# Arcade — Runtime that brokers OAuth, executes MCP tools and audits every agent action against the user's own permissions. > Source: The Agents Index — https://theagentsindex.com/arcade-dev (structured, researched, re-verified) Arcade is an actions runtime that sits between AI agents and business systems, brokering OAuth, executing more than 8,000 pre-built MCP tools and recording every call. It runs on Arcade Cloud, in your own cloud, on-premises or air-gapped. **Best for:** Enterprise teams putting agents into production that must pass a security review | Fact | Value | | --- | --- | | Website | https://arcade.dev | | Category | Tool integrations & auth | | Open source | Partly | | Price | Free | | Price source | https://www.arcade.dev/pricing/ | | Price checked | 28 October 2026 | | MCP server | Yes | | API | Not stated | | Self-host | Yes | | Facts | 21 facts from 5 sources | | Facts checked | 28 October 2026 | Screenshot of Arcade: https://theagentsindex.com/img/1920/screenshots/arcade-dev.webp, captured 30 October 2026 **What we checked** - Pages last read: 28 October 2026 - Facts checked: 21 facts (From 5 sources) - AI answers: Named in 1 of 151 (Our October check) ## What we checked on Arcade ### How much it does unattended **Agent permissions** · Yes — Every call is evaluated at the moment of action against the intersection of the user's own permissions and the agent's scope, rather than a standing service account, and crossing either boundary stops the action. > Every agent action runs at the intersection of what the user can do and what the agent is allowed to do. Not a service account. Not a shared token. Evaluated per action, at runtime. > — https://www.arcade.dev/product/ · "Under the hood", Secure Agent Authorization section, checked 28 October 2026 ### Which models it runs on **Open models** · Yes — The vendor says any LLM works behind the runtime because it is model agnostic; it does not name specific open-weight models or a self-hosted inference endpoint anywhere read. > any agent client, including Claude, Cursor, ChatGPT, Copilot, or your own, and any LLM > — https://www.arcade.dev/ · FAQ, "Is Arcade compatible with existing AI development frameworks?", checked 28 October 2026 **Model choice** · Yes — The buyer chooses: the vendor describes itself as framework agnostic across LangChain, CrewAI, Mastra, Google ADK and OpenAI Agents, with any client and any LLM behind it. > Yes. Arcade is framework agnostic. Build with LangChain, LlamaIndex, Mastra, CrewAI, Pydantic, Google ADK, or OpenAI Agents. The same flexibility extends across the stack: any agent client > — https://www.arcade.dev/ · FAQ, "Is Arcade compatible with existing AI development frameworks?", checked 28 October 2026 ### Whose machine it runs on **Self-hosted** · Yes — The runtime can be deployed in the buyer's own cloud, a VPC, on-premises or fully air-gapped, and the docs publish a Helm chart for running the platform on your own Kubernetes cluster. > Yes. You can deploy the Arcade MCP runtime in your own cloud environment, a virtual private cloud, on-premises, or in a fully air-gapped environment. > — https://www.arcade.dev/ · FAQ, "Can I deploy Arcade on my own infrastructure?", checked 28 October 2026 **Open source** · Partly — The tool-building framework arcade-mcp is MIT-licensed on GitHub, but the vendor says only much of what it builds is open source, and the runtime platform itself is distributed as licensed images. > Much of what we build is open source, including the arcade-mcp framework for building and running MCP servers. > — https://www.arcade.dev/about/ · "Who we are", final paragraph, checked 28 October 2026 ### Building with it **SDK languages** · Yes — Python and JavaScript/TypeScript are the languages named: the runtime connects to an existing Python or JavaScript codebase, and the open-source tool framework is Python with a CLI. > Connect the Arcade runtime to your existing Python or JavaScript codebase and your agents start taking authorized actions right away. > — https://www.arcade.dev/ · FAQ, "Is Arcade compatible with existing AI development frameworks?", checked 28 October 2026 **Tracing and evals** · Yes — Tool executions and audit logs are visible in one control plane and exportable over OpenTelemetry, and the open-source framework ships arcade evals for scoring tool-call accuracy against real LLMs. > Evals run against real LLMs, so you test tool-call accuracy before you ship. > — https://www.arcade.dev/product/ · "Under the hood", Open source framework for custom tools, checked 28 October 2026 ### What it costs to run **How it meters** · Yes — Billing is a flat monthly platform fee plus two metered units, auth events and tool calls, each priced per event rather than per seat or per token. > Auth events at $0.10 each Tool calls at $0.01 each > — https://www.arcade.dev/pricing/ · Plan cards, Team column, bullets two and three, checked 28 October 2026 **Cost of one job** · Yes — On the cheapest paid plan a job is priced per action: 1,000 tool calls cost $10 and 1,000 user authorisations cost $100, on top of the $25 monthly platform fee. > $25 / month platform fee Auth events at $0.10 each Tool calls at $0.01 each > — https://www.arcade.dev/pricing/ · Plan cards, Team column, bullet list, checked 28 October 2026 **Free tier** · Yes — A standing Free plan can be self-served with no sales call and no card, carrying a monthly allowance of auth events and tool calls on the managed cloud. > $0 platform fee, no credit card required > — https://www.arcade.dev/pricing/ · Plan cards, Free column, first bullet, checked 28 October 2026 **MCP server** · Yes — Arcade federates its own, custom and third-party MCP servers into one endpoint that any MCP client can point at, and documents setup for ChatGPT, Claude, Cursor and Copilot clients. > Arcade federates your MCP servers, Arcade-hosted, custom, or third-party, into a single endpoint. Pick which tools each gateway exposes, then point any MCP client at one URL. > — https://www.arcade.dev/product/ · "Under the hood", MCP Gateway, checked 28 October 2026 **Bring your own key** · Yes — You can run the runtime in your own AWS, Azure or GCP account so data stays in your environment, and the open-source framework lets you supply your own access tokens when running standalone. > BYO Cloud Your AWS, Azure, or GCP. Data never leaves your environment. > — https://www.arcade.dev/product/ · "Your infrastructure, your rules", BYO Cloud card, checked 28 October 2026 ### Buying it for a team **A company can buy it** · Yes — An organisation can buy the Team plan self-serve or an Enterprise contract through sales, the latter bundling annual allowances, SLA support and a dedicated account team. > Platform pricing includes annual bundles of auth events and tool calls > — https://www.arcade.dev/pricing/ · Plan cards, Enterprise column, first bullet, checked 28 October 2026 **Seat model** · No — There is no seat price or seat minimum: the vendor bills a flat platform fee plus usage and says explicitly that it does not charge per seat. > Pay for what your agents actually do, not per seat. > — https://www.arcade.dev/pricing/ · Pricing page subheading under "Simple, scalable pricing", checked 28 October 2026 **Pooled budget** · Yes — Allowances are account-level pools of auth events and tool calls rather than per-person balances, and the vendor states plainly that it does not charge per seat. > Pay for what your agents actually do, not per seat. > — https://www.arcade.dev/pricing/ · Pricing page subheading under "Simple, scalable pricing", checked 28 October 2026 **Admin controls** · Yes — Policies are enforced outside the model through pre- and post-tool-call hooks an admin configures once, plus group-based tool access and rate limiting, so a team can block or redact actions per call. > Arcade supports pre- and post-tool-call hooks that let your team add custom policies without forking the runtime. Inspect every request before it runs and every response before it returns. Block sensitive actions, redact PII > — https://www.arcade.dev/ · FAQ, "Can I add custom policies to Arcade for AI agents?", checked 28 October 2026 **Audit log** · Yes — Each tool call records the agent, the user it acted for, the scope and the policy decision, and logs can be streamed to a customer's own SIEM over OpenTelemetry; the vendor says this is out of the box. > Every tool call records the agent, the user it acted on behalf of, the scope, and the policy decision applied. Logs stream to your SIEM via OpenTelemetry > — https://www.arcade.dev/product/ · "Central Control Plane", Fine-grained visibility and audit logs, checked 28 October 2026 **Single sign-on** · Partly — SSO is listed as an Enterprise entitlement on the pricing page, while the homepage claims it out of the box; neither page names SAML or OIDC, and the Free and Team cards do not mention it. > SSO, RBAC, audit logs, and private registry access > — https://www.arcade.dev/pricing/ · Plan cards, Enterprise column, final bullet, checked 28 October 2026 ### What happens to your code **Opt out of training** · Partly — Content pulled from connected third-party accounts is never used for model training, but the same policy says other collected information may be used to train the vendor's models with no opt-out described. > We do not use content retrieved from your connected third-party accounts, including Google Workspace, to develop, improve, or train any AI or machine learning model. > — https://www.arcade.dev/privacy-policy/ · Section 1, Information We Collect, opening paragraph, checked 28 October 2026 **Data residency** · Yes — Residency follows the deployment model a buyer picks: Arcade Cloud, the buyer's own AWS, Azure or GCP account, on-premises or air-gapped, with the vendor saying data never leaves the chosen environment. > Data residency tied to your deployment model > — https://www.arcade.dev/product/ · "Deployment & Compliance", Compliance bullet list, checked 28 October 2026 **Certifications** · Yes — The vendor states SOC 2 compliance and links a trust centre; it names no ISO 27001 certificate, and GDPR is addressed only as data-subject rights in its privacy policy rather than as an attestation. > SOC 2 compliant. SSO, RBAC, and full audit logs out of the box. > — https://www.arcade.dev/ · "Built to clear the security review", Compliance-ready card, checked 28 October 2026 ## Arcade price and terms **Terms** - Free plan: Yes — Free plan: $0 platform fee, no credit card, 2,000 auth events and 2,000 tool calls per month, Arcade Cloud only, community support on Discord and GitHub. **What needs a higher plan** - Enterprise: Single sign-on ## For AI agents - MCP server: Yes Pricing page as we captured it: https://theagentsindex.com/img/1920/screenshots/arcade-dev/pricing.webp, captured 30 October 2026 Read on https://www.arcade.dev/pricing/, 28 October 2026. ## Arcade alternatives - [Aident Loadout](https://theagentsindex.com/aident-loadout) · Free plan, then $9.90 a month: Managed capability layer that connects any AI agent to 1,000+ apps through one reusable, audited setup. - [Composio](https://theagentsindex.com/composio) · Free plan, then $29 a month: Managed OAuth, tool discovery and execution across 1,500+ apps for agents you already run. - [Nango](https://theagentsindex.com/nango) · Free plan, then $50 a month: Handles OAuth for 1,000+ APIs and runs your TypeScript integration functions, exposed to agents over MCP. All 3 publish a price. [All 3 alternatives](https://theagentsindex.com/arcade-dev/alternatives/) ## Questions about Arcade ### How much does Arcade cost? Arcade is free to use. From arcade.dev/pricing, checked 28 October 2026. ### Does Arcade have an API or an MCP server? It has an MCP server. ### Is Arcade open source, and can you host it yourself? Part of it is open source. You can host it yourself. ### What have we checked on Arcade? 21 facts, under these headings: How much it does unattended, which models it runs on, whose machine it runs on, building with it, what it costs to run, buying it for a team, what happens to your code. ### How do we check Arcade? We hold 21 facts on Arcade, quoted from 5 pages. Facts and price last checked 28 October 2026. How we check every listing: https://theagentsindex.com/methodology/ ## Sources and changes Last changed 30 October 2026 **Sources on arcade.dev** (5) - https://www.arcade.dev/pricing/, read 28 October 2026 - https://www.arcade.dev/, read 28 October 2026 - https://www.arcade.dev/product/, read 28 October 2026 - https://www.arcade.dev/about/, read 28 October 2026 - https://www.arcade.dev/privacy-policy/, read 28 October 2026 ## Is this yours? AI assistants like ChatGPT and Claude opened The Agents Index pages 2,746 times in September. Claim Arcade: https://theagentsindex.com/claim/arcade-dev Report an error if a fact is wrong: hello@theagentsindex.com, subject "Report an error: Arcade (arcade-dev)".