Feature Requests

Official remote meshStack MCP server
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.
0
Limit concurrency of asyncronous pipeline building blocks
Asynchronous pipeline-based building blocks are not limited by the available capacity of meshStack runners in the same way as synchronous building blocks. When a building block depends on another building block and the dependency's definition is updated, meshStack triggers new runs for the dependent (parent) building blocks as well. We have a building block that has been ordered more than 80 times. When we update its dependency, all 80 instances are triggered almost simultaneously. This results in 80 pipeline executions being dispatched and queued in our external CI/CD system, waiting for available pipeline runners. Unfortunately, we haven't found an easy way to control the concurrency of these executions at the meshStack runner level. Currently, the only practical workaround seems to be maintaining a separate agent pool exclusively for these building blocks. Expected behavior We would like to have configurable concurrency limits for building block runners, particularly for asynchronous building blocks. For example: Configure a maximum number of concurrent executions per runner (e.g. 5). Additional runs remain queued in meshStack until execution capacity becomes available. Once an execution finishes, the next queued run is dispatched automatically. Ideally, the concurrency limit could be configured per runner or even per building block definition. This would allow us to control the load on external CI/CD systems without having to introduce dedicated agent pools or implement additional throttling mechanisms in our pipelines. Benefit Configurable concurrency limits would provide better control over external execution capacity, prevent sudden spikes in pipeline workloads, and make asynchronous building blocks easier to operate at scale.
1
Load More
→