指定されたディレクトリの src 配下のソースコードの関連性を解析するMCPサーバーです。
言語ごとのインポート文を解析し、ファイル間の依存関係を特定します。
Claudeに組み込むことで、Claudeがプロジェクトの依存関係を素早く確認でき、関連するファイルの特定に役立ちます。
複数言語のインポート解析をサポート
TypeScript/JavaScript: import文、require文
Python: import文、from ... import文
Ruby: require文、require_relative文
Rust: mod宣言、use文
tsconfig.jsonのパスエイリアス（@/components/...など）に対応
言語ごとの特殊な機能に対応
Python: __init__.py、相対インポート
Rust: mod.rsパターン
TypeScript: エイリアス、index.ts
Ruby: 拡張子なしのrequire
Related MCP server: QoutaMCP
Python 3.10以上
uv
# uvのインストール
$ curl -LsSf https://astral.sh/uv/install.sh | sh
$ cd /path/to/mcp-source-relation
# ライブラリのインストール
$ uv syncclaude_desktop_config.json に以下の設定を追加してください：
{
"mcpServers": {
"source-relation": {
"command": "uv",
"args": [
"--directory",
"/path/to/mcp-source-relation", # このプロジェクトディレクトリの絶対パスに書き換えてください
"run",
"source_relation.py"
]
}
}
}/Users/xxx/GitHub/xxx/ のソースの依存関係を確認して のように指示すると動作します
`/Users/owa/GitHub/mcp-source-relation/` のソースコードの依存関係を確認してみましょう。
依存関係の分析結果から、以下のような構造が確認できます：
1. メインの解析モジュール: `src/source_analyzer.py`
- 各言語固有の解析モジュールを利用しています（Ruby, Python, TypeScript, Rust）
2. 言語別の解析モジュール:
- `src/analyzers/ruby.py`
- `src/analyzers/python.py`
- `src/analyzers/typescript.py`
- `src/analyzers/rust.py`
- すべて `src/analyzers/base.py` を継承しています
3. 共通基盤:
- `src/analyzers/base.py`: 基本的な解析機能を提供
- `src/utils/path.py`: パス操作のユーティリティ
- `src/configs/typescript.py`: TypeScript固有の設定
特徴的な点：
- 各言語の解析モジュールは共通の基底クラス（base.py）を継承しており、一貫性のある設計になっています
- TypeScriptのみ独自の設定ファイル（configs/typescript.py）を持っています
- パス操作は共通のユーティリティモジュール（utils/path.py）に集約されています
この構造から、新しい言語のサポートを追加する場合は、`src/analyzers/` に新しいモジュールを追加し、`base.py` を継承することで実現できる設計になっていることがわかります。ディレクトリを指定した場合はその下の src ディレクトリを解析します
ファイルを指定した場合はそのファイルを基準に解析します
promptからのパス入力にも対応しています
promptで利用する場合は、Attach from MCP->Choose an integration->source-relationを選択してください
解析結果は以下のようなJSON形式で出力されます：
{
"dependencies": {
"components/Button.tsx": [
"types/index.ts",
"utils/theme.ts"
],
"pages/index.tsx": [
"components/Button.tsx",
"utils/api.ts"
]
}
}すべてのパスはsrcディレクトリを基準とした相対パスで表示されます。
import { Component } from './Component'
import type { Type } from '@/types'
import './styles.css'
require('./module')
エイリアスパス（@/components/...）
import module
from module import name
from .module import name
from ..module import name
require 'module'
require_relative './module'
拡張子なしのrequire
mod module;
use crate::module;
use super::module;
use self::module;
Analyze dependencies between source files
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. The description only states what the tool does at a high level ('analyze dependencies'), but doesn't disclose behavioral traits like whether this is a read-only operation, what format the analysis returns, whether it has side effects, performance characteristics, or error conditions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise at just 5 words with no wasted language. It's front-loaded with the core purpose and uses efficient phrasing. Every word earns its place in conveying the basic function.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has no annotations, no output schema, and 0% schema description coverage, the description is completely inadequate. For a tool that performs analysis (potentially complex), the description provides minimal context about what analysis means, what results to expect, or how to interpret them.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description provides no information about parameters. With 0% schema description coverage and a single required parameter 'path', the description doesn't compensate at all - it doesn't explain what the path parameter represents, what format it expects, or how it relates to the dependency analysis.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Analyze dependencies between source files' states a general purpose (analyzing dependencies) and resource (source files), but lacks specificity about what kind of analysis is performed or what 'dependencies' means in this context. It doesn't distinguish from siblings, but there are no sibling tools to differentiate from.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives, prerequisites, or constraints. The description implies it's for dependency analysis, but doesn't specify scenarios where this is appropriate or what problems it solves.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
get_source_relationScored across 1 tool
With only one tool, there is no possibility of ambiguity or overlap between tools. The single tool has a clearly defined purpose of analyzing dependencies between source files, making it impossible for an agent to misselect between non-existent alternatives.
A single tool inherently exhibits perfect naming consistency, as there are no other tools to compare against. The tool name 'get_source_relation' follows a clear verb_noun pattern, which would be consistent if more tools existed.
A single tool is generally too few for most server purposes, as it limits functionality and suggests an incomplete or overly narrow scope. While it might be appropriate for a highly specialized task, it feels thin and insufficient for comprehensive source dependency analysis, which typically involves multiple operations like listing, updating, or visualizing relations.
The tool set is severely incomplete for the inferred domain of source dependency analysis. With only a 'get' operation, there are obvious gaps such as creating, updating, deleting, or listing source relations, and no support for lifecycle management or advanced queries. This will likely cause agent failures when more complex operations are needed.
Generate SBOMs, scan vulnerabilities, and analyze dependencies from local projects or Git repos.
AI-powered codebase analysis — call graphs, security, dead code, complexity. 150+ tools.
Code intelligence for coding agents: semantic, AST, graph, and full-text search. 279+ languages.
Code intelligence platform for AI agents. 20 tools for architecture, security & impact analysis.
