Agentic Index

AI agent platforms that support Model Context Protocol tools (2026)

Of the 565 agentic AI platforms in the Agentic Index, 258 document Model Context Protocol (MCP) support and extensibility in full. Only 94 also document tool calling into real systems and model flexibility in full. That is 16.6% of the field. This is a bar, not a leaderboard: a platform either documents all three in its own public materials or it does not clear, and Partial evidence on any one of the three does not count.

The finding underneath the list is more useful than the list. The tool layer opened and the model layer did not. Tool calling is documented in full by 76% of the pool and MCP by 46%, but model flexibility and routing by only 24%. Of the 169 platforms sitting exactly one capability short of the bar, 137 are short on model flexibility alone. MCP is sold as the end of integration lock in, and most of the platforms that speak it still choose the model for you.

There is a second number worth carrying into a vendor call. 199 of the 430 platforms that document tool calling in full do not document MCP support. Nearly half the platforms that can call a tool cannot show they speak the protocol. Tool calling and MCP get used as synonyms in vendor marketing and they are not the same claim.

The bar, and how the 565 platforms score against it

Capability	What has to be documented	Full	Only blocker
MCP and extensibility	Model Context Protocol (MCP) support as a client, a server or both, plus a public API or SDK the buyer can build against	258 (46%)	24
Integrations and tool calling	documented tool calling into real systems, through prebuilt connectors, an MCP server or both	430 (76%)	8
Model flexibility and routing	bring your own model or bring your own key (BYOK), or documented routing between providers rather than one hardwired model	135 (24%)	137

Full means the vendor publishes evidence meeting the capability in its own public materials, under the Agentic Index verification standard. Only blocker counts platforms that document the other two in full and fail on this one alone.

Clears the bar and scores 12.5 or higher of 14 overall

These 13 platforms document MCP and extensibility, tool calling and model flexibility in full, and also sit at the top of the Agentic Index coverage score across all 14 capabilities. Ordered by total coverage, ties broken alphabetically.

1. 1.UiPath

   13.5 / 14 capabilities

   enterprise operations agents, multi-agent platforms, agent builders

   Agentic automation orchestrating agents, robots and people end to end through Maestro. Autopilot is documented against GPT, Gemini and Claude running on the customer's own cloud, which is why it clears the axis that stops 137 other platforms.

2. 2.Automation Anywhere

   13.0 / 14 capabilities

   enterprise operations agents, multi-agent platforms, agent builders

   Agentic process automation pairing goal driven agents with RPA bots and human decision points. Deliberately model agnostic across Bedrock, fine tuned and RAG models, and the connector surface reaches Salesforce, ServiceNow, SAP and custom APIs through Mozart.

3. 3.CrewAI

   13.0 / 14 capabilities

   multi-agent platforms

   Open source multi agent orchestration for collaborative crews. Open source frameworks are the class most likely to clear this bar, because portability is the reason people pick them.

4. 4.Salesforce

   13.0 / 14 capabilities

   enterprise operations agents

   CRM platform whose Agentforce layer runs autonomous agents across sales, service and marketing. Connects through MCP connectors and the Atlas Reasoning Engine is documented across OpenAI, Anthropic and Google Gemini rather than one house model.

5. 5.Agno

   12.5 / 14 capabilities

   agent infrastructure platforms

   High performance agent runtime, formerly Phidata, Apache 2.0 licensed. The lightest thing on this list and it still clears all three, which is what a runtime rather than a suite ought to look like.

6. 6.Atomicwork

   12.5 / 14 capabilities

   enterprise operations agents

   AI native ITSM and ESM platform deploying governed AI coworkers across IT, HR, finance and legal. Built on the Model Context Protocol with more than five hundred tools, and lets teams bring their own agent harness and model.

7. 7.Boomi

   12.5 / 14 capabilities

   enterprise operations agents, multi-agent platforms, agent builders

   Integration platform with an agent control tower over enterprise systems. MCP support sits next to a vendor agnostic registry that governs third party agents, and the model layer stays open across Bedrock, Snowflake Cortex and OpenAI.

8. 8.Coworker

   12.5 / 14 capabilities

   enterprise operations agents, agent builders

   Enterprise agent platform built on an organizational memory knowledge graph. Its memory layer is reachable from any MCP enabled client, and routing scores each task across closed, open source and self hosted models.

9. 9.CrowdStrike

   12.5 / 14 capabilities

   multi-agent platforms, agent builders (secondary lane membership, primary category Security and SOC agent)

   Security platform whose Charlotte AI runs agentic detection, triage and response in the SOC. AgentWorks documents model optionality across Anthropic, OpenAI and NVIDIA. Qualifies here on secondary lane membership as an agent builder and multi agent platform, which a buyer scanning this list should know.

10. 10.Pydantic AI

    12.5 / 14 capabilities

    agent infrastructure platforms

    Open source Python agent framework with first class MCP support alongside Agent2Agent and UI event stream standards. Carries one of the strongest model positions in the index, compatible with virtually every provider.

11. 11.Rasa

    12.5 / 14 capabilities

    multi-agent platforms

    Open source conversational AI with an enterprise framework, full channel coverage and dialog orchestration. Multi model support is documented in the open source docs rather than asserted in marketing.

12. 12.Sim

    12.5 / 14 capabilities

    multi-agent platforms, agent builders

    Open source Apache 2.0 agent workspace with a public API, SDKs and a Function block for custom code. More than a thousand native service integrations and fifteen plus model providers documented.

13. 13.SimplAI

    12.5 / 14 capabilities

    multi-agent platforms, agent builders, agent infrastructure platforms

    Enterprise agentic operating system running multi agent systems across cloud, on premises and air gapped environments. A model and intelligence layer routes across multiple LLMs, and the step library spans twenty five plus categories.

The remaining 81 platforms that clear the bar

Every one of these documents MCP and extensibility, tool calling and model flexibility in full. They score below 12.5 of 14 on total coverage, which says something about breadth across the whole taxonomy, not about how open they are. Several of the most portable things in the index sit low here precisely because they do one job.

Common questions

Which AI agent platforms support Model Context Protocol tools?

258 of 565 agentic AI platforms in the Agentic Index document Model Context Protocol support and extensibility in full. 94 of them also document tool calling into real systems and model flexibility in full, which is the bar used on this page. That is 16.6% of the field. The list is ordered by total documented coverage across the Agentic Index 14 point capability taxonomy and is graded from public evidence only.

What counts as real Model Context Protocol support in an AI agent platform?

Three things, and a platform has to document all three in public materials to clear the bar used here. Model Context Protocol (MCP) support as a client, a server or both, alongside a public API or SDK. Documented tool calling into real systems through prebuilt connectors, an MCP server or both. And model flexibility: bring your own model or bring your own key (BYOK), or documented routing between providers rather than one hardwired model. Partial evidence on any one of the three does not clear.

Do most AI agent platforms that call tools support MCP?

No. 430 of the 565 platforms document tool calling in full, and 199 of those do not document MCP support. Nearly half the platforms that can call a tool cannot show they speak the protocol. MCP adoption is real but it trails tool calling by a wide margin.

Why do so few AI agent platforms clear the interoperability bar?

Model flexibility, not the protocol. Across the 565 platform pool, tool calling is documented in full by 76% and MCP by 46%, but model flexibility and routing by only 24%. Of the 169 platforms sitting exactly one capability short of the bar, 137 are short on model flexibility alone. MCP is sold as the end of integration lock in, and most platforms that speak it still choose the model for you.

Is this ranking paid or sponsored?

No. No vendor pays for placement, no vendor has reviewed this page, and every grade comes from the vendor's own public materials under the Agentic Index verification standard. 984 vendors are graded against the same 14 capabilities. Data last verified August 8, 2026.

Method: membership is the same 565 platform pool used by the best agentic AI platforms in 2026, drawn from 984 researched vendors. The four editorial pages over this pool are one method with different bars, not four opinions. Every grade comes from the vendor's own public materials under the Agentic Index verification standard. No vendor pays for placement and no vendor has reviewed this page. Data last verified August 8, 2026. How this evidence is graded

Related: agent observability platforms, enterprise security and compliance platforms, autonomous AI workforce platforms, how every vendor scores on MCP and extensibility, compare platforms side by side.