claude-code-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LOG_LEVEL | No | Specifies the log level. Possible values: debug, info, warn, error | info |
| CLAUDE_BIN | Yes | Specifies the path to the Claude CLI executable |
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| explain_codeC | Provides detailed explanation of the given code. |
| review_codeD | Reviews the given code. |
| fix_codeC | Fixes bugs or issues in the given code. |
| edit_codeC | Edits the given code based on instructions. |
| test_codeC | Generates tests for the given code. |
| simulate_commandC | Simulates the execution of a given command. |
| your_own_queryC | Sends a custom query with context. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 7 tools
There is significant overlap between edit_code, fix_code, and review_code, as all involve modifying or analyzing code for improvements, which could confuse an agent about which to use for specific tasks. However, explain_code, simulate_command, test_code, and your_own_query have more distinct purposes, providing some clarity.
Most tools follow a consistent verb_noun pattern (e.g., edit_code, explain_code, fix_code), which is predictable and readable. The only deviation is your_own_query, which uses a different style but doesn't severely disrupt the overall consistency.
With 7 tools, the count is well-scoped for a code-focused server, falling within the typical 3-15 range. Each tool appears to serve a specific purpose in code development and analysis, making the set appropriately sized for the domain.
The tool set covers key aspects of code interaction such as editing, explaining, fixing, reviewing, simulating, testing, and custom queries, which aligns well with a code assistant domain. Minor gaps might include operations like code generation or version control integration, but core workflows are adequately supported.