MCP-compatible agent or client to `https://app.civic.com/hub/mcp`.

<CardGroup cols={2}>
  <Card title="LangChain / LangGraph" icon="code" href="/civic/recipes/langchain">
    Python agents with streamable HTTP transport
  </Card>

  <Card title="Vercel AI SDK" icon="code" href="/civic/recipes/vercel-ai-sdk">
    TypeScript agents and Next.js apps
  </Card>

  <Card title="Anthropic SDK" icon="code" href="/civic/recipes/anthropic">
    Direct Anthropic SDK with MCP beta header
  </Card>

  <Card title="Claude Desktop" icon="desktop" href="/civic/quickstart/clients/claude-desktop">
    Interactive client, 2-minute setup
  </Card>
</CardGroup>

## Pricing

Free trial: 10,000 credits, 14 days. Paid plans from \$25/month.

<Card title="Billing & Credits" icon="credit-card" href="/civic/billing">
  Credits consumed by tool calls and Civic Chat (Configurator, Audit, Revocation)
</Card>

## Need Help?

<CardGroup cols={2}>
  <Card title="Troubleshooting" icon="wrench" href="/civic/troubleshooting">
    Common setup issues and solutions
  </Card>

  <Card title="Developer Community" icon="slack" href="https://join.slack.com/t/civic-developers/shared_invite/zt-37tv9fyo7-aDT43mUjOFQwdQFmfZLTRw">
    Ask questions and get support
  </Card>
</CardGroup>