debug-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MODEL | No | The model to use for debugging. Options: deepseek-chat, gpt-4, claude-3-opus, etc. | deepseek-chat |
| CASE_FILE | No | Path to the case file for storing memory. | cases/debug_cases.json |
| MAX_STEPS | No | Maximum number of debugging steps. | 5 |
| DEEPSEEK_API_KEY | Yes | Your DeepSeek API key (or other LLM API key). Required for the debug agent to function. |
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 | {} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| debugC | 排查问题 - 输入错误信息,返回解决方案 |
| search_caseC | 搜索历史案例 |
| list_casesC | 列出所有历史案例 |
| get_statsB | 获取记忆系统统计信息 |
| clear_memoryB | 清空所有记忆 |
| search_codeC | 搜索代码文件 |
| read_fileD | 读取文件内容 |
| grepC | 正则搜索代码 |
| check_syntaxC | 检查文件语法 |
| list_filesC | 列出匹配的文件 |
| refresh_indexB | 刷新文件索引 |
| get_caseB | 获取指定案例详情 |
| delete_caseD | 删除指定案例 |
| mark_effectiveB | 标记案例解决方案是否有效 |
| get_recommended_fixesC | 获取高评价的有效解决方案 |
| pre_check_codeC | 主动预防:检查代码中可能的风险模式 |
| get_weekly_reportB | 获取本周错误报告 |
| get_error_trendsC | 获取错误趋势分析 |
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 18 tools
Most tools have clearly distinct purposes: case memory operations vs. code inspection vs. reporting. The main ambiguity is between search_code and grep (both search code) and between search_case and list_cases, though descriptions partially clarify the differences.
The vast majority follow a consistent snake_case verb_noun pattern (search_case, list_cases, delete_case, read_file, check_syntax). The exceptions are 'grep' and 'debug', which are bare verbs and break the pattern, but the overall convention is strong.
At 18 tools, the set sits in the borderline-heavy range. The count is justified somewhat by spanning case memory, code analysis, and reporting, but it still feels more expansive than a typical debug tool requires.
The case memory lifecycle is well covered (create via debug, read, search, list, delete, mark effectiveness) and code inspection is solid. Minor gaps exist, such as no way to manually add or edit a case, and no direct code modification, but these are workable for the stated debugging purpose.