Skip to main content
Open

CLI client for Miro

Related products:Apps & IntegrationsAPIOther
  • May 19, 2026
  • 2 replies
  • 243 views

Hi there!

It would be great if there was a CLI for Miro so AI agents can perform the same (if not more) actions as allowed with the MCP server. 

CLI has the benefit of not polluting the context (which MCP tools do and can take up lots of context depending on how many tools there are). 

Please see this video from IBM on CLI vs MCP as a reference:

 

With thanks,
Matt

2 replies

Eca
Mironeer
Forum|alt.badge.img+5
  • Mironeer
  • May 19, 2026

Hi ​@Matt Chamberlain 

Thanks so much for taking the time to submit this Wish List idea. Our team will review this and it’s open for votes and comments. 

For those coming across this idea, if you feel this would be helpful for you or your business, please be sure to vote for it and leave a comment about your use case to help our team scope this request!

Thank you again for helping make Miro better!


Hey folks, we use Miro for architectural diagrams and would benefit from an official CLI. Agents do best when they write code [1]. The shell provides a mechanism for composing tools in code via the shell language and pipes. Agents utilize both general purpose languages like Python [6], and DSLs like jq [4], to compose pipelines which can then be saved as new utilities.

CLI tools help to manage context in multiple ways [2][3]:

  • By enabling the composition of output into filters [5], the agent is not forced to consume the full output of a tool call, conserving the context window.
  • By allowing progressive discovery of documentation via --help and man pages, the agent only fills its context with documentation when it needs to utilize the tool. This is similar to the skills mechanism included in some harnesses.

Since the CLI is utilized by both the agent, humans, build pipelines, etc.; any workflows or utilities utilized by the agent can be incorporated into a deterministic workflow.

A CLI could be automatically generated from OpenAPI specifications, in the style of gws [7], which provides a discoverable command hierarchy and encapsulates the specific REST calls.

[1]: https://machinelearning.apple.com/research/codeact
[2]: https://lucumr.pocoo.org/2025/8/18/code-mcps/
[3]: https://blog.cloudflare.com/code-mode/
[4]: https://jqlang.org/
[5]: https://www.cs.dartmouth.edu/~doug/reader.pdf
[6]: https://arxiv.org/pdf/2503.17181v1
[7]: https://github.com/googleworkspace/cli