agent · AI Agents Platform
Arcade
26 fields evidenced · 29 with no public information. Every value below links to the document it came from and the date we checked it.
Trust gap
How this is scoredRuntime governance
2/3
Are scope, spend, and authority enforced while the agent runs?
Scored from 2 evidenced field(s): runtime_governance, permission_scopes. Automated score; capped at 2 pending review.
Audit trail
1/3
Is there a tamper-evident record of what it actually did?
Scored from 1 evidenced field(s): audit_trail. Automated score; capped at 2 pending review.
How this gap gets closed →Compliance
1/3
Are compliance obligations attached per engagement?
Scored from 1 evidenced field(s): compliance_certs. Automated score; capped at 2 pending review.
How this gap gets closed →Outcome settlement
1/3
Does payment depend on a verified result?
Scored from 1 evidenced field(s): outcome_based_pricing. Automated score; capped at 2 pending review.
How this gap gets closed →Insurance & indemnity
unscored
Can the deployment be insured, and is the customer indemnified?
Assurance
- Insurance available
- no public informationarcade-ai.com · checked Aug 1, 2026 · source did not state this
- Insurance carriers
- no public informationarcade-ai.com · checked Aug 1, 2026 · source did not state this
- Coverage limits
- no public informationarcade-ai.com · checked Aug 1, 2026 · source did not state this
- Indemnification
- no public informationarcade-ai.com · checked Aug 1, 2026 · source did not state this
- Liability cap
- no public informationarcade-ai.com · checked Aug 1, 2026 · source did not state this
- Audit trail
- You can answer that for every action, every time, without slowing down the teams shipping agents. One place to set policy, one place to audit.
“You can answer that for every action, every time, without slowing down the teams shipping agents. One place to set policy, one place to audit.”
arcade-ai.com · checked Aug 1, 2026 - Tamper-evident log
- no public informationarcade-ai.com · checked Aug 1, 2026 · source did not state this
- Explainability
- What did the agent do, on behalf of which user, in which system?
“What did the agent do, on behalf of which user, in which system?”
arcade-ai.com · checked Aug 1, 2026 - Runtime governance
- Arcade enforces permissions through your existing OAuth and identity provider flows. Agents act on behalf of the authenticated user, never through broad service accounts. Every action runs at the intersection of what the user can do and what the agent is scoped to do. Cross either line and the action stops.
“Arcade enforces permissions through your existing OAuth and identity provider flows. Agents act on behalf of the authenticated user, never through broad service accounts. Every action runs at the intersection of what the user can do and what the agent is scoped to do. Cross either line and the action stops.”
arcade-ai.com · checked Aug 1, 2026 - Permission scopes
- Agents act on behalf of the authenticated user, never through broad service accounts. Every action runs at the intersection of what the user can do and what the agent is scoped to do.
“Agents act on behalf of the authenticated user, never through broad service accounts. Every action runs at the intersection of what the user can do and what the agent is scoped to do.”
arcade-ai.com · checked Aug 1, 2026 - Compliance certifications
- Compliance-ready SOC 2 compliant. SSO, RBAC, and full audit logs out of the box.
“Compliance-ready SOC 2 compliant. SSO, RBAC, and full audit logs out of the box.”
arcade-ai.com · checked Aug 1, 2026 - Regulatory alignment
- Compliance-ready SOC 2 compliant. SSO, RBAC, and full audit logs out of the box.
“Compliance-ready SOC 2 compliant. SSO, RBAC, and full audit logs out of the box.”
arcade-ai.com · checked Aug 1, 2026 - Outcome-based pricing
- Priced by usage.
“Priced by usage.”
arcade-ai.com · checked Aug 1, 2026 - Settlement mechanism
- no public informationarcade-ai.com · checked Aug 1, 2026 · source did not state this
- Dispute process
- no public informationarcade-ai.com · checked Aug 1, 2026 · source did not state this
- SLA terms
- no public informationarcade-ai.com · checked Aug 1, 2026 · source did not state this
- Evaluation coverage
- no public informationarcade-ai.com · checked Aug 1, 2026 · source did not state this
Agency
- Autonomy level
- no public informationarcade-ai.com · checked Aug 1, 2026 · source did not state this
- Human oversight
- Agents act on behalf of the authenticated user, never through broad service accounts. Every action runs at the intersection of what the user can do and what the agent is scoped to do. Cross either line and the action stops.
“Agents act on behalf of the authenticated user, never through broad service accounts. Every action runs at the intersection of what the user can do and what the agent is scoped to do. Cross either line and the action stops.”
arcade-ai.com · checked Aug 1, 2026 - Goal complexity
- no public informationarcade-ai.com · checked Aug 1, 2026 · source did not state this
- Action space
- The runtime between your agents and every system they need to reach. Auth, tools, and governance in one layer. So your agents sail through security review.
“The runtime between your agents and every system they need to reach. Auth, tools, and governance in one layer. So your agents sail through security review.”
arcade-ai.com · checked Aug 1, 2026 - Operating environment
- AI agents using Arcade access a catalog of pre-built Model Context Protocol tools for major systems like Google Workspace, Slack, Microsoft, and Salesforce.
“AI agents using Arcade access a catalog of pre-built Model Context Protocol tools for major systems like Google Workspace, Slack, Microsoft, and Salesforce.”
arcade-ai.com · checked Aug 1, 2026 - Initiative
- no public informationarcade-ai.com · checked Aug 1, 2026 · source did not state this
Safety
- Safety evaluations
- no public informationarcade-ai.com · checked Aug 1, 2026 · source did not state this
- Red teaming
- no public informationarcade-ai.com · checked Aug 1, 2026 · source did not state this
- Safety policy
- Compliance-ready SOC 2 compliant. SSO, RBAC, and full audit logs out of the box.
“Compliance-ready SOC 2 compliant. SSO, RBAC, and full audit logs out of the box.”
arcade-ai.com · checked Aug 1, 2026 - Usage restrictions
- Cross either line and the action stops.
“Cross either line and the action stops.”
arcade-ai.com · checked Aug 1, 2026 - Model or system card
- no public informationarcade-ai.com · checked Aug 1, 2026 · source did not state this
- Incident reporting
- no public informationarcade-ai.com · checked Aug 1, 2026 · source did not state this
- Third-party evaluations
- no public informationarcade-ai.com · checked Aug 1, 2026 · source did not state this
- Data handling
- You control where your data lives and how it's secured.
“You control where your data lives and how it's secured.”
arcade-ai.com · checked Aug 1, 2026
Practicality
- Pricing model
- Free to start. Priced by usage.
“Free to start. Priced by usage.”
arcade-ai.com · checked Aug 1, 2026 - Price point
- See Pricing
“See Pricing”
arcade-ai.com · checked Aug 1, 2026 - Availability
- Free to start. Ready for enterprise when you are.
“Free to start. Ready for enterprise when you are.”
arcade-ai.com · checked Aug 1, 2026 - Deployment options
- 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.
“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.”
arcade-ai.com · checked Aug 1, 2026 - Integrations
- AI agents using Arcade access a catalog of pre-built Model Context Protocol tools for major systems like Google Workspace, Slack, Microsoft, and Salesforce.
“AI agents using Arcade access a catalog of pre-built Model Context Protocol tools for major systems like Google Workspace, Slack, Microsoft, and Salesforce.”
arcade-ai.com · checked Aug 1, 2026 - Supported regions
- no public informationarcade-ai.com · checked Aug 1, 2026 · source did not state this
- Support model
- no public informationarcade-ai.com · checked Aug 1, 2026 · source did not state this
Foundation models
- Base models
- no public informationarcade-ai.com · checked Aug 1, 2026 · source did not state this
- Model provider
- no public informationarcade-ai.com · checked Aug 1, 2026 · source did not state this
- Model swappable
- Build with LangChain, LlamaIndex, Mastra, CrewAI, Pydantic, Google ADK, or OpenAI Agents. The same flexibility extends across the stack: any agent client, including Claude, Cursor, ChatGPT, Copilot, or your own, and any LLM.
“Build with LangChain, LlamaIndex, Mastra, CrewAI, Pydantic, Google ADK, or OpenAI Agents. The same flexibility extends across the stack: any agent client, including Claude, Cursor, ChatGPT, Copilot, or your own, and any LLM.”
arcade-ai.com · checked Aug 1, 2026 - Open weights
- no public informationarcade-ai.com · checked Aug 1, 2026 · source did not state this
- Fine-tuning
- no public informationarcade-ai.com · checked Aug 1, 2026 · source did not state this
- Context window
- no public informationarcade-ai.com · checked Aug 1, 2026 · source did not state this
Ecosystem
- Protocols supported
- AI agents using Arcade access a catalog of pre-built Model Context Protocol tools for major systems like Google Workspace, Slack, Microsoft, and Salesforce.
“AI agents using Arcade access a catalog of pre-built Model Context Protocol tools for major systems like Google Workspace, Slack, Microsoft, and Salesforce.”
arcade-ai.com · checked Aug 1, 2026 - Tool use
- The runtime gives you visibility and control over every tool your AI agent accesses.
“The runtime gives you visibility and control over every tool your AI agent accesses.”
arcade-ai.com · checked Aug 1, 2026 - Multi-agent
- no public informationarcade-ai.com · checked Aug 1, 2026 · source did not state this
- API access
- Drop Arcade into your agent with our SDKs, quickstarts, and copy-paste examples.
“Drop Arcade into your agent with our SDKs, quickstarts, and copy-paste examples.”
arcade-ai.com · checked Aug 1, 2026 - Open source
- Developers can also build custom tools using the open-source Arcade framework in Python or JavaScript
“Developers can also build custom tools using the open-source Arcade framework in Python or JavaScript”
arcade-ai.com · checked Aug 1, 2026 - Marketplace presence
- The Arcade Registry lets you share and discover all your MCP tools.
“The Arcade Registry lets you share and discover all your MCP tools.”
arcade-ai.com · checked Aug 1, 2026
Impact
- User base
- no public informationarcade-ai.com · checked Aug 1, 2026 · source did not state this
- Deployment scale
- Arcade is trusted for production agents at
“Arcade is trusted for production agents at”
arcade-ai.com · checked Aug 1, 2026 - Target sectors
- We built an AI sales agent that knows everything about every deal by analyzing calls, emails, and CRM data.
“We built an AI sales agent that knows everything about every deal by analyzing calls, emails, and CRM data.”
arcade-ai.com · checked Aug 1, 2026 - High-risk domains
- no public informationarcade-ai.com · checked Aug 1, 2026 · source did not state this
- Documented incidents
- no public informationarcade-ai.com · checked Aug 1, 2026 · source did not state this