Problem / Use Case Coding agents with shell access (Claude Code, Copilot, Codex, etc.) can already use the meshStack CLI and meshStack's integrated agent context including skills to work with meshStack. But many agent runtimes now being built inside companies don't have a shell at all: hosted platforms like Microsoft Copilot Studio, M365 Copilot, claude.ai/ChatGPT connectors, or custom serverless bots (e.g. running on AWS Lambda) can only reach tools over MCP. They cannot install or run a CLI binary, and every customer who wants this today has to build and secure their own wrapper around our API. Running a CLI from such an agent would also mean handing it long-lived, broadly-scoped credentials, which is a worse security posture than keeping credentials server-side and authorizing each call under the calling user or a properly scoped API key. Proposed Solution Offer an official, remote meshStack MCP server that: Is a thin, purpose-built layer over the meshObject API (not a 1:1 tool-per-endpoint wrapper, to keep token usage sane for LLM callers) Consider supporting both OAuth (so a call can run as the requesting user) and API keys (for autonomous/service agents) Enforces the same permissions and access control that already exist in meshStack today This would let any hosted or serverless agent runtime integrate with meshStack without every customer building and maintaining their own bridge. We are keen to hear from you which use cases you have and which tool calls you'd like us to support specifically.