CodeRabbit CLI MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| TSX_BANNER | No | Controls whether tsx displays a banner | false |
| CODERRABBIT_MCP_LOCK_MODE | No | Pre-configured mode for CodeRabbit CLI output format (interactive|plain|prompt-only) | |
| CODERRABBIT_MCP_LOCK_TYPE | No | Pre-configured diff scope for CodeRabbit (all|committed|uncommitted) | |
| CODERRABBIT_TOOL_TIMEOUT_SEC | No | Tool timeout in seconds, should match tool_timeout_sec configuration | |
| CODERRABBIT_MCP_LOCK_CONFIG_FILES | No | JSON array of config file paths for CodeRabbit's -c flag (e.g., "[".coderabbit.yaml"]") |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| logging | {
"levels": [
"debug",
"info",
"notice",
"warning",
"error"
]
} |
| prompts | {
"listChanged": true
} |
| resources | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| run_reviewD | – |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| review_local_uncommitted | Run CodeRabbit review on uncommitted changes with plain output. |
| review_all_plain | Review entire repository with default plain output. |
| prompt_only_uncommitted | Minimal prompt-only run against uncommitted diff for LLM agents. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 1 tool
With only one tool, there is no possibility of confusing it with another. The single tool's purpose is unambiguous within the set, even though its description is missing.
The tool name 'run_review' follows a clear verb_noun pattern. Since there is only one tool, naming consistency is trivially maintained.
A single tool is extremely thin for a server claiming to represent a CLI. Even a narrow-purpose server typically needs more than one operation to be useful, making this count feel inadequate.
The server only offers 'run_review', with no way to retrieve review results, list past reviews, or manage settings. This severely limits the functionality and leaves obvious gaps for any real-world workflow.