Action & orchestration

Which AI agent platforms connect to real systems through tool calling?

Tool calling is the most widely documented capability in the taxonomy. Of the 955 vendors in the index, 725 publish full evidence of connecting agents to real systems through native integrations, authenticated actions, custom tools, APIs, webhooks or MCP compatible tools. Another 211 document partial coverage and only 19 document none at all.

Every vendor in the index is assessed against the same 14 point taxonomy from public documentation, and no vendor pays for placement. Counts on this page were measured across all 955 public vendors on October 7, 2026.

How the 955 vendors split

Full coverage725 vendors, 75.9%
Partial coverage211 vendors, 22.1%
No public evidence19 vendors, 2%

No public evidence means the reviewed sources did not document the capability. On this index that is a statement about the evidence, not proof that the capability is absent. See methodology.

What counts as full coverage

Full coverage means the vendor publishes evidence that agents can take authenticated action in outside systems, not merely read from them or hand a suggestion back to a person. A named integration catalog, documented custom tool support, or an authenticated action framework each qualify on their own. Partial usually means a short fixed list of connectors with no way to add your own, or a deep catalog confined to one class of system such as a single CRM.

How to read these numbers

Treat a high score here as table stakes rather than a differentiator, and read the low end instead. Ten of the 13 lanes clear 65 percent, and the SRE and DevOps lane documents full coverage for 32 of its 37 members, which follows from what those agents do: an incident agent with no hands is a dashboard. The interesting number is the 19 vendors that document nothing, since a platform that cannot evidence how its agents reach your stack is selling a demo. Where teams actually get surprised is the shape of the integration, so check whether the vendor supports custom tools or only its own catalog before treating full coverage as a match.

Leading platform for integrations & tool calling in each use case

Picked mechanically: the highest total coverage vendor in each lane that documents full evidence on this axis, one vendor per row. Scores are out of 14.

  1. 1. Appian, for enterprise operations agents

    14 / 14

    Full enterprise operations agents ranking · Compare the whole lane on all 14 axes

  2. 2. FLOWX.AI, for multi-agent platforms

    14 / 14

    Full multi-agent platforms ranking · Compare the whole lane on all 14 axes

  3. 3. Gumloop, for GTM and revenue agents

    14 / 14

    Full GTM and revenue agents ranking · Compare the whole lane on all 14 axes

  4. 4. Mastra, for agent infrastructure platforms

    14 / 14

    Full agent infrastructure platforms ranking · Compare the whole lane on all 14 axes

  5. 5. ServiceNow, for customer support agents

    14 / 14

    Full customer support agents ranking · Compare the whole lane on all 14 axes

  6. 6. UiPath, for agent builders

    14 / 14

    Full agent builders ranking · Compare the whole lane on all 14 axes

  7. 7. GitHub Copilot, for coding agents

    13.5 / 14

    Full coding agents ranking · Compare the whole lane on all 14 axes

  8. 8. Dataiku, for data analyst agents

    13 / 14

    Full data analyst agents ranking · Compare the whole lane on all 14 axes

  9. 9. HappyRobot, for voice agents

    13 / 14

    Full voice agents ranking · Compare the whole lane on all 14 axes

  10. 10. Komodor, for SRE and DevOps agents

    13 / 14

    Full SRE and DevOps agents ranking · Compare the whole lane on all 14 axes

  11. 11. Adopt AI, for browser and computer-use agents

    12.5 / 14

    Full browser and computer-use agents ranking · Compare the whole lane on all 14 axes

  12. 12. Torq, for security and SOC agents

    12.5 / 14

    Full security and SOC agents ranking · Compare the whole lane on all 14 axes

  13. 13. Innovaccer, for healthcare agents

    11.5 / 14

    Full healthcare agents ranking · Compare the whole lane on all 14 axes

Documented coverage by use case

Share of each lane documenting full coverage on this axis. Vendors that sit in two lanes count in both, the same rule the rankings and matrices use.

Use case Full coverage Share
customer support agents 108 of 115 94%
voice agents 77 of 83 93%
security and SOC agents 77 of 85 91%
healthcare agents 61 of 69 88%
SRE and DevOps agents 32 of 37 86%
agent builders 102 of 118 86%
multi-agent platforms 43 of 52 83%
coding agents 57 of 70 81%
GTM and revenue agents 111 of 138 80%
enterprise operations agents 229 of 301 76%
agent infrastructure platforms 117 of 186 63%
browser and computer-use agents 26 of 42 62%
data analyst agents 31 of 59 53%

Recent verified changes from the vendors named above

Capability coverage is not a static picture. These are the most recent sourced change log entries for the platforms listed above, newest first, one per vendor. Scores on this page update as entries like these are verified.

  1. GitHub Copilot integrations

    Medium impact

    Coding from a chat thread is now generally available with @GitHub in Slack and Microsoft Teams, which can investigate bugs, create issues, implement changes and open pull requests without leaving the conversation. In Teams, a new Canvas shows implementation plans, code changes and previews next to the discussion so the group can refine the work together.

    November 6, 2026 · Verified · All GitHub Copilot changes

  2. Dataiku mcp / tool calling / api

    High impact

    Headless is a new plugin and MCP server that lets coding agents such as Claude Code, Codex and Cursor create and change Dataiku projects, including pipelines, models, dashboards and agents, by handing the build to Cobuild. It can also help move workflows built in SAS, Alteryx or Excel into Dataiku, and gives administrators tools that mainly inspect projects and failing jobs. It installs from the public Claude Code and Codex plugin marketplaces.

    October 27, 2026 · Verified · All Dataiku changes

  3. Mastra mcp / tool calling / api

    High impact

    MCP servers built with Mastra can now send events to connected clients by push, poll or webhook, instead of only answering requests. Agents receive each event in their thread as a notification, and workflows can start a run from one, so a failed deploy or a merged pull request can set work in motion. The feature is experimental, needs @mastra/mcp 2.5.0 or later, and records event traces automatically when observability is set up.

    October 23, 2026 · Verified · All Mastra changes

  4. Torq integrations

    Medium impact

    Torq highlighted its integration and partnership with CrowdStrike at Fal.Con 2026, connecting Falcon telemetry directly to the Torq Context Graph. This integration enables near-real-time case management and automated remediation of CrowdStrike detections.

    September 3, 2026 · Verified · All Torq changes

  5. FLOWX.AI integrations

    Medium impact

    FlowX.AI made its specialized industry AI agents and orchestration platform available on Gemini Enterprise via the Google Cloud Marketplace. The integration allows organizations to run FlowX.AI's orchestration layer alongside Gemini models within a single managed environment.

    August 25, 2026 · Partially Verified · All FLOWX.AI changes

Full change log · updated weekly across the whole index

Questions buyers ask

Does this include MCP support?

Partly. Native MCP tool consumption counts as evidence here, but MCP as a first class extensibility surface is graded separately on the APIs, SDKs and MCP extensibility axis, which is the page to read if MCP is the requirement.

What does partial coverage mean for a shortlist?

It usually means a fixed connector list with no documented path to custom tools. That is fine when the systems you care about are already on the list and a problem the first time they are not.

How current are these counts?

They are a census of the grid taken on October 7, 2026 across all 955 public vendors. Rankings and matrices recompute continuously, so the live lane pages can move ahead of the counts quoted here.

The other 13 axes

No single axis decides a shortlist. Buyers who care about this one usually check browser & computer use and workflow orchestration next, or open the full taxonomy to see how the 14 axes fit together.

Contact us

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