MCP, file scope and token usage - feature request?

[rmoriz]

MCP

From my understanding of how MCP works, each request from the agent to the model provider includes the tools array with function definitions, descriptions and payload-structure of all configured MCP servers.

For example, when I configure 10 MCP servers with 25 functions each, they will increase every call to the AI model, all the time, because 250 functions have to be described. This of course counts to the token usage/limits.

I wonder if there is a smarter way. Maybe a /MCP or some inline phrase to enable a specific MCP tool for this request or session/context only.

Think about this fictional examples:

e.g.

# list active MCP servers 
/mcp list

# start/connect to MCP server "playwright"
/mcp use playwright

# stop/disconnect
/mcp stop playwright

Or (let's say there is an MCP set up named JIRA for interfacing with JIRA)

Analyze ticket JIRA-1234 in 3 human-readable sentences for a management position %JIRA

Files

To my knowledge, pretty much all files of the local directory will be added to the context which may be beneficial for refactoring, understanding the application etc.

However, sometimes the model should just focus on the prompts and a specific file. 

What about something like:

Using %JIRA analyze status of all tickets mentioned in @output.json

Thanks!

Roland

[Jovana Dunisijevic]

Hey @rmoriz 

Thank you for sharing!

When you configure multiple MCP servers and functions, all of them are included in every agent request. This does increase token usage, as you noticed.

Currently, there isn’t a built-in way to activate only specific tools/functions per request or session using inline commands (like /mcp use). All enabled tools are always exposed to the model.

For files, Rovo Dev CLI tries to include relevant files, but you can help by being specific in your prompt (e.g., “analyze only output.json”). There isn’t yet a prompt modifier to restrict file context, but this is a common feature request.

The team is actively exploring ways to make tool and file exposure more dynamic and efficient, so your feedback is very timely!

If you’d like to see these features prioritised, you're welcome to submit feedback via /feedback in the CLI or the Bug report - Rovo Dev in CLI.

I will either way pass this back to our product team and get their attention!

Kindest regards,

Jovana