Innovation & Tech

Recast's New MCP Server Puts Live Endpoint Data in AI Chats

Recast unveiled an MCP Server for Right Click Tools at Microsoft Ignite on November 17, feeding AI assistants live endpoint data while keeping existing permissions and approval steps intact.

By Amara Osei

3 min read

Recast Brings AI Troubleshooting to Right Click Tools With MCP Server
Recast Brings AI Troubleshooting to Right Click Tools With MCP Serverkewl / pixabay

What's News

  • Recast announced the MCP Server for Right Click Tools at Microsoft Ignite on November 17.
  • Recast says its products manage more than 60 million endpoints.
  • The server works with GitHub Copilot in Visual Studio Code and GitHub Copilot CLI.
  • Recast provides no independent benchmarks on investigation time or diagnostic accuracy.
  • The integration honors existing permissions, routing and licensing, with tool-run approval built in.

Recast launched an MCP Server for its Right Click Tools at Microsoft Ignite on November 17, connecting natural-language AI assistants with live information from managed devices. The company, whose products manage more than 60 million endpoints, says the server respects existing permissions, routing and licensing. What it doesn't provide is independent proof the integration speeds investigations or improves diagnostic accuracy.

The announcement targets a familiar bottleneck for IT teams: gathering enough current context to understand a problem before deciding how to fix it. Recast's answer is to feed AI assistants live device data instead of stale inventory records. A record of a machine's earlier state may serve reporting, but troubleshooting often depends on what's happening at the moment an administrator investigates.

What does the integration actually do?

Recast positions the integration as another way to work with its existing tools, not a chatbot replacement for endpoint-management software. Administrators ask questions about device and application issues, and the assistant draws on Right Click Tools workflows and data from their own environment.

The company also pitches the server as a way to combine multiple Right Click Tools workflows, which could cut the manual work of moving between individual checks and assembling results into a coherent picture. It doesn't, by itself, establish that an AI-generated diagnosis is correct or that a recommended intervention should run without review.

Recast's setup documentation describes running the server with GitHub Copilot in Visual Studio Code and with GitHub Copilot CLI. Its examples include checking device reachability and retrieving BitLocker status.

What MCP adds to Right Click Tools

Model Context Protocol provides a standardized way for AI assistants to connect with external tools and data. In this deployment, the server bridges an AI platform and the capabilities available through Right Click Tools. The model supplies the conversational interface; the connected software supplies environment-specific information.

That separation matters. An assistant can explain a common endpoint problem from general knowledge, but it can't know the present condition of a particular corporate device without an authorized evidence source. An MCP connection can supply that evidence without turning the model into the endpoint-management system itself.

The operational context runs deeper than a pasted description. Checking whether a device is reachable and then inspecting a security-related setting requires a connection to the relevant tools, access to the intended machine and permission to retrieve the requested information. Recast's approach brings that context into the conversation rather than asking the model to reason blind.

Do existing controls survive?

Yes, and that's the core of the pitch. Recast's announcement says the MCP Server honors existing permissions, routing and licensing rather than opening an unrestricted path into the environment. The documentation shows tool-run approval as part of the workflow — a natural-language interface doesn't have to mean unrestricted execution.

"AI is most valuable when it gives IT professionals the context to make the right decision," said Will Teevan, Recast's CEO, in the announcement. The company's stated aim is reducing manual effort while keeping administrators' expertise central to troubleshooting.

Those benefits remain claims to evaluate in practice. The release provides no independent benchmarks showing how much investigation time the server saves, nor measured improvement in diagnostic accuracy. Teams should distinguish faster information gathering from proven remediation outcomes, particularly when a suggested action could affect multiple devices.

Why it matters for enterprise AI

Recast's broader portfolio extends Microsoft Intune and Configuration Manager across application delivery, automation, remediation and operational visibility. The MCP announcement adds an AI-facing connection to that management context rather than asking enterprises to replace their operational stack.

The open question is whether conversational access makes routine investigations clearer and quicker without obscuring how a conclusion was reached. Live data improves the evidence available to an assistant, but administrators still need to know which devices were queried, which tools ran and what permissions governed the result. Recast's announcement points to a narrower, more testable role for enterprise AI — helping IT professionals collect and interpret information, while operational accountability stays with the people responsible for the environment.

Source: unite.ai

Share this article:

More from Amara Osei

Amara Osei

Show full bio

Senior reporter covering companies, deals and strategy in entrepreneurship, startups and venture funding at Business Bearings.

2,248 articles

Related articles

« Previous articleNext article »