chore: go back to byethrow mcp server - #542
Conversation
WalkthroughReplaces the “byethrow” MCP server config with “@praha/byethrow,” adding type and env, and simplifying args in .mcp.json. Removes a related tip from CLAUDE.md. Adds @praha/byethrow-mcp as a devDependency in package.json. No runtime code changes. Changes
Estimated code review effort🎯 2 (Simple) | ⏱️ ~10 minutes Possibly related PRs
Poem
✨ Finishing Touches🧪 Generate unit tests
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. 🪧 TipsChatThere are 3 ways to chat with CodeRabbit:
SupportNeed help? Create a ticket on our support page for assistance with any issues or questions. CodeRabbit Commands (Invoked using PR/Issue comments)Type Other keywords and placeholders
CodeRabbit Configuration File (
|
Deploying with
|
| Status | Name | Latest Commit | Preview URL | Updated (UTC) |
|---|---|---|---|---|
| ✅ Deployment successful! View logs |
ccusage-guide | 63f02e6 | Commit Preview URL Branch Preview URL |
Aug 18 2025, 09:35 AM |
There was a problem hiding this comment.
Summary of Changes
Hello @ryoppippi, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!
This pull request updates the project's configuration to integrate with the byethrow Model Context Protocol (MCP) server using a dedicated package. It refactors the existing byethrow setup to leverage the new @praha/byethrow-mcp package, streamlining its execution and dependency management. This change aims to improve the consistency and maintainability of the MCP server integration.
Highlights
- Refactored Byethrow MCP Configuration: The
.mcp.jsonfile'sbyethrowentry has been updated to@praha/byethrow, changing its execution method from a genericsitemcpcommand to a direct call tobun byethrow-mcp, indicating a shift to a dedicated executable. - New Dependency for Byethrow MCP: The
@praha/byethrow-mcppackage has been added topackage.jsonandbun.lock, formalizing the dependency on the new dedicated Byethrow MCP server implementation. - Documentation Cleanup: The
CLAUDE.mdfile has been modified to remove an outdated or no longer relevant documentation link for thebyethrowMCP server.
Using Gemini Code Assist
The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.
Invoking Gemini
You can request assistance from Gemini at any point in your pull request via creating an issue comment (i.e. comment on the pull request page) using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands.
| Feature | Command | Description |
|---|---|---|
| Code Review | /gemini review |
Performs a code review for the current pull request in its current state. |
| Pull Request Summary | /gemini summary |
Provides a summary of the current pull request in its current state. |
| Comment | @gemini-code-assist | Responds in comments when explicitly tagged, both in issue comments and review comments. |
| Help | /gemini help |
Displays a list of available commands. |
Customization
To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.
Limitations & Feedback
Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.
You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.
Footnotes
-
Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩
commit: |
|
Review the following changes in direct dependencies. Learn more about Socket for GitHub.
|
There was a problem hiding this comment.
Code Review
This pull request updates the byethrow MCP server configuration to use a local package (@praha/byethrow-mcp) instead of fetching from a remote URL via sitemcp. The changes are consistent across the configuration file, documentation, and package dependencies. I have one suggestion regarding the new configuration in .mcp.json to improve its clarity and address a potential breaking change.
| "@praha/byethrow": { | ||
| "type": "stdio", | ||
| "command": "bun", | ||
| "args": [ | ||
| "x", | ||
| "sitemcp", | ||
| "https://praha-inc.github.io/byethrow/", | ||
| "--concurrency 10", | ||
| "--no-cache" | ||
| ] | ||
| "byethrow-mcp" | ||
| ], | ||
| "env": {} | ||
| } |
There was a problem hiding this comment.
This change introduces two points for consideration:
- Breaking Change: The key for the byethrow MCP server has been changed from
"byethrow"to"@praha/byethrow". This is a breaking change for any tools or scripts that consume this configuration file. All consumers must be updated to use the new key. - Redundant Property: The
envproperty is an empty object and can be removed for simplicity if no environment variables are needed.
"@praha/byethrow": {
"type": "stdio",
"command": "bun",
"args": [
"byethrow-mcp"
]
}
There was a problem hiding this comment.
Actionable comments posted: 1
🧹 Nitpick comments (1)
.mcp.json (1)
31-31: Nit: remove empty env block to reduce noise
"env": {}is redundant if you don’t need any variables. Consider removing it for a cleaner config.- ], - "env": {} + ]
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro
💡 Knowledge Base configuration:
- MCP integration is disabled by default for public repositories
- Jira integration is disabled by default for public repositories
- Linear integration is disabled by default for public repositories
You can enable these sources in your CodeRabbit configuration.
⛔ Files ignored due to path filters (1)
bun.lockis excluded by!**/*.lock
📒 Files selected for processing (3)
.mcp.json(1 hunks)CLAUDE.md(0 hunks)package.json(1 hunks)
💤 Files with no reviewable changes (1)
- CLAUDE.md
🧰 Additional context used
📓 Path-based instructions (1)
package.json
📄 CodeRabbit Inference Engine (CLAUDE.md)
Dependencies should be added as devDependencies unless explicitly requested otherwise
Files:
package.json
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (1)
- GitHub Check: Workers Builds: ccusage-guide
🔇 Additional comments (2)
package.json (1)
72-72: Dev dependency addition aligns with guidelinesAdding "@praha/byethrow-mcp" under devDependencies is correct and matches the project’s usage pattern and the provided coding guideline.
.mcp.json (1)
26-26: LGTM on stdio type
"type": "stdio"is appropriate for an MCP server launched via a local process.
| "@praha/byethrow": { | ||
| "type": "stdio", | ||
| "command": "bun", | ||
| "args": [ | ||
| "x", | ||
| "sitemcp", | ||
| "https://praha-inc.github.io/byethrow/", | ||
| "--concurrency 10", | ||
| "--no-cache" | ||
| ] | ||
| "byethrow-mcp" | ||
| ], | ||
| "env": {} | ||
| } |
There was a problem hiding this comment.
Fix command invocation: use bun x or bunx to resolve the binary
With "command": "bun" and "args": ["byethrow-mcp"], Bun will try to run a local file named byethrow-mcp rather than resolve the package binary. To execute an npm-style binary, you need Bun’s x-runner. Use either bun x byethrow-mcp or bunx byethrow-mcp.
Apply one of the following diffs (preferred: use bunx):
Option A (preferred, simpler):
- "command": "bun",
- "args": [
- "byethrow-mcp"
- ],
+ "command": "bunx",
+ "args": [
+ "byethrow-mcp"
+ ],Option B (keep command as bun, call x subcommand):
"command": "bun",
"args": [
- "byethrow-mcp"
+ "x",
+ "byethrow-mcp"
],📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| "@praha/byethrow": { | |
| "type": "stdio", | |
| "command": "bun", | |
| "args": [ | |
| "x", | |
| "sitemcp", | |
| "https://praha-inc.github.io/byethrow/", | |
| "--concurrency 10", | |
| "--no-cache" | |
| ] | |
| "byethrow-mcp" | |
| ], | |
| "env": {} | |
| } | |
| "@praha/byethrow": { | |
| "type": "stdio", | |
| "command": "bunx", | |
| "args": [ | |
| "byethrow-mcp" | |
| ], | |
| "env": {} | |
| } |
🤖 Prompt for AI Agents
In .mcp.json around lines 25 to 32 the run configuration uses "command": "bun"
with args ["byethrow-mcp"], which makes Bun try to execute a local file instead
of resolving the package binary; replace this by using Bun's x-runner: either
set "command" to "bunx" and keep args ["byethrow-mcp"], or keep "command": "bun"
and change args to ["x", "byethrow-mcp"] so the package binary is correctly
resolved and executed.
Summary by CodeRabbit
Chores
Documentation