diff --git a/app/en/get-started/about-arcade/page.mdx b/app/en/get-started/about-arcade/page.mdx index 44a049a7a..633bd4fe0 100644 --- a/app/en/get-started/about-arcade/page.mdx +++ b/app/en/get-started/about-arcade/page.mdx @@ -1,6 +1,6 @@ --- -title: "How Arcade helps with Agent Authorization" -description: "Learn how Arcade helps with auth and tool calling" +title: "About Arcade: the enterprise-ready actions runtime for AI agents" +description: "Arcade is the enterprise-ready actions runtime for AI agents — enforce security on every action (agent authorization), execute reliably across any system, and govern agents centrally." --- import { Tabs } from "nextra/components"; @@ -8,6 +8,18 @@ import Image from "next/image"; # About Arcade +Arcade is the enterprise-ready actions runtime for AI agents. An agent isn't an agent if it can't take actions — and the moment an agent acts, three problems hit at once. Arcade solves all three at runtime, so teams ship production agents without rebuilding plumbing every time: + +- **Enforce — Agent Authorization:** Deploy agents your security team approves. Arcade handles OAuth and manages user tokens, API keys, and secrets, then enforces your existing IdP, DLP, SIEM, and compliance policies plus per-action authorization at runtime. +- **Execute — Agent-Optimized Tools:** Agents that work across every business system, with 7,500+ agent-optimized tools across 81 MCP servers, built for reliable execution at scale — not thin API wrappers. +- **Govern — Agent Lifecycle Governance:** Scale agents across the org from a central control plane: shared registry, version control, visibility filtering, and OpenTelemetry audit logs. + +Configure once and use any model, framework, and client. Deploy the first agent the same way you deploy the hundredth. + +The rest of this page focuses on the first pillar — **agent authorization** — which is where most agentic applications hit their first wall. + +## Why agent authorization matters + Applications that use models to perform tasks (_agentic applications_) commonly require access to sensitive data and services. Authentication complexities often hinder AI from performing tasks that require user-specific information, like what emails were recently received or what's coming up on a calendar. To retrieve this information, agentic applications need to be able to authenticate and authorize access to external services like Gmail or Google Calendar. diff --git a/app/en/get-started/agent-frameworks/google-adk/overview/page.mdx b/app/en/get-started/agent-frameworks/google-adk/overview/page.mdx index 7c8f6ed71..035de4f25 100644 --- a/app/en/get-started/agent-frameworks/google-adk/overview/page.mdx +++ b/app/en/get-started/agent-frameworks/google-adk/overview/page.mdx @@ -5,7 +5,7 @@ description: "Integrate Arcade tools with Google ADK agents" # Arcade with Google ADK -[Google ADK](https://github.com/google/adk-python/) is a modular framework for building and deploying AI agents. It's optimized for Gemini and the Google ecosystem. Arcade integrates with both the Python and TypeScript versions, giving your agents access to Gmail, GitHub, Slack, and 7,000+ other tools. +[Google ADK](https://github.com/google/adk-python/) is a modular framework for building and deploying AI agents. It's optimized for Gemini and the Google ecosystem. Arcade integrates with both the Python and TypeScript versions, giving your agents access to Gmail, GitHub, Slack, and 7,500+ other tools. ## Get started @@ -22,6 +22,6 @@ With Arcade and Google ADK, your agents can: - Post messages to Slack channels - Create GitHub issues and pull requests - Search the web and extract content -- Access 7,000+ other integrations +- Access 7,500+ other integrations Browse the [full MCP server catalog](/resources/integrations) to see all available tools. diff --git a/app/en/get-started/agent-frameworks/google-adk/setup-typescript/page.mdx b/app/en/get-started/agent-frameworks/google-adk/setup-typescript/page.mdx index 8dd07b528..a1cd9e664 100644 --- a/app/en/get-started/agent-frameworks/google-adk/setup-typescript/page.mdx +++ b/app/en/get-started/agent-frameworks/google-adk/setup-typescript/page.mdx @@ -7,7 +7,7 @@ import { Steps, Tabs, Callout } from "nextra/components"; # Setup Arcade with Google ADK (TypeScript) -[Google ADK for TypeScript](https://github.com/google/adk-js) provides a framework for building AI agents in TypeScript. Arcade's `@arcadeai/arcadejs` library provides the tools integration, allowing your agents to access Gmail, GitHub, Slack, and 7,000+ other services. +[Google ADK for TypeScript](https://github.com/google/adk-js) provides a framework for building AI agents in TypeScript. Arcade's `@arcadeai/arcadejs` library provides the tools integration, allowing your agents to access Gmail, GitHub, Slack, and 7,500+ other services. diff --git a/app/en/get-started/agent-frameworks/langchain/overview/page.mdx b/app/en/get-started/agent-frameworks/langchain/overview/page.mdx index fcd81cd90..4b81fe88b 100644 --- a/app/en/get-started/agent-frameworks/langchain/overview/page.mdx +++ b/app/en/get-started/agent-frameworks/langchain/overview/page.mdx @@ -5,7 +5,7 @@ description: "Integrate Arcade tools with LangChain agents" # Arcade with LangChain -[LangChain](https://www.langchain.com/) is a popular framework for building AI agents that abstracts much of the complexity of agent development. Arcade integrates with both the Python and JavaScript versions, giving your agents access to Gmail, GitHub, Slack, and 7,000+ other tools. +[LangChain](https://www.langchain.com/) is a popular framework for building AI agents that abstracts much of the complexity of agent development. Arcade integrates with both the Python and JavaScript versions, giving your agents access to Gmail, GitHub, Slack, and 7,500+ other tools. ## Get started @@ -22,7 +22,7 @@ With Arcade and LangChain, your agents can: - Post messages to Slack channels - Create GitHub issues and pull requests - Search the web and extract content -- Access 7,000+ other integrations +- Access 7,500+ other integrations Browse the [full MCP server catalog](/resources/integrations) to see all available tools. diff --git a/app/en/get-started/agent-frameworks/openai-agents/overview/page.mdx b/app/en/get-started/agent-frameworks/openai-agents/overview/page.mdx index a88de02ef..486489123 100644 --- a/app/en/get-started/agent-frameworks/openai-agents/overview/page.mdx +++ b/app/en/get-started/agent-frameworks/openai-agents/overview/page.mdx @@ -5,7 +5,7 @@ description: "Integrate Arcade tools with the OpenAI Agents SDK" # Arcade with OpenAI Agents -The [OpenAI Agents SDK](https://openai.github.io/openai-agents-python/) provides a framework for building AI agents. Arcade integrates with both the Python and JavaScript versions, giving your agents access to Gmail, GitHub, Slack, and 7,000+ other tools. +The [OpenAI Agents SDK](https://openai.github.io/openai-agents-python/) provides a framework for building AI agents. Arcade integrates with both the Python and JavaScript versions, giving your agents access to Gmail, GitHub, Slack, and 7,500+ other tools. ## Get started @@ -22,6 +22,6 @@ With Arcade and OpenAI Agents, your agents can: - Post messages to Slack channels - Create GitHub issues and pull requests - Search the web and extract content -- Access 7,000+ other integrations +- Access 7,500+ other integrations Browse the [full MCP server catalog](/resources/integrations) to see all available tools. diff --git a/app/en/home/landing-page.tsx b/app/en/home/landing-page.tsx index a1c87f643..f3310f473 100644 --- a/app/en/home/landing-page.tsx +++ b/app/en/home/landing-page.tsx @@ -229,7 +229,7 @@ export function LandingPage() { initial={{ opacity: 0, y: 20 }} transition={{ duration: ANIMATION_DURATION }} > - MCP Runtime for AI agents that get things done. + The enterprise-ready actions runtime for AI agents. - Arcade handles OAuth, manages user tokens, and gives you 7,000+ - pre-built integrations so your agents can take real action in - production. + Arcade handles OAuth and manages user tokens, enforces your + security policies on every action, executes reliably across 7,500+ + agent-optimized tools, and governs agents centrally — so your + agents take real action in production. - See all 7,000+ + See all 7,500+ @@ -574,27 +575,27 @@ export function LandingPage() { How Arcade Works

- Three core components that power your AI agents. + Three pillars that power AI agents in production.

diff --git a/app/en/home/page.mdx b/app/en/home/page.mdx index aa86f7fa6..dcc287593 100644 --- a/app/en/home/page.mdx +++ b/app/en/home/page.mdx @@ -1,6 +1,6 @@ --- title: "Arcade Docs" -description: "Guides, resources, sample agents, and references for Arcade auth providers and MCP servers for agents and developers." +description: "Arcade is the enterprise-ready actions runtime for AI agents. Guides, resources, sample agents, and references for agent authorization, agent-optimized tools (MCP servers), and agent lifecycle governance." --- import { LandingPage } from "./landing-page"; diff --git a/app/layout.tsx b/app/layout.tsx index f9275167f..2bd3723f7 100644 --- a/app/layout.tsx +++ b/app/layout.tsx @@ -50,7 +50,8 @@ export function generateMetadata() { default: "Arcade Docs", template: "%s | Arcade Docs", }, - description: "Arcade - AI platform for developers", + description: + "Arcade is the enterprise-ready actions runtime for AI agents — enforce your security policies on every action, execute reliably across any system, and govern agents centrally in production.", metadataBase: new URL("https://docs.arcade.dev"), manifest: "/site.webmanifest", icons: { diff --git a/public/llms.txt b/public/llms.txt index 33abf060b..6b34d2771 100644 --- a/public/llms.txt +++ b/public/llms.txt @@ -2,11 +2,11 @@ # Arcade -> Arcade is the only runtime for MCP +> Arcade is the enterprise-ready actions runtime for AI agents. -As the MCP runtime, Arcade is the only one able to deliver secure agent authorization, high-accuracy tools, and centralized governance. Deploy multi-user AI agents that take actions across any system with granular permissions and complete visibility. No complex infrastructure required. Ship faster and scale with control. +Arcade is the enterprise-ready actions runtime for AI agents. We enforce your security policies on every action, execute reliably across any system, and govern agents centrally in production. Configure once and use any model, framework, and client — deploy the first agent the same way you deploy the hundredth. -Arcade delivers three core capabilities: Deploy agents even your security team will love with authorization-first architecture. Unlock highest accuracy actions across all MCP tools with agent-optimized integrations and the Arcade TDK. Maintain centralized control over production MCP without slowing down AI development. Access 1000s of pre-built MCP servers or bring your own, with unified governance across all tools. +Arcade delivers three capabilities. Enforce (Agent Authorization): deploy agents your security team approves — Arcade handles OAuth and manages user tokens, API keys, and secrets, then enforces your existing IdP, DLP, SIEM, and compliance policies plus per-action authorization at runtime. Execute (Agent-Optimized Tools): the largest catalog of agent-optimized tools — 7,500+ across 81 MCP servers, built for reliable execution at scale, not thin API wrappers. Govern (Agent Lifecycle Governance): a central control plane with a shared registry, version control, visibility filtering, and OpenTelemetry audit logs. ## Getting Started diff --git a/scripts/generate-llmstxt.ts b/scripts/generate-llmstxt.ts index 2cf3cf32e..2798ae084 100644 --- a/scripts/generate-llmstxt.ts +++ b/scripts/generate-llmstxt.ts @@ -354,14 +354,14 @@ function generateLlmsTxt( // Header lines.push("# Arcade"); lines.push(""); - lines.push("> Arcade is the only runtime for MCP"); + lines.push("> Arcade is the enterprise-ready actions runtime for AI agents."); lines.push(""); lines.push( - "As the MCP runtime, Arcade is the only one able to deliver secure agent authorization, high-accuracy tools, and centralized governance. Deploy multi-user AI agents that take actions across any system with granular permissions and complete visibility. No complex infrastructure required. Ship faster and scale with control." + "Arcade is the enterprise-ready actions runtime for AI agents. We enforce your security policies on every action, execute reliably across any system, and govern agents centrally in production. Configure once and use any model, framework, and client — deploy the first agent the same way you deploy the hundredth." ); lines.push(""); lines.push( - "Arcade delivers three core capabilities: Deploy agents even your security team will love with authorization-first architecture. Unlock highest accuracy actions across all MCP tools with agent-optimized integrations and the Arcade TDK. Maintain centralized control over production MCP without slowing down AI development. Access 1000s of pre-built MCP servers or bring your own, with unified governance across all tools." + "Arcade delivers three capabilities. Enforce (Agent Authorization): deploy agents your security team approves — Arcade handles OAuth and manages user tokens, API keys, and secrets, then enforces your existing IdP, DLP, SIEM, and compliance policies plus per-action authorization at runtime. Execute (Agent-Optimized Tools): the largest catalog of agent-optimized tools — 7,500+ across 81 MCP servers, built for reliable execution at scale, not thin API wrappers. Govern (Agent Lifecycle Governance): a central control plane with a shared registry, version control, visibility filtering, and OpenTelemetry audit logs." ); lines.push("");