Code Context Provider MCP
Code-Kontextanbieter MCP
MCP-Server, der Codekontext und -analyse für KI-Assistenten bereitstellt. Extrahiert Verzeichnisstruktur und Codesymbole mithilfe von WebAssembly Tree-Sitter-Parsern ohne native Abhängigkeiten.
Merkmale
Verzeichnisbaumstruktur generieren
Analysieren Sie JavaScript/TypeScript- und Python-Dateien
Codesymbole extrahieren (Funktionen, Variablen, Klassen, Importe, Exporte)
Kompatibel mit dem MCP-Protokoll für die nahtlose Integration mit KI-Assistenten
Related MCP server: syntax-map-mcp
Schnelle Verwendung (MCP-Setup)
Installation über Smithery
So installieren Sie Code Context Provider für Claude Desktop automatisch über Smithery :
npx -y @smithery/cli install @AB498/code-context-provider-mcp --client claudeWindows
{
"mcpServers": {
"code-context-provider-mcp": {
"command": "cmd.exe",
"args": [
"/c",
"npx",
"-y",
"code-context-provider-mcp@latest"
]
}
}
}MacOS/Linux
{
"mcpServers": {
"code-context-provider-mcp": {
"command": "npx",
"args": [
"-y",
"code-context-provider-mcp@latest"
]
}
}
}ODER global mit npm installieren:
npm install -g code-context-provider-mcpVerwenden Sie es dann, indem Sie Folgendes ausführen:
code-context-provider-mcp # if you're not using @latest, you may want to clear the cache for latest version using `Remove-Item -Path "$env:LOCALAPPDATA\npm-cache\_npx" -Recurse -Force` for windows and `rm -rf ~/.npm/_npx` for linux/macosVerfügbare Tools
get_code_context
Analysiert ein Verzeichnis und gibt seine Struktur zusammen mit Codesymbolen zurück (optional).
Parameter:
absolutePath(Zeichenfolge, erforderlich): Absoluter Pfad zum zu analysierenden VerzeichnisanalyzeJs(boolesch, optional): Ob JavaScript-/TypeScript- und Python-Dateien analysiert werden sollen (Standard: false)includeSymbols(Boolesch, optional): Ob Codesymbole in die Antwort aufgenommen werden sollen (Standard: „false“)symbolType(Aufzählung, optional): Typ der einzuschließenden Symbole, wenn includeSymbols wahr ist (Optionen: „Funktionen“, „Variablen“, „Klassen“, „Importe“, „Exporte“, „alle“, Standard: „alle“)filePatterns(Array von Zeichenfolgen, optional): Zu analysierende Dateimuster (z. B. [' .js', ' .py', 'config.*'])maxDepth(Zahl, optional): Maximale Verzeichnistiefe für die Analyse (Standard: 5 Ebenen)
Hinweis: Anonyme Funktionen werden automatisch aus den Ergebnissen herausgefiltert.
Beispiel für Ausgabetext beim Tool-Aufruf
Directory structure for: C:\Users\Admin\Desktop\mcp\context-provider-mcp
Code Analysis Summary:
- Files analyzed: 3
- Total functions: 29
- Total variables: 162
- Total classes: 0
Note: Symbol analysis is supported for JavaScript/TypeScript (.js, .jsx, .ts, .tsx) and Python (.py) files only.
Code analysis limited to a maximum depth of 5 directory levels (default).
├── index.js (39 KB)
│ └── [Analyzed: 22 functions, 150 variables, 0 classes]
│ Functions:
│ - initializeTreeSitter [39:0]
│ - getLanguageFromExtension [107:0]
│ - getPosition [138:24]Beispiele für Dateimuster
Mit dem Parameter filePatterns können Sie angeben, welche Dateien analysiert werden sollen. Dies ist nützlich für komplexe Projekte mit mehreren Sprachen oder bestimmten Dateien.
Beispiele:
["*.js", "*.py"]– Analysieren Sie alle JavaScript- und Python-Dateien["config.*"]- Analysieren Sie alle Konfigurationsdateien unabhängig von der Erweiterung["package.json", "*.config.js"]– Analysieren Sie package.json und alle JavaScript-Konfigurationsdateien[".ts", ".tsx", ".py"]– TypeScript- und Python-Dateien analysieren (unter Verwendung des Erweiterungsformats)
Der Dateimusterabgleich unterstützt:
Einfache Glob-Muster mit Platzhaltern (*)
Direkte Dateierweiterungen (mit oder ohne Punkt)
Genaue Dateinamen
Abwicklung großer Projekte
Bei sehr großen Projekten können Sie den Parameter maxDepth verwenden, um zu begrenzen, wie tief das Tool Verzeichnisse durchsucht:
maxDepth: 2- Analysieren Sie nur das Stammverzeichnis und eine Ebene der UnterverzeichnissemaxDepth: 3- Analysieren Sie das Stammverzeichnis und zwei Ebenen von UnterverzeichnissenmaxDepth: 0– Analysieren Sie nur Dateien im Stammverzeichnis
Dies ist insbesondere in folgenden Fällen nützlich:
Arbeiten mit großen Monorepos
Analysieren von Projekten mit vielen Abhängigkeiten
Konzentrieren Sie sich nur auf den Hauptquellcode und nicht auf Bibliotheken von Drittanbietern
Unterstützte Sprachen
Die Codesymbolanalyse wird unterstützt für:
JavaScript (.js)
JSX (.jsx)
TypeScript (.ts)
TSX (.tsx)
Python (.py)
Durch die Verwendung des Parameters filePatterns können Sie andere Dateitypen in die Verzeichnisstruktur einschließen, die symbolische Analyse kann jedoch eingeschränkt sein.
Entwicklung
Einrichten der Entwicklungsumgebung
# Clone the repository
git clone https://github.com/your-username/code-context-provider-mcp.git
cd code-context-provider-mcp
# Install dependencies
npm install
# Set up WASM parsers
npm run setupNach der Installation
Nach der Installation wird das prepare des Pakets automatisch ausgeführt, um die WASM-Parser herunterzuladen. Sollte der Download aus irgendeinem Grund fehlschlagen, können Benutzer das Setup manuell ausführen:
npx code-context-provider-mcp-setupLizenz
MIT
Weitere Informationen oder Hilfe
Available Tools
1 toolget_code_contextA
Returns Complete Context of a given project directory, including directory tree, and code symbols. Useful for getting a quick overview of a project. Use this tool when you need to get a comprehensive overview of a project's codebase. Useful at the start of a new task.
| Name | Required | Description | Default |
|---|---|---|---|
| absolutePath | Yes | Absolute path to the directory to analyze. For windows, it is recommended to use forward slashes to avoid escaping (e.g. C:/Users/username/Documents/project/src) | |
| analyzeJs | No | Whether to analyze JavaScript/TypeScript and Python files. Returns the count of functions, variables, classes, imports, and exports in the codebase. | |
| includeSymbols | No | Whether to include code symbols in the response. Returns the code symbols for each file. | |
| maxDepth | No | Maximum directory depth for code analysis (default: 5 levels). Directory tree will still be built for all levels. Reduce the depth if you only need a quick overview of the project. | |
| symbolType | No | Type of symbols to include if includeSymbols is true. Otherwise, returns only the directory tree. | all |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It describes what the tool returns (context, directory tree, code symbols) and its usefulness for project overviews, but lacks details on performance, error handling, or specific output format. This provides basic behavioral context but leaves gaps for a tool with 5 parameters.
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 appropriately sized with three sentences that each add value: stating the tool's purpose, its usefulness for overviews, and when to use it. It is front-loaded with the core functionality. A minor deduction for slight redundancy ('useful' appears twice).
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's complexity (5 parameters, no output schema, no annotations), the description is moderately complete. It covers the purpose and usage context but lacks details on output format, error cases, or performance considerations. Without an output schema, more guidance on return values would be beneficial for full contextual understanding.
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 schema description coverage is 100%, so the schema fully documents all 5 parameters. The description does not add any parameter-specific semantics beyond what the schema provides, such as explaining interactions between parameters like analyzeJs and includeSymbols. The baseline score of 3 reflects adequate but not enhanced parameter understanding.
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 clearly states the tool's purpose with specific verbs ('returns complete context') and resources ('project directory, including directory tree, and code symbols'). It distinguishes the tool's comprehensive overview capability, which is well-defined even without sibling tools for comparison.
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?
The description provides clear context for when to use the tool ('useful for getting a quick overview of a project' and 'useful at the start of a new task'). However, it lacks explicit guidance on when not to use it or alternatives, as there are no sibling tools mentioned to differentiate from.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
1 tool update
v1.0.0- First observed
get_code_context
TDQS
Scored across 1 tool
With only one tool, there is no possibility of ambiguity or overlap between tools. The single tool has a clear and distinct purpose focused on providing project context.
The naming follows a consistent verb_noun pattern (get_code_context), and with only one tool, there is no inconsistency to evaluate. The naming is clear and descriptive.
A single tool is generally too few for most MCP server purposes, as it limits functionality and can feel thin. For a 'Code Context Provider', one tool may not cover all potential needs like updating or filtering context, making it borderline inadequate.
The tool set is severely incomplete for the implied domain of code context provision. While it offers a comprehensive overview, there are obvious gaps such as tools for updating context, filtering by file type, or handling specific symbols, which could lead to agent workarounds or failures.
Maintenance
Related MCP Connectors
Codebase graphs, caller impact analysis, and recorded project context for AI coding agents.
Code intelligence for LLMs. Analyze, search, and retrieve code from any public git repository.
Code intelligence for coding agents: semantic, AST, graph, and full-text search. 279+ languages.
Deterministic context layer for your codebase: change impact, blast radius, answers with receipts.
Related MCP Servers
- AlicenseAqualityDmaintenanceEnables AI assistants to understand and navigate codebases through structural analysis. Provides code mapping, symbol search, and impact analysis using ast-grep for accurate parsing of Python, JavaScript, TypeScript, and Go projects.453MIT
- AlicenseCqualityDmaintenanceEnables code analysis of JavaScript, TypeScript, TSX, Python, and Rust files using Tree-sitter, providing symbol listing, definition/reference lookup, AST queries, LSP-style features, and SQLite indexing for efficient cross-file searches.219 npmMIT
- AlicenseNot gradedqualityCmaintenanceProvides a semantic understanding of your codebase by parsing with tree-sitter and building a graph of symbols and dependencies. Enables AI assistants to navigate code, analyze changes, and discover architecture using 18 tools with minimal context overhead.9 npm1MIT
- AlicenseAqualityFmaintenanceA deterministic structural code map server for AI agents, giving them the shape of a codebase (imports, exports, classes, functions, signatures, comments, TODO-markers) without reading whole files into context. Powered by tree-sitter WASM grammars, it runs anywhere Node 18+ works.77 npm1AGPL 3.0