MCP server de ContextPack
Commit 7 nov 2026Converts codebases, directories, and Git diffs into token-budgeted, LLM-ready context in XML, Markdown, or llms.txt formats.
También conocido como fastpresspages/contextpack
- Stars
- 0
- Herramientas
- —
- Descargas, 30 días
- —
- Última versión
- —
- Último commit
- 7 nov 2026
- Licencia
- Apache-2.0
¿Qué es ContextPack MCP?
Converts codebases, directories, and Git diffs into token-budgeted, LLM-ready context in XML, Markdown, or llms.txt formats.
Resumen generado a partir del README del proyecto
Acerca del MCP server de ContextPack
Preparing codebases and Git diffs for large language models is what ContextPack enables for developers using Claude, GPT, or DeepSeek. This tool converts directories and file changes into structured context using XML, Markdown, or llms.txt formats. It functions as a local CLI, a Node.js library, or a stdio-ready MCP server that integrates with environments like Claude Desktop, Cursor, and Zed.
Users can manage prompt size by setting specific token budgets, such as 32k or 128k, ensuring that the most important files are prioritized without overflowing the model. The server includes specialized tools like pack_codebase for directory packing, get_tree for visual directory structures, pack_diff for Git changes, and estimate_tokens for calculating text length. It automatically respects .gitignore files and skips binary data or build artifacts like node_modules to keep the context clean and relevant.
Qué puedes hacer con él
- 1Manage token limits for promptsA developer can specify a maximum token ceiling to ensure their codebase context fits within the model's window.
- 2Provide Git diffs to AI agentsYou can send only the staged or unstaged changes from a Git repository to an AI to explain recent code modifications.
- 3Visualize project structureGenerate an ASCII or Unicode directory tree to give an AI a high-level overview of the file system.
- 4Automate context creation in CI/CDIntegrate context packing into GitHub Workflows to prepare data for automated pull request reviews.
Escrito a partir del README del proyecto. Cada caso de uso se verifica con una cita del mismo.
Verificaciones automáticas
Ejecutado 15 nov 2026Informe completo →Aún no verificado. Un servidor necesita una puntuación de 80, ningún hallazgo grave y suficientes datos para que podamos revisarlo. Cómo funcionan las verificaciones · Qué corregir para obtener más puntos
- Repositorio de origen vinculado y accesiblefastpresspages/contextpack is public and reachablegithub.com/fastpresspages/contextpack ↗Aprobado
- El paquete indica este repositorio como su origenNo verificado
- Procedencia de la compilación (atestación de Sigstore)No verificado
- Licencia de código abierto (OSI)Apache-2.0spdx.org/licenses/Apache-2.0.html ↗Aprobado
- Commit o lanzamiento en el último añoLast commit or release 2026-11-07github.com/fastpresspages/contextpack ↗Aprobado
- OpenSSF ScorecardNo verificado
- El nombre del paquete no es similar a un paquete popularNo verificado
- No hay avisos críticos en el paquete ni en sus dependenciasNo verificado
- Sin instrucciones ocultas para el modelo0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersAprobado
- Las herramientas destructivas están etiquetadasNo verificado
- El endpoint remoto responde al handshake de MCPNo verificado
README
Ver en GitHubContextPack 📦
Pack codebases, directories, and Git diffs into token-budgeted, LLM-ready context.
Website · MCP Spec · GitHub Action · FastPress Labs
ContextPack is a 100% free, zero-runtime-dependency CLI, Node.js library, and Model Context Protocol (MCP) server that turns any codebase, subdirectory, or Git diff into clean, token-budgeted context for Claude, GPT, DeepSeek, and coding agents.
It formats context in Anthropic-standard XML (<documents><document>), Markdown, or llms-full.txt, includes an ASCII/Unicode directory tree, integrates staged/unstaged Git diffs, and respects token budgets so your prompts never overflow.
Why ContextPack?
- ⚡ Zero runtime dependencies: Pure Node.js standard library (
node:fs,node:path,node:child_process,node:crypto). Fast startup, zero supply-chain risk. - 🎯 Token-Budget Aware: Specify
--max-tokens 32k(or64k,128k). ContextPack prioritizes key files and warns if files had to be omitted. - 🤖 First-Class MCP Server: Native stdio MCP server (
contextpack-mcp) ready for Claude Code, OpenCode, Cursor, and Zed with tools forpack_codebase,get_tree,pack_diff, andestimate_tokens. - 📁 Smart Filtering: Automatically respects
.gitignore, skips binary files, and ignores build artifacts (node_modules,dist, lockfiles). - 🔄 Git Diff Integration: Pack only changed files, staged files, or append full git diffs with line-level context.
- 🛠️ Composite GitHub Action: Pack repos in CI/CD pipelines and export token counts and packed artifacts for LLM review steps.
Quick Start
1. Run via npx (no install required)
# Pack current directory into Anthropic XML format
npx -p github:fastpresspages/contextpack contextpack .
# Pack into Markdown with a 32,000 token budget
npx -p github:fastpresspages/contextpack contextpack src/ -f markdown -t 32k -o context.md
# Pack only Git diff & modified files against main
npx -p github:fastpresspages/contextpack contextpack . --git-diff --diff-target main -o diff-context.xml
# Just generate an ASCII directory tree with file sizes
npx -p github:fastpresspages/contextpack contextpack . --tree-only
# Generate an llms-full.txt file for your documentation site
npx -p github:fastpresspages/contextpack contextpack . --llms-txt -o site/llms-full.txt
2. Connect to AI Agents via MCP
Add ContextPack to your Claude Desktop, OpenCode, or Cursor MCP configuration:
{
"mcpServers": {
"contextpack": {
"command": "npx",
"args": ["-y", "-p", "github:fastpresspages/contextpack", "contextpack-mcp"]
}
}
}
Available MCP tools:
pack_codebase: Pack directory or files into token-capped XML, Markdown, or llms.txt.get_tree: Return visual directory structure with token estimates and file counts.pack_diff: Pack staged or unstaged Git diffs with changed file contents.estimate_tokens: Fast token count approximation for any text or local file.
Output Formats
1. XML (--format xml / default)
Strict prompt structure modeled on Anthropic best practices:
<documents>
<directory_tree>
├── src/
│ ├── index.js (1.2 KB)
│ └── pack.js (8.4 KB)
└── package.json (820 B)
</directory_tree>
<document index="1">
<source>src/index.js</source>
<document_content>
1: export * from './pack.js';
...
</document_content>
</document>
</documents>
2. Markdown (--format markdown)
Clean, human-readable markdown with language code blocks:
# Codebase Context
## Directory Tree
\`\`\`
...
\`\`\`
## Codebase Contents
### `src/index.js`
\`\`\`javascript
1: export * from './pack.js';
...
\`\`\`
3. LLMS Full Text (--format llms / --llms-txt)
Structured context designed for /llms-full.txt endpoints following the llms.txt convention.
CLI Options
Usage: contextpack [target_dir_or_file] [options]
Options:
-o, --out <path> Write output to file instead of stdout
-f, --format <format> Output format: xml, markdown, llms, json (default: xml)
-t, --max-tokens <tokens> Token budget ceiling (e.g. 16k, 32k, 128k, 200000)
-g, --git-diff Include Git diff in output
--staged Include only staged changes in Git diff
--diff-target <ref> Git ref to diff against (e.g. main, HEAD~1)
--tree-only Output only the visual directory tree
--tokens-only Calculate and print token estimation only
--llms-txt Shortcut for --format llms
--include <pattern> Comma-separated glob-style patterns to include
--exclude <pattern> Comma-separated glob-style patterns to exclude
--max-depth <n> Maximum directory traversal depth (default: 8)
--max-file-size <kb> Max file size in KB to include (default: 500)
--no-tree Omit the directory tree from context
--no-line-numbers Omit 1-based line numbers in file content
--summary Print packing summary to stderr
-v, --version Show ContextPack version
-h, --help Show help information
GitHub Action
Use fastpresspages/contextpack in your GitHub Workflows to prepare context for automated AI PR reviews, changelog generation, or docs updates:
- name: Pack Repository Context
uses: fastpresspages/contextpack@main
id: pack
with:
path: '.'
format: 'xml'
max-tokens: '64k'
with-tree: 'true'
git-diff: 'true'
out: 'context.xml'
- name: Inspect Packing Stats
run: |
echo "Packed ${{ steps.pack.outputs.files }} files"
echo "Total tokens: ${{ steps.pack.outputs.tokens }}"
echo "Omitted files: ${{ steps.pack.outputs.omitted }}"
Node.js Programmatic API
ContextPack can be imported directly in ESM or Node 18+:
import { pack, countTokens, buildTree } from 'contextpack';
const result = await pack({
path: './src',
format: 'xml',
maxTokens: 32000,
includeTree: true,
includeGitDiff: false
});
console.log(`Packed ${result.totalFiles} files (${result.tokens} tokens)`);
console.log(result.output);
Verification & Testing
ContextPack includes a comprehensive native test suite using node:test:
# Run unit & integration tests
node --test test/*.test.js
# Test CLI directly
node bin/contextpack.js . --tokens-only
License
Apache-2.0. Maintained by FastPress Labs. Free forever, no telemetry, no paid APIs.
Preguntas sobre ContextPack MCP
What formats does ContextPack support?
It supports Anthropic-standard XML, Markdown, and the llms.txt convention.