Local-first documentation for AI agents. Offline, instant, private doc retrieval.
AI agents are trained on outdated docs. When libraries release new versions, your AI doesn't know — and confidently gives you wrong answers.
// Your AI, mass-trained on AI SDK v5 docs, will suggest:
import { Experimental_Agent as Agent, stepCountIs } from 'ai';
// But v6 changed the API entirely:
import { ToolLoopAgent } from 'ai';The fix isn't better prompting. It's giving your AI the right docs.
Context is an MCP server backed by a community-driven package registry with 100+ popular libraries already built and ready to use. When your AI agent needs documentation, it searches the registry, downloads the right package, and queries it locally — all automatically.
Install once. Configure once. Then just ask your AI.
npm install -g @neuledge/contextContext works with any MCP-compatible agent. Pick yours:
<details> <summary><strong>Claude Code</strong></summary>claude mcp add context -- context serveAdd to your config file:
~/.config/claude/claude_desktop_config.json~/Library/Application Support/Claude/claude_desktop_config.json%APPDATA%\Claude\claude_desktop_config.json{
"mcpServers": {
"context": {
"command": "context",
"args": ["serve"]
}
}
}Restart Claude Desktop to apply changes.
</details> <details> <summary><strong>Cursor</strong></summary>Add to ~/.cursor/mcp.json (global) or .cursor/mcp.json (project-specific):
{
"mcpServers": {
"context": {
"command": "context",
"args": ["serve"]
}
}
}Or use Settings > Developer > Edit Config to add the server through the UI.
</details> <details> <summary><strong>OpenAI Codex</strong></summary>Either use the CLI
codex mcp add context -- context serveOr add to ~/.codex/config.toml (global) or .codex/config.toml (project-specific):
[mcp_servers.context]
command = "context"
args = ["serve"]Restart OpenAI Codex to apply changes.
</details> <details> <summary><strong>VS Code (GitHub Copilot)</strong></summary>Requires VS Code 1.102+ with GitHub Copilot
Add to .vscode/mcp.json in your workspace:
{
"servers": {
"context": {
"type": "stdio",
"command": "context",
"args": ["serve"]
}
}
}Click the Start button that appears in the file, then use Agent mode in Copilot Chat.
</details> <details> <summary><strong>Windsurf</strong></summary>Add to ~/.codeium/windsurf/mcp_config.json:
%USERPROFILE%\.codeium\windsurf\mcp_config.json{
"mcpServers": {
"context": {
"command": "context",
"args": ["serve"]
}
}
}Or access via Windsurf Settings > Cascade > MCP Servers.
</details> <details> <summary><strong>Zed</strong></summary>Add to your Zed settings (cmd+, or ctrl+,):
{
"context_servers": {
"context": {
"command": {
"path": "context",
"args": ["serve"]
}
}
}
}Check the Agent Panel settings to verify the server shows a green indicator.
</details> <details> <summary><strong>Goose</strong></summary>Run goose configure and select Command-line Extension, or add directly to ~/.config/goose/config.yaml:
extensions:
context:
type: stdio
command: context
args:
- serve
timeout: 300That's it. Just ask:
"How do I create middleware in Next.js?"
Your agent searches the community registry, downloads the docs, and answers with accurate, version-specific information. Everything happens automatically — no manual context install needed for registry packages.
The registry is what makes Context plug and play. It's a growing collection of 100+ pre-built documentation packages maintained by the community. Think of it like a package manager, but for AI-ready docs.
Popular packages available today:
| Category | Libraries |
|---|---|
| Frameworks | Next.js, Nuxt, Astro, SvelteKit, Remix, Hono |
| React ecosystem | React, React Router, TanStack Query, Zustand, Redux Toolkit |
| Databases & ORMs | Prisma, Drizzle, Mongoose, TypeORM |
| Styling | Tailwind CSS, shadcn/ui, Styled Components |
| Testing | Vitest, Playwright, Jest, Testing Library |
| APIs & Auth | tRPC, GraphQL, NextAuth.js, Passport |
| AI & LLMs | LangChain, AI SDK, OpenAI, Anthropic SDK |
Anyone can contribute. If a library you use isn't listed, submit a PR to add it — your contribution helps every Context user.
Context runs entirely on your machine. Docs are downloaded once and stored as compact SQLite databases in ~/.context/packages/. After that, everything is local.
The registry covers popular open-source libraries, but Context also works with any documentation source. Use context add to build packages from private repos, internal libraries, or anything not yet in the registry.
# Build from a git repository
context add https://github.com/your-company/design-system
# Build from a local directory
context add ./my-project
# Specific version tag
context add https://github.com/vercel/next.js/tree/v16.0.0Once built, share packages with your team — they're portable .db files that install instantly:
# Export a package
context add ./my-project --name my-lib --pkg-version 2.0 --save ./packages/
# Teammate installs it (no build step needed)
context add ./packages/my-lib@2.0.dbRun Context as a containerized HTTP server for multi-client or Kubernetes deployments:
# Run from the repository root (required for the monorepo lockfile)
docker build -t context:local -f packages/context/Dockerfile .
docker run --rm -p 8080:8080 context:localThe container starts Context with HTTP transport on port 8080, accessible at http://localhost:8080/mcp. The image uses a multi-stage build with node:22-bookworm-slim for native module compatibility.
context browse <package>Search for packages available on the registry server.
# Browse by registry/name
context browse npm/next
# Output:
# npm/next@15.1.3 3.4 MB The React Framework for the Web
# npm/next@15.0.4 3.2 MB The React Framework for the Web
# ...
#
# Found 12 versions. Install with: context install npm/next
# Browse with just a name (defaults to npm)
context browse reactcontext install <registry/name> [version]Download and install a pre-built package from the registry server.
# Install latest version
context install npm/next
# Install a specific version
context install npm/next 15.0.4
# Install from other registries
context install pip/djangocontext add <source>Build and install a documentation package from source. Use this for libraries not in the registry, or for private/internal docs. The source type is auto-detected.
From git repository:
Works with GitHub, GitLab, Bitbucket, Codeberg, or any git URL:
# HTTPS URLs
context add https://github.com/vercel/next.js
context add https://gitlab.com/org/repo
context add https://bitbucket.org/org/repo
# Specific tag or branch
context add https://github.com/vercel/next.js/tree/v16.0.0
# SSH URLs
context add git@github.com:user/repo.git
context add ssh://git@github.com/user/repo.git
# Custom options
context add https://github.com/vercel/next.js --path packages/docs --name nextjsFrom local directory:
Build a package from documentation in a local folder:
# Auto-detects docs folder (docs/, documentation/, doc/)
context add ./my-project
# Specify docs path explicitly
context add /path/to/repo --path docs
# Custom package name and version
context add ./my-lib --name my-library --pkg-version 1.0.0| Option | Description |
|---|---|
--pkg-version <version> | Custom version label |
--path <path> | Path to docs folder in repo/directory |
--name <name> | Custom package name |
--save <path> | Save a copy of the package to the specified path |
Saving packages for sharing:
# Save to a directory (auto-names as name@version.db)
context add https://github.com/vercel/next.js --save ./packages/
# Save to a specific file
context add ./my-docs --save ./my-package.dbFrom URL:
context add https://cdn.example.com/react@18.dbFrom local file:
context add ./nextjs@15.0.dbFinding the right documentation repository:
Many popular projects keep their documentation in a separate repository from their main codebase. If you see a warning about few sections found, the docs likely live elsewhere:
# Example: React's docs are in a separate repo
context add https://github.com/facebook/react
# ⚠️ Warning: Only 45 sections found...
# The warning includes a Google search link to help find the docs repo
# The actual React docs repository:
context add https://github.com/reactjs/react.devCommon patterns for documentation repositories:
project-docs (e.g., prisma/docs)project.dev or project.io (e.g., reactjs/react.dev)project-website (e.g., expressjs/expressjs.com)When the CLI detects few documentation sections, it will show a Google search link to help you find the correct repository.
context listShow installed packages.
$ context list
Installed packages:
nextjs@16.0 4.2 MB 847 sections
react@18 2.1 MB 423 sections
Total: 2 packages (6.3 MB)context remove <name>Remove a package.
context remove nextjscontext serveStart the MCP server (used by AI agents).
# Stdio transport (default, for single-client MCP integrations)
context serve
# HTTP transport (for multi-client access over the network)
context serve --http
context serve --http 3000
context serve --http 3000 --host 0.0.0.0| Option | Description |
|---|---|
--http [port] | Start as HTTP server instead of stdio (default port: 8080) |
--host <host> | Host to bind to (default: 127.0.0.1) |
The HTTP transport uses the MCP Streamable HTTP protocol, enabling multiple clients on the local network to connect to a single server instance. The endpoint is available at http://<host>:<port>/mcp.
context query <library> <topic>Query documentation directly from the command line. Useful for testing and debugging.
# Query a package (use name@version format from 'context list')
context query 'nextjs@16.0' 'middleware authentication'
# Returns the same JSON format as the MCP get_docs tool┌─────────────────────────────────────────────────────────┐
│ Your Machine │
│ │
│ ┌──────────┐ ┌──────────────────┐ ┌────────────┐ │
│ │ AI │ │ Context MCP │ │ ~/.context │ │
│ │ Agent │───▶│ Server │───▶│ /packages │ │
│ │ │ │ │ └────────────┘ │
│ └──────────┘ └────────┬─────────┘ │ │
│ │ ┌──────────┐ │
│ │ │ SQLite │ │
│ │ │ FTS5 │ │
│ │ └──────────┘ │
└───────────────────────────┼─────────────────────────────┘
│ (first use only)
▼
┌────────────────┐
│ Community │
│ Registry │
└────────────────┘First time you ask about a library:
.db file)~/.context/packages/Every time after:
Yes! Context is language-agnostic. It natively supports Markdown (.md, .mdx), AsciiDoc (.adoc), reStructuredText (.rst), and HTML — no conversion needed.
# Python - FastAPI (Markdown)
context add https://github.com/fastapi/fastapi --path docs/en/docs
# Python - Django (reStructuredText)
context add https://github.com/django/django --path docs
# Java - Spring Boot (AsciiDoc)
context add https://github.com/spring-projects/spring-boot --path spring-boot-project/spring-boot-docs/src/docs
# Rust - The Rust Book
context add https://github.com/rust-lang/book --path srcPoint Context at the docs folder with --path and it handles the rest.
Yes! The registry/ directory has YAML definitions organized by package manager:
registry/npm/ — JavaScript/TypeScript (Next.js, React, Tailwind, etc.)registry/pip/ — Python (FastAPI, Flask, Django, Pydantic)registry/maven/ — Java (Spring Boot, JUnit, Micrometer)To add a package, create a YAML file. Two source types are supported:
Git source — clone a repo at a version tag:
# registry/pip/my-library.yaml
name: my-library
description: "Short description of the library"
repository: https://github.com/org/my-library
versions:
- min_version: "2.0.0"
source:
type: git
url: https://github.com/org/my-library
docs_path: docs
tag_pattern: "v{version}"ZIP source — download HTML docs from a URL (supports {version} placeholder):
# registry/python/python.yaml
name: python
description: "Python programming language official documentation"
versions:
- versions: ["3.14", "3.13", "3.12"]
source:
type: zip
url: "https://docs.python.org/3/archives/python-{version}-docs-html.zip"
docs_path: "python-{version}-docs-html"
exclude_paths:
- "whatsnew/**"
- "changelog.html"Version discovery is supported for npm, PyPI, and Maven Central. See existing definitions for examples.
# Install dependencies
pnpm install
# Build
pnpm build
# Test
pnpm test
# Lint
pnpm lint