Back to vendors
T

Tray.ai

Also known as: Tray.io, Tray

Visit site
Entry priceCustom quote · free trial · Pro / Team / EnterpriseFull pricing detail

Enterprise automation and AI agent platform with MCP-native integration capabilities.

Tray.ai (formerly Tray.io) is an enterprise orchestration platform for data and AI that unifies integration, automation, and AI-agent development on one governed foundation. Rather than treating agents as an add-on, Tray positions itself as the infrastructure beneath them, applying the same disciplines that govern API integration (access control, observability, versioning, auditability) to AI agents and the tools they call.

The platform combines several layers. Intelligent iPaaS connects and automates the stack through a library of 700+ managed connectors (Salesforce, Workday, Snowflake, Jira, NetSuite, ServiceNow, and more). Merlin Agent Builder, which shipped in December 2024, is a no-code environment where operations leads and analysts build production agents (a master agent coordinating department sub-agents, each with its own tools, knowledge, and context) with guardrails, PII protection, audit logging, and human-in-the-loop approvals baked in. Agents can use long-term memory, any LLM (or a customer's own), and deploy to Slack, Teams, chatbots, or APIs. Enterprise Core supplies governance, security, and monitoring, and the Insights Hub tracks every tool call.

Tray has leaned heavily into the Model Context Protocol. Its Agent Gateway is an MCP registry and governance layer that lets IT build, version, and publish governed MCP servers and tools (including composite tools and connector-backed tools drawn from the 700+ library) while curbing 'shadow MCP' sprawl; it works with any client (Claude, OpenAI, Copilot Studio) and supports Agent-to-Agent (A2A) interoperability. Gartner named Tray a Visionary in its Magic Quadrant for iPaaS and a Pioneer in the inaugural 2026 Emerging Market Quadrant for No-Code Agent Builders. Pricing is usage-based across Pro, Team, and Enterprise tiers, with a free trial.

Vendor details

Canonical URL

https://tray.ai

Category

Agent infrastructure

Subcategory

Enterprise iPaaS + AI agent orchestration / MCP governance

Funding status

Established enterprise iPaaS vendor (formerly Tray.io); venture-backed; CEO/co-founder Rich Waldron. Recognized by Gartner (Visionary in the Magic Quadrant for iPaaS; Pioneer in the inaugural 2026 Emerging Market Quadrant for No-Code Agent Builders; included in the 2026 Hype Cycle for Agentic AI) and Nucleus Research (Leader 7×).

Company status

independent

Use cases & customers

Primary use cases

Building and deploying no-code enterprise AI agents (Merlin Agent Builder)Governing MCP tools and servers across the enterprise (Agent Gateway)App-to-app integration and process automation across 700+ connectorsMulti-agent orchestration (master + department sub-agents) with human-in-the-loopWiring AI into existing systems of record (CRM, ERP, HR, data warehouses)

Target customers

Enterprise IT & automation teamsIntegration / API developersOperations teams

Deployment options

SaaSRegional hosting (Enterprise)On-premise connectors (Enterprise)

Integrations

700+ managed connectors (Salesforce, Workday, Snowflake, Jira, NetSuite, ServiceNow, and more), each governable through the same RBAC and publishable as MCP tools. Agent Gateway provides an MCP registry and governance layer — composite and connector-backed MCP tools, MCP consumption, and Agent-to-Agent (A2A) support — with audit trails streamable to Datadog and Splunk. Agents deploy to Slack, Teams, chatbots, or APIs.

In practice

Your team spins up AI agents faster than IT can govern them, and shadow MCP servers multiply. Tray's Agent Gateway is an MCP registry that lets IT build, version, and publish governed MCP tools.

An agent is only useful if it can reach your stack. Tray connects through more than 700 managed connectors, so agents act across Salesforce, Workday, Snowflake, and the rest.

Ops leads need to build agents without waiting on engineering. Tray's Merlin Agent Builder is a no-code environment with guardrails, PII protection, and human-in-the-loop baked in.

Agentic Index coverage score

11.5 / 14 capabilities · 82%

Integrations & Tool CallingTray.ai documentation, trust report, and 2026 analyst coverage confirm 700+ managed connectors with tool calling, iPaaS and multi agent orchestration, an MCP native Agent Gateway with A2A and headless developer access, built in guardrails and PII controls via Merlin Guardian with human in the loop approvals, SOC 1 and SOC 2 Type II plus HIPAA, GDPR, and CCPA with SSO and RBAC, audit trails across every action with external log streaming, regional hosting in North America, EMEA, and APAC with on premise connectivity, any LLM or bring your own model, agent long term memory, and broad triggers with Slack, Teams, chatbot, and API deployment. Full
Workflow OrchestrationTray.ai documentation, trust report, and 2026 analyst coverage confirm 700+ managed connectors with tool calling, iPaaS and multi agent orchestration, an MCP native Agent Gateway with A2A and headless developer access, built in guardrails and PII controls via Merlin Guardian with human in the loop approvals, SOC 1 and SOC 2 Type II plus HIPAA, GDPR, and CCPA with SSO and RBAC, audit trails across every action with external log streaming, regional hosting in North America, EMEA, and APAC with on premise connectivity, any LLM or bring your own model, agent long term memory, and broad triggers with Slack, Teams, chatbot, and API deployment. Full
Knowledge Grounding & RAGKnowledge grounding is available in Merlin Agent Builder where agents are backed by knowledge and tools, though the depth of the managed retrieval layer is not fully documented; prebuilt content centers on connector templates and accelerators such as the ready to use ITSM agent rather than a large prebuilt agent library; and testing relies on workflow debug logs and monitoring rather than a dedicated agent evaluation suite. Partial
Human Oversight & GuardrailsTray.ai documentation, trust report, and 2026 analyst coverage confirm 700+ managed connectors with tool calling, iPaaS and multi agent orchestration, an MCP native Agent Gateway with A2A and headless developer access, built in guardrails and PII controls via Merlin Guardian with human in the loop approvals, SOC 1 and SOC 2 Type II plus HIPAA, GDPR, and CCPA with SSO and RBAC, audit trails across every action with external log streaming, regional hosting in North America, EMEA, and APAC with on premise connectivity, any LLM or bring your own model, agent long term memory, and broad triggers with Slack, Teams, chatbot, and API deployment. Full
Security, Identity & GovernanceTray.ai documentation, trust report, and 2026 analyst coverage confirm 700+ managed connectors with tool calling, iPaaS and multi agent orchestration, an MCP native Agent Gateway with A2A and headless developer access, built in guardrails and PII controls via Merlin Guardian with human in the loop approvals, SOC 1 and SOC 2 Type II plus HIPAA, GDPR, and CCPA with SSO and RBAC, audit trails across every action with external log streaming, regional hosting in North America, EMEA, and APAC with on premise connectivity, any LLM or bring your own model, agent long term memory, and broad triggers with Slack, Teams, chatbot, and API deployment. Full
Observability & AuditabilityTray.ai documentation, trust report, and 2026 analyst coverage confirm 700+ managed connectors with tool calling, iPaaS and multi agent orchestration, an MCP native Agent Gateway with A2A and headless developer access, built in guardrails and PII controls via Merlin Guardian with human in the loop approvals, SOC 1 and SOC 2 Type II plus HIPAA, GDPR, and CCPA with SSO and RBAC, audit trails across every action with external log streaming, regional hosting in North America, EMEA, and APAC with on premise connectivity, any LLM or bring your own model, agent long term memory, and broad triggers with Slack, Teams, chatbot, and API deployment. Full
Memory & State PersistenceTray.ai documentation, trust report, and 2026 analyst coverage confirm 700+ managed connectors with tool calling, iPaaS and multi agent orchestration, an MCP native Agent Gateway with A2A and headless developer access, built in guardrails and PII controls via Merlin Guardian with human in the loop approvals, SOC 1 and SOC 2 Type II plus HIPAA, GDPR, and CCPA with SSO and RBAC, audit trails across every action with external log streaming, regional hosting in North America, EMEA, and APAC with on premise connectivity, any LLM or bring your own model, agent long term memory, and broad triggers with Slack, Teams, chatbot, and API deployment. Full
Deployment & Data ResidencyTray.ai documentation, trust report, and 2026 analyst coverage confirm 700+ managed connectors with tool calling, iPaaS and multi agent orchestration, an MCP native Agent Gateway with A2A and headless developer access, built in guardrails and PII controls via Merlin Guardian with human in the loop approvals, SOC 1 and SOC 2 Type II plus HIPAA, GDPR, and CCPA with SSO and RBAC, audit trails across every action with external log streaming, regional hosting in North America, EMEA, and APAC with on premise connectivity, any LLM or bring your own model, agent long term memory, and broad triggers with Slack, Teams, chatbot, and API deployment. Full
Prebuilt Agents, Templates & PacksKnowledge grounding is available in Merlin Agent Builder where agents are backed by knowledge and tools, though the depth of the managed retrieval layer is not fully documented; prebuilt content centers on connector templates and accelerators such as the ready to use ITSM agent rather than a large prebuilt agent library; and testing relies on workflow debug logs and monitoring rather than a dedicated agent evaluation suite. Partial
Triggers & Channel CoverageTray.ai documentation, trust report, and 2026 analyst coverage confirm 700+ managed connectors with tool calling, iPaaS and multi agent orchestration, an MCP native Agent Gateway with A2A and headless developer access, built in guardrails and PII controls via Merlin Guardian with human in the loop approvals, SOC 1 and SOC 2 Type II plus HIPAA, GDPR, and CCPA with SSO and RBAC, audit trails across every action with external log streaming, regional hosting in North America, EMEA, and APAC with on premise connectivity, any LLM or bring your own model, agent long term memory, and broad triggers with Slack, Teams, chatbot, and API deployment. Full
Model Flexibility & RoutingTray.ai documentation, trust report, and 2026 analyst coverage confirm 700+ managed connectors with tool calling, iPaaS and multi agent orchestration, an MCP native Agent Gateway with A2A and headless developer access, built in guardrails and PII controls via Merlin Guardian with human in the loop approvals, SOC 1 and SOC 2 Type II plus HIPAA, GDPR, and CCPA with SSO and RBAC, audit trails across every action with external log streaming, regional hosting in North America, EMEA, and APAC with on premise connectivity, any LLM or bring your own model, agent long term memory, and broad triggers with Slack, Teams, chatbot, and API deployment. Full
APIs, SDKs & MCP ExtensibilityTray.ai documentation, trust report, and 2026 analyst coverage confirm 700+ managed connectors with tool calling, iPaaS and multi agent orchestration, an MCP native Agent Gateway with A2A and headless developer access, built in guardrails and PII controls via Merlin Guardian with human in the loop approvals, SOC 1 and SOC 2 Type II plus HIPAA, GDPR, and CCPA with SSO and RBAC, audit trails across every action with external log streaming, regional hosting in North America, EMEA, and APAC with on premise connectivity, any LLM or bring your own model, agent long term memory, and broad triggers with Slack, Teams, chatbot, and API deployment. Full
Testing, Debugging & OptimizationKnowledge grounding is available in Merlin Agent Builder where agents are backed by knowledge and tools, though the depth of the managed retrieval layer is not fully documented; prebuilt content centers on connector templates and accelerators such as the ready to use ITSM agent rather than a large prebuilt agent library; and testing relies on workflow debug logs and monitoring rather than a dedicated agent evaluation suite. Partial
Browser & Computer UseTray.ai orchestrates through APIs, connectors, and MCP tools and does not provide browser or computer use automation. Unable to verify

The Agentic Index coverage score grades every vendor Full, Partial or Unable to verify against the same 14 buyer facing capabilities, from public evidence only. Each capability links to how all vendors in the index score on it. How this evidence is graded

Recent platform changes

2026-08-04·Security / enterpriseVerified

Tray.ai introduced Tray Helix, a governed runtime environment designed for AI-built applications. The release features a centralized credential broker that allows apps to reference authentication aliases, ensuring that raw secrets never touch application code or AI prompts.

Bears on: Security / enterprise

View source
2026-06-17·MCP / tool calling / APIVerified

Tray.ai made MCP dynamic authentication generally available. MCP tools can now run using end-user credentials instead of shared service accounts, with allowlists, authentication management, and a usage monitor.

Bears on: MCP / tool calling / API

View source
2026-06-15·Deployment / data residencyVerified

Tray Headless MCP added region-specific endpoints for US, EU, and APAC workspaces.

Bears on: Deployment / data residency

View source
View all 4 changes for Tray.ai →Tracked since Jun 2026 · Verified from public vendor sources

Pricing

Custom quote · free trial · Pro / Team / Enterprise

usage (tasks)

Trial available

Included quota

Pro covers up to 3 workspaces with 7 day insights retention. Team covers 20 workspaces with 30 day insights retention, enhanced insights, 24/7 support, and dedicated Slack. Enterprise covers unlimited workspaces with 180 day insights retention, regional hosting, log streaming, on premise connectivity, and embedded white label options. All plans include business hours support and a free trial. Task volume is quoted per customer.

What is public

Public: the tier structure (Pro, Team, Enterprise), workspace limits, insights retention windows, support levels, and that billing is usage based on tasks. Not public: the actual dollar rates, which are quoted by sales based on usage and features.

Billing mechanics

Usage based subscription metered by tasks across three tiers, with a customized quote based on expected usage and the features required. Multi step automations, real time triggers, connector count, and error retries all consume tasks. The Merlin Agent Builder agent product is licensed separately from the core integration platform, and HIPAA, SSO, and extended log retention can be add ons.

Cost watchouts

The Merlin Agent Builder is licensed separately from core iPaaS, and HIPAA, SSO, and extended log retention can be add ons. Task consumption is driven by automation complexity and trigger frequency, so real usage can exceed initial estimates. Enterprise features like regional hosting and on premise connectivity sit at the top tier.

Variable cost rationale

Billing is usage based on tasks, and task consumption scales with workflow complexity, trigger frequency, data volume, connector count, and retry logic, so heavy automation and agent activity drive cost up quickly. Add ons such as HIPAA, extended retention, and the separately licensed agent product add further cost, making exposure high.

Additional watchouts

Pricing is quote only with no public dollar figures. The agent builder is a separate line item from core iPaaS, HIPAA is an add on, and task based billing means cost scales with automation volume.

Overage / add-ons

Task usage is set by the quoted plan; exceeding it requires moving to a higher tier or a larger task allotment agreed with sales.

Sales call required

Mixed (some tiers require a call)

Free / trial

A free trial is available to explore the platform before committing. There is no perpetual free tier.

Lowest paid plan

Pro tier for up to 3 workspaces, priced by a custom usage based quote above a free trial.

Commercial notes

A single AI native platform spanning integration, automation, MCP governance, and agents, positioned to replace fragmented legacy iPaaS stacks. Tray reports customers ship faster and spend materially less than legacy iPaaS, though the usage based, quote driven model requires sizing task volume carefully.

Key ambiguities

No dollar pricing is public, so total cost depends entirely on a sales quote driven by task volume, workspaces, and add ons. The agent product is priced separately from the integration platform.

Support SLA / resale

All plans include business hours support (Tray Advantage). Team and Enterprise add 24/7/365 support, enhanced SLAs, and dedicated Slack channels (Tray Advantage Plus). An embedded white label bundle is available at Enterprise.

Missing data

Dollar rates for each tier, per task pricing, the separate Merlin Agent Builder license cost, and add on pricing for HIPAA and extended retention are not public.

Agentic Index verified 2026-07-01

Alternatives to Tray.ai

The closest documented capability profiles to Tray.ai among agent infrastructure platforms tracked by Agentic Index, ordered by similarity on the same 14 point evidence the rankings use. No vendor pays for placement.

  • Kestra12.0 / 14Fuller documented coverage on Prebuilt Agents, Templates & Packs
  • Agno12.5 / 14Adds documented Browser & Computer Use
  • Pipecat10.0 / 14A lighter documented profile than Tray.ai
  • Thread AI10.0 / 14A lighter documented profile than Tray.ai
  • Windmill10.0 / 14A lighter documented profile than Tray.ai
  • Bernstein10.5 / 14Fuller documented coverage on Testing, Debugging & Optimization

Similarity is computed from each vendor's Agentic Index coverage score evidence, axis by axis, not from the totals. How this evidence is graded

Contact us

Found a vendor we missed? Have feedback on the index? We'd love to hear from you.