Home / Directory / Agents & orchestration / AI agent tool integrations / Arcade.dev
Arcade.dev
AI agent runtime founded in February 2024 by a former Okta executive that handles user sign-in, permissions, and tool calls so agents act on a user's behalf.
Teams shipping agents into companies with strict security rules that need per-user sign-in, permission checks, and audit logs on every action.
Hobby projects that only need a few public APIs, or teams that want flat pricing regardless of how many users connect.
Verdict
Arcade.dev is worth using for teams whose agents must take real actions in business systems under each user's own permissions. Its security focus and deployment options suit enterprise buyers. Simple projects may not need this much control.
Score Breakdown
How Arcade.dev scores in the categories that matter to its buyers.
Pricing
Arcade.dev publishes a free plan and a $25 Team plan billed per sign-in event and tool call, with no seat fees.
| Plan | Price | What stands out |
|---|---|---|
| Free | $0 | 2,000 auth events and 2,000 tool calls a month |
| Team | $25 / month platform fee | Auth events $0.10 each; tool calls $0.01 each |
| Enterprise | Custom | Dedicated forward-deployed engineer and account team |
The Field at a Glance
How Arcade.dev compares with other AI agent tool integrations vendors we reviewed, by Overall Score and relative typical engagement cost.
Arcade.dev scores 7.9 in AI agent tool integrations, under Composio (8.1) and Nango (8.0), and ahead of Paragon (7.7). Relative cost lands lower for this subcategory.
Use-case matrix
| Use case | Fit | Notes |
|---|---|---|
| Agent acts as the user | Strong | Delegated authorization against your identity provider. |
| Audit trail | Strong | Each action records the agent, user, and system. |
| Deployment choice | Strong | Cloud, VPC, on-premises, or air-gapped. |
| Tool catalog | Strong | More than 8,000 permission-aware tools. |
| Pricing at scale | Mixed | Auth events cost $0.10 each on Team. |
| Simple public-API use | Mixed | Built for governed actions more than quick prototypes. |
Who it’s for
Good fit
- Enterprise agent teams
- Security-conscious SaaS companies
- Teams building agents on MCP
Poor fit
- Hobby projects
- Teams with very high user sign-in volume on a budget
- Agents that only read public data
Review Excerpts
Below are excerpts from public reviews. Our team scoured public reviews, forums, and chat rooms to get a balanced view of customers' experience with this company. Paid reviews and pay-for-play sites such as Clutch were excluded.
“The runtime layer from Arcade makes MCP enterprise-ready. Connects to identity providers, enforces agent authorization, and enables real actions in Google, Slack, and Salesforce.”
“By using Arcade, we're able to authenticate users' Twitter/LinkedIn accounts without worrying about refresh tokens, broken auth, or any of the other hassle that comes with setting up auth connections.”
Arcade.dev's Team plan charges $0.10 for every auth event and $0.01 for every tool call on top of the $25 monthly fee, so costs rise with each user who connects an account.
Company Facts
- Founded
- February 2024 (TechCrunch)
- Funding
- $12M from Laude Ventures, March 2025 (TechCrunch)
- Founders
- Alex Salazar (CEO) and Sam Partee (CTO) (Arcade.dev)
- Website
- arcade.dev
Key Leadership
Alex Salazar
Co-founder and CEO
Methodology
This page is an independent evaluation of Arcade.dev for buyers comparing options in AI agent tool integrations. AI Industry Reviews accepts no sponsorships, advertising, or pay-for-placement fees. Arcade.dev did not pay for this review.
What we scored
The headline number is an Overall Score on a 0-10 scale. Eight criteria sit under it in two groups.
- Buyer outcomes (for AI agent tool integrations)
- Per-user authorization
- Deployment options
- Tool catalog
- Cost at high user volume
- Company & commercial
- Innovation & product leadership
- Project management & communication
- Pricing
- Contract fairness
Pricing measures whether the price looks fair for the value delivered, including packaging and renewal friction that show up in real buying cycles.
Score Composition
| Input | Weight | What it covers |
|---|---|---|
| Reviews | 40% | A proprietary read of what practitioners say about likes, complaints, and day-to-day use, including public review sites, forums, and private chat rooms. Paid reviews and pay-for-play sites such as Clutch are out of scope. |
| Product | 35% | Hands-on look at screens and workflows. |
| Pricing | 15% | Whether the price looks fair for what you get. |
| Docs & training | 10% | Docs, tutorials, and training material. |
How we balanced the evidence
The Overall Score is the simple average of the eight criteria. Recommendation language follows that score and the fit pattern described above.
Scope
Arcade.dev is graded here as AI agent tool integrations. Criteria scores can move as more review volume and product checks are added.