Frequently Asked Questions

Quick answers to the questions we hear most often. For deeper detail, follow the links to the relevant documentation pages.

Account & Billing

Is Context Repo free to use?

Yes. The free tier includes unlimited prompts via the MCP Server and API, all 26 MCP tools, the Chrome Extension, version history, and document processing for 75+ file formats. Paid plans unlock the Dashboard, Collection Chat, Deep Search, Text-to-Speech, and increased storage. See Plans & Billing for a full comparison.

What do paid plans add?

Paid plans unlock the Dashboard for managing your workspace visually, plus Collection Chat (RAG-powered Q&A across grouped context with source citations), Deep Search (hierarchical vector search inside documents), Text-to-Speech (6 voices, 2 quality tiers), and increased storage limits. Visit the pricing page for current plan details.

Which plan do I need for Collection Chat?

Collection Chat requires a Pro Max or Ultimate subscription. It isn't available on the Pro plan or the free tier.

Prompts

What are variables and how do I use them?

Variables let you create dynamic prompt templates using ${variableName} syntax. When you or an AI assistant uses the prompt, each variable becomes a fill-in-the-blank field. Variables support three types: string, number, and boolean. Learn more in the Prompts guide.

Does Context Repo track prompt changes?

Yes — every edit is automatically versioned. Each version records what changed and when, and you can restore any previous version at any time. Version history starts the moment you create a prompt. See Prompts — Version History for details.

Can I share prompts publicly?

You can toggle any prompt between public and private. Public prompts are visible to other Context Repo users, while private prompts are only accessible to you.

Documents

What file formats can I upload?

Context Repo supports 75+ file formats including PDFs, Word documents, Excel spreadsheets, PowerPoints, images (with OCR), plain text, markdown, HTML, CSV, and many more. See the Documents guide for the full list.

Can I scrape web pages as documents?

Yes. Enter a URL and Context Repo uses Firecrawl to extract the page content. You can configure options like extracting only the main content, including a screenshot, and setting a wait time for pages that load dynamically. Learn more in Documents — Web Scraping.

Does Context Repo support text-to-speech?

Yes — you can listen to any document using the text-to-speech feature on the document detail page. Choose from multiple voices and quality tiers. See Documents — Text-to-Speech for details.

MCP Server

What is MCP?

The Model Context Protocol (MCP) is an open standard that lets AI assistants connect to external tools and data sources. Context Repo's MCP Server provides 26 tools that give your AI assistant direct access to your prompts, documents, and collections. Learn more in the MCP overview.

What AI tools work with Context Repo?

Context Repo works with Claude, Cursor, ChatGPT, VS Code, Windsurf, Factory, Amp, and 90+ other MCP-compatible clients. Check the setup guides for step-by-step instructions for popular clients, or use the generic setup guide for any MCP-compatible tool.

How do I connect Context Repo to my AI assistant?

Each client has its own setup process. For Cursor, there's a one-click deep link. For Claude Desktop, you add a JSON config file. For other clients, see the setup guides for detailed instructions.

What can I do with the 26 MCP tools?

The tools are organized into 6 categories: User Info, Prompts (create, read, update, delete, version), Documents (create, read, update, delete, version), Collections (create, read, update, delete, manage items), Search (find items across your workspace), and Deep Search (explore document content chunk by chunk). See the Tools Reference for full parameter details.

API

How do I authenticate API requests?

The API supports two authentication methods: Bearer JWT (using a Clerk-issued token) and API-Key (using a key generated from Dashboard > Settings). Both use the Authorization header. See Authentication for setup details.

Where do I get an API key?

Go to Dashboard > Settings > API Keys and click New API Key. Choose a name, select permission scopes, and optionally set an expiration date. The full key is shown once — copy it immediately. See Settings for details.

What permission scopes are available for API keys?

There are two scopes: prompts.read (access to the Prompts API) and documents.read (read-only access to collections and documents). You can assign one or both when creating a key. See Settings — Permission Scopes for details.

What endpoints are available?

The REST API includes endpoints for prompts, documents, collections, search, and progressive disclosure. Every endpoint is documented with methods, paths, parameters, and examples in the Endpoints reference.

Integrations

What does the Chrome Extension do?

The Chrome Extension lets you capture web pages directly to your Context Repo workspace with one click. It uses your API key for authentication and supports Firecrawl-powered extraction.

How does the ChatGPT App work?

The ChatGPT App connects to your Context Repo workspace through OAuth. Once authorized, you can access your prompts, documents, and collections directly inside ChatGPT conversations — using the same 26 MCP tools available in other clients.