Skip to content

AI application discovery

Know which AI applications run on your workstations.

Vekri Endpoint finds coding agents, desktop AI apps, IDE assistants, local model runtimes and the MCP servers they are configured to use, without running them or reading credentials. Vekri Control turns what devices report into one inventory with owners, approval status and an explained risk score.

Contact SalesRequest a Demo

The problem

Why it matters.

Engineers install AI agents and connect them to MCP servers faster than any approval process. Security teams learn about them from an incident, not an inventory.
  1. 01

    Enroll the device

    One executable per user, installed as a per-user service on macOS or Linux. Each device enrolls with a one-time grant and signs every delivery.

  2. 02

    Discover applications

    Installed bundles, binaries, extensions and plugins are matched against a catalog of AI applications. Nothing is started.

  3. 03

    List MCP servers

    Each supported client's configuration is read for server names, transports and commands or hosts, never credential values.

  4. 04

    Review the inventory

    AI Applications in Vekri Control shows every application and server, who uses it, its approval status, its risk and whether Vekri mediates it.

See it work

Step by step.

AI application discovery
Illustrative data

ws-dev-07

macOS · Vekri Endpoint

  • Claude Code · Coding agent · 2.1.283
  • Cursor · IDE assistant
  • Claude Desktop · Desktop app
  • Ollama · Local models · 3 installed

MCP servers in client configuration

Name, transport, host. No secrets.

github · through a Vekri profile
linear · configured directly
notion · configured directly

Vekri Control · AI Applications

  • Claude CodeApproved
  • CursorUnder review
  • MCP: githubMediated
  • MCP: linearNot mediated

1 of 3 MCP servers mediated by Vekri

What happens

Capabilities

What Vekri does today.

Each item is in the current release and verified by tests in the product repository, with its limits beside it.

  • Vekri Endpoint

    AI coding agent discovery

    Finds Claude Code, OpenAI Codex CLI and GitHub Copilot CLI on a workstation, with their versions and configuration, without running them.

    Vekri Endpoint inventory · macOS, Linux

  • Vekri Endpoint

    Desktop and IDE AI application discovery

    Finds Claude Desktop, ChatGPT Desktop, Cursor, GitHub Copilot in VS Code and Copilot for JetBrains from their installed bundles, extensions and plugins.

    Vekri Endpoint inventory · macOS, Linux

    Limit: Claude Desktop and ChatGPT Desktop are macOS only (neither has a Linux build); Cursor is discovered on macOS, its configuration on both. Copilot for JetBrains is detected from its plugin only, and Claude Cowork as part of Claude Desktop, without knowing whether it is used.

  • Vekri Endpoint

    MCP client and server inventory

    Lists the MCP servers configured in each supported client (name, transport, command or host), and whether each is mediated by Vekri. Servers are never started and credential values are never read.

    Vekri Endpoint inventory · macOS, Linux

  • Vekri Endpoint

    Local model runtime discovery

    Finds Ollama and lists its installed models through its local API. Prompts and completions are never read.

    Vekri Endpoint inventory · macOS, Linux

  • Vekri Control

    AI Applications inventory

    Every AI application and MCP server found across your organization, with approval status, an explainable risk score, owner, employees, first and last seen, and coverage taken from evidence.

    Vekri Control

    Limit: Approval status is enforced only where Vekri has a control point (the local MCP gateway); elsewhere it is recorded.

  • Vekri Endpoint

    Endpoint fleet health

    Heartbeats, hook coverage, queue depth and delivery loss for each enrolled device, in Vekri Control.

    Vekri Control · macOS, Linux

Not yet available

  • Not supportedBrowser AI application discovery. Discovering AI use in web browsers needs a browser extension, which Vekri does not have.
  • Not supportedDirect AI API use. Detecting scripts and applications that call AI provider APIs directly is not covered.
  • Not verifiedOther AI applications in imported telemetry. Identifiers exist in the catalog, but no test verifies them end to end, and Vekri Endpoint does not discover these applications.
  • PlannedWindows endpoint. Vekri Endpoint on Windows.

Listed so you know where the edges are. Ask us before relying on anything here.

Support matrix

What Vekri Endpoint can do for each application.

The same levels the product reports with its inventory, taken from its capability catalog.

  • Claude Code

    Coding agent · tested with 2.1.283

    Discovery
    macOS: SupportedLinux: Supported
    MCP servers
    macOS: SupportedLinux: Supported
    Live hooks
    macOS: SupportedLinux: Supported
    Local MCP gateway
    macOS: SupportedLinux: Supported

  • OpenAI Codex CLI

    Coding agent

    Discovery
    macOS: SupportedLinux: Supported
    MCP servers
    macOS: SupportedLinux: Supported
    Live hooks
    macOS: Version-dependentLinux: Version-dependent
    Local MCP gateway
    macOS: Not yet testedLinux: Not yet tested

  • Claude Desktop

    Desktop app

    Discovery
    macOS: SupportedLinux: Unsupported
    MCP servers
    macOS: SupportedLinux: Unsupported
    Live hooks
    macOS: UnsupportedLinux: Unsupported
    Local MCP gateway
    macOS: Not yet testedLinux: Unsupported

  • Claude Cowork

    Desktop app

    Discovery
    macOS: PartialLinux: Unsupported
    MCP servers
    macOS: UnsupportedLinux: Unsupported
    Live hooks
    macOS: UnsupportedLinux: Unsupported
    Local MCP gateway
    macOS: UnsupportedLinux: Unsupported

  • ChatGPT Desktop

    Desktop app

    Discovery
    macOS: SupportedLinux: Unsupported
    MCP servers
    macOS: UnsupportedLinux: Unsupported
    Live hooks
    macOS: UnsupportedLinux: Unsupported
    Local MCP gateway
    macOS: UnsupportedLinux: Unsupported

  • Cursor

    IDE assistant

    Discovery
    macOS: SupportedLinux: Not yet tested
    MCP servers
    macOS: SupportedLinux: Supported
    Live hooks
    macOS: UnsupportedLinux: Unsupported
    Local MCP gateway
    macOS: Not yet testedLinux: Not yet tested

  • GitHub Copilot in VS Code

    IDE assistant

    Discovery
    macOS: SupportedLinux: Supported
    MCP servers
    macOS: SupportedLinux: Supported
    Live hooks
    macOS: UnsupportedLinux: Unsupported
    Local MCP gateway
    macOS: Not yet testedLinux: Not yet tested

  • GitHub Copilot CLI

    Coding agent

    Discovery
    macOS: SupportedLinux: Supported
    MCP servers
    macOS: PartialLinux: Partial
    Live hooks
    macOS: UnsupportedLinux: Unsupported
    Local MCP gateway
    macOS: Not yet testedLinux: Not yet tested

  • GitHub Copilot for JetBrains

    IDE assistant

    Discovery
    macOS: PartialLinux: Partial
    MCP servers
    macOS: UnsupportedLinux: Unsupported
    Live hooks
    macOS: UnsupportedLinux: Unsupported
    Local MCP gateway
    macOS: UnsupportedLinux: Unsupported

  • Ollama

    Local models

    Discovery
    macOS: SupportedLinux: Supported
    MCP servers
    macOS: UnsupportedLinux: Unsupported
    Live hooks
    macOS: UnsupportedLinux: Unsupported
    Local MCP gateway
    macOS: UnsupportedLinux: Unsupported
  • Windows: Vekri Endpoint builds for Windows, but nothing has been tested there yet, so no application is supported on it.
  • Supported means a test or demo in the product repository verifies it; it does not mean protected. Coverage comes from evidence: hooks reporting, or calls decided through a gateway.
  • Not yet tested means implemented or plausible but unverified, and never counted as coverage. Built-in tool denial is not enabled for any application.

Products

Where it comes from.

Related capabilities

Contact Sales

See Vekri with your own AI applications, agents and systems.

Talk to us about the AI your organization uses, the systems agents reach and how you deploy: in Vekri's cloud, or inside your own Kubernetes cluster.

Contact SalesRequest a Demo