Top SitesArcade: The MCP Runtime for Production AI Agents

Machine Readiness

Stored receipt and evidence

Overall

16

Readable

55

Callable

0

Commerce

0

Payment

0

Machine Access

Inspect the site's MCP endpoint

Open MCP explorer

DialtoneApp can scan the stored discovery files for this domain, try the MCP initialize handshake, and show the raw protocol transcript.

Purchase boundary

read only

Control boundary

unknown

Payment rails

None

Payment providers

None

Payment methods

None

Payment protocols

None

Payment assets

None

Payment networks

None

Capabilities

None

Verified payment surface

No

Crypto only

No

Readable docs

robots, llms

Products

0

Variants

0

Priced variants

0

Currencies

0

Offers

0

Priced offers

0

Priced actions

0

Samples

Offer samples

No stored offer samples.

Samples

Action samples

No stored action samples.

Samples

Product samples

No stored product samples.

Document

robots.txt

Open robots.txt
User-agent: *
Allow: /
Sitemap: https://www.arcade.dev/sitemap-index.xml

Document

llms.txt

Open llms.txt
# Arcade

> The MCP runtime delivering secure agent authorization, highly reliable tools, and agent lifecycle governance for multi-user AI agents at scale.

Arcade lets you deploy multi-user AI agents that take actions across any system with granular permissions and complete visibility — no complex infrastructure required.

## Key Capabilities

- **Agent Authorization**: Multi-user, per-action authorization evaluated at runtime — intersection of what the agent is allowed to do AND what the user is allowed to do. Integrates with existing OAuth/IDP flows, manages full token lifecycle, and keeps credentials isolated from the LLM.
- **Agent-Optimized Tools**: 1000s of MCP tools designed for agents to take actions, not just wrap APIs. Arcade translates natural language intent into precise API calls. Includes parallelized execution, automatic failover, and intelligent retries.
- **Agent Lifecycle Governance**: Centralized control plane for all tools and agents — shared discovery, version control, fine-grained audit logs (OTel-compatible), and visibility filtering so agents only see tools their user is permitted to invoke.

## Docs

- [Create an agent](https://docs.arcade.dev/en/get-started/quickstarts/call-tool-agent): Build an AI agent that calls Arcade tools
- [Tool calling from your custom agent](https://docs.arcade.dev/en/get-started/agent-frameworks): Integrate Arcade tools into LangChain, OpenAI Agents, CrewAI, Vercel AI, Google ADK, Mastra, and more
- [Create MCP servers with managed auth](https://docs.arcade.dev/en/guides/create-tools/tool-basics/build-mcp-server): Build and deploy custom MCP servers with Arcade's managed OAuth and authorization
- [Add user authorization to your tools](https://docs.arcade.dev/en/home/build-tools/create-a-tool-with-auth): Add OAuth-backed user authorization to your MCP tools
- [Create MCP gateways](https://docs.arcade.dev/en/guides/mcp-gateways): Federate tools from multiple MCP servers into a single URL for your agents and apps
- [Use tools from MCP clients](https://docs.arcade.dev/en/get-started/quickstarts/call-tool-client): Connect Arcade tools to Cursor, Claude Desktop, VS Code, and other MCP-compatible clients

## Resources

- [Pre-built integrations](https://docs.arcade.dev/en/resources/integrations): GitHub, Slack, Gmail, Google Sheets, Jira, Notion, Salesforce, and more
- [API reference](https://docs.arcade.dev/en/references/api)
- [Sample applications](https://docs.arcade.dev/en/resources/examples)

Document

llms-full.txt

Not stored for this site.