easy-code-reader
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MAVEN_REPO | No | Custom Maven repository path. Defaults to MAVEN_HOME or ~/.m2/repository if not set. | |
| PROJECT_DIR | No | Path to the directory containing local Java projects. Required for local project reading tools. |
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": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_group_idA | 在本地 Maven 仓库中按 artifact_id 查找 groupId 和可读版本，包括 SNAPSHOT 和仅源码包。group_prefix 是完整 groupId 前缀（如 org.springframework），可缩小扫描范围。version_hint 为可选版本子串；每次调用直接搜索当前 Maven 仓库。选择结果中的坐标后使用 read_jar_source 读取源码。 |
| read_jar_sourceA | 读取 Maven JAR 中指定 Java 类的源码。优先使用 sources JAR；SNAPSHOT 优先读取普通包，普通包不存在时回退时间戳包。内部类使用 Outer$Inner，必要时返回外部类源码并附简短提示。默认返回全文；start_line/end_line 为从 1 开始、包含首尾的可选行范围。全文结果包含 class_name、artifact、source_type、code；分段读取附带行数信息，失败设置 isError=true。 |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| Easy Code Reader 使用指南 | 两个 JAR 读取工具的配置与用法 |
TDQS
Scored across 2 tools
The two tools have clearly distinct roles: one resolves Maven coordinates by artifact_id, and the other reads source code from a chosen JAR. There is no meaningful overlap or ambiguity between them.
Both tool names follow the same verb_noun pattern: search_group_id and read_jar_source. The naming is predictable and consistent with the server's purpose.
With only two tools, the surface is minimal, but each tool is substantial and the pair covers the core workflow of finding and reading source. Still, it sits at the thin end of the scale for a general-purpose code reading server.
The two tools cover the main workflow: locate an artifact by artifact_id, then read any class source from the JAR, including internal classes and line ranges. Minor gaps exist, such as no way to browse available classes or search by class name, but the core purpose is well served.