Replace token-heavy Jira and GitLab MCPs with CLI skills
I have mixed feelings about this. Task: I have mixed feelings about this. Going all-in on Model Context Protocol (MCP) is definitely a bad idea because I noticed the Jira and GitLab MCPs were consuming an excessive amount of tokens. To solve this, I decided to install their respective CLIs instead so we could find a balance and get the best of both worlds. For example, certain MCPs bring too much overhead, especially when they only handle a single task. Instead of letting the coding agent constantly waste resources re-discovering how to fetch a specific work item field, I had Claude recursively run --help on the CLIs and save all possible actions into separate Markdown files. This approach allowed me to build two lightweight plugins that do exactly what an MCP is supposed to do but with significantly less token consumption. If anyone wants to check out the code or use them, I have open-sourced both repositories on my profile:* * acli-skills: An Atlassian CLI agent skill that maps out Jira commands cleanly. * glab-skills: A GitLab CLI companion built directly for efficient agent workflows. *To maintain visibility with this setup, we also developed a custom [Claude Code](https://code.claude.com/docs/en/plugins) plugin that streams live updates regarding our background operations directly into the console. That said, MCPs are still extremely useful for rapid prototyping and when we build custom internal tools to speed up development. We found them particularly valuable for:* * Sampling: Asking the LLM directly to detect entities and summarize log files. * Notifications: Handling long-running tasks that require fetching data from multiple sources. By logging each step and aggregating them via sampling, a single update is sent back to the coding agent, preventing it from spinning up multiple redundant processes. *; tools: Claude Code. Human role: The original post does not say how a person stayed involved.; limitations: The source does not state specific limitations, costs, or integration constraints beyond the general observation that single-task MCPs have high overhead. Reliability is based on a single user's experience with Claude Code and specific CLI tools. Human approval processes are not detailed, though the workflow implies manual setup of the CLI skills..
Tools
Published on Agent Work Atlas:
Overview
I have mixed feelings about this.
Workflow
I have mixed feelings about this. Going all-in on Model Context Protocol (MCP) is definitely a bad idea because I noticed the Jira and GitLab MCPs were consuming an excessive amount of tokens. To solve this, I decided to install their respective CLIs instead so we could find a balance and get the best of both worlds. For example, certain MCPs bring too much overhead, especially when they only handle a single task. Instead of letting the coding agent constantly waste resources re-discovering how to fetch a specific work item field, I had Claude recursively run --help on the CLIs and save all possible actions into separate Markdown files. This approach allowed me to build two lightweight plugins that do exactly what an MCP is supposed to do but with significantly less token consumption. If anyone wants to check out the code or use them, I have open-sourced both repositories on my profile:* * acli-skills: An Atlassian CLI agent skill that maps out Jira commands cleanly. * glab-skills: A GitLab CLI companion built directly for efficient agent workflows. *To maintain visibility with this setup, we also developed a custom [Claude Code](https://code.claude.com/docs/en/plugins) plugin that streams live updates regarding our background operations directly into the console. That said, MCPs are still extremely useful for rapid prototyping and when we build custom internal tools to speed up development. We found them particularly valuable for:* * Sampling: Asking the LLM directly to detect entities and summarize log files. * Notifications: Handling long-running tasks that require fetching data from multiple sources. By logging each step and aggregating them via sampling, a single update is sent back to the coding agent, preventing it from spinning up multiple redundant processes. *
Reported result
The author reports that the CLI-based plugins achieved the same functionality as MCPs with significantly less token consumption. No specific quantitative metrics or measured performance improvements are provided in the source. The success is attributed to the reduction of redundant resource usage when fetching specific work item fields.
Human role
The original post does not say how a person stayed involved.
Limitations
The source does not state specific limitations, costs, or integration constraints beyond the general observation that single-task MCPs have high overhead. Reliability is based on a single user's experience with Claude Code and specific CLI tools. Human approval processes are not detailed, though the workflow implies manual setup of the CLI skills.
Try it
I want to replicate the workflow of replacing token-heavy MCPs with CLI skills for Jira and GitLab using Claude Code. First, install the Atlassian CLI and GitLab CLI. Then, instruct Claude Code to recursively run --help on these CLIs and save all possible actions into separate Markdown files to create lightweight agent skills. Develop a custom Claude Code plugin to stream live updates of background operations to the console. Keep MCPs only for rapid prototyping, log sampling, and aggregating notifications for long-running tasks. Before finalizing, run a sample task to verify token usage reduction compared to the original MCP setup. Ensure human confirmation is obtained before deploying these changes to production environments. [Replaceable inputs: specific Jira/GitLab project URLs, target token reduction percentage, output directory for Markdown files].
Source reports are not independently verified. Publication date is the catalog publication date, not the original article date.