Context Repo DocsMCP Server
Connect your AI assistant to Context Repo with the Model Context Protocol (MCP). Access 27 tools (29 including ChatGPT Apps SDK aliases) for managing prompts, documents, collections, and search — directly from Claude, Cursor, VS Code, and more.
The Model Context Protocol (MCP) is an open standard that lets AI assistants connect to external tools and data sources. Instead of copying and pasting between your AI assistant and Context Repo, MCP gives your assistant direct access to your prompts, documents, and collections — so it can read, create, update, and search your workspace without you ever leaving the conversation.
Why MCP Matters
Without MCP, working with AI context looks something like this:
- Open Context Repo in one tab, your AI assistant in another
- Copy a prompt, switch tabs, paste it in
- Get a response, switch back, save it as a document
- Repeat for every interaction
With the Context Repo MCP Server, your AI assistant handles all of this directly. Ask it to list your prompts, create a document, search your collections, or explore content chunk by chunk — all through natural conversation.
One connection. 27 tools. Zero tab-switching.
Tools Overview
The MCP Server provides 27 tools organized into 7 categories. Each tool maps to a specific action in your Context Repo workspace. The web-hosted server also registers two OpenAI Apps SDK aliases — search and fetch — for ChatGPT's built-in retrieval surface, bringing the total to 29 tools exposed to every client on the https://contextrepo.com/mcp endpoint. The standalone context-repo-mcp stdio package ships the 27 power tools below.
User Info
| Tool | Description |
|---|---|
get_user_info | Get your account details (name, email, profile image) |
Prompts (7 tools)
| Tool | Description |
|---|---|
search_prompts | List all your prompts with optional search filtering |
read_prompt | Get a specific prompt's full content, variables, and metadata |
create_prompt | Create a new prompt template with title, description, and content |
update_prompt | Update an existing prompt's title, description, or content |
delete_prompt | Permanently delete a prompt |
get_prompt_versions | View a prompt's version history with change logs |
restore_prompt_version | Restore a prompt to a previous version |
Documents (7 tools)
| Tool | Description |
|---|---|
list_documents | List all your documents with optional search filtering |
get_document | Get a specific document's full content and metadata |
create_document | Create a new text document with optional tags |
update_document | Update an existing document's title or content |
delete_document | Permanently delete a document |
get_document_versions | View a document's version history with change logs |
restore_document_version | Restore a document to a previous version |
Collections (7 tools)
| Tool | Description |
|---|---|
list_collections | List all your collections with optional search filtering |
get_collection | Get a collection's details and its items |
create_collection | Create a new collection with name, description, icon, and color |
update_collection | Update a collection's name, description, icon, or color |
delete_collection | Delete a collection (items aren't deleted — they stay in your workspace) |
add_to_collection | Add prompts or documents to a collection |
remove_from_collection | Remove prompts or documents from a collection |
Search (1 tool)
| Tool | Description |
|---|---|
find_items | Search across prompts, documents, and collections using semantic similarity or keyword matching. Filter by type and toggle between search modes. |
Deep Search (3 tools)
| Tool | Description |
|---|---|
deep_search | Search within document content and get ranked, hierarchical chunks with navigation links |
deep_read | Read a specific chunk with full content, structural position, and metadata |
deep_expand | Navigate from a chunk in 5 directions: up (parent), down (children), next, previous, or surrounding |
Deep Search is designed for exploring large documents progressively. Start with deep_search to find relevant passages, use deep_read to examine them in detail, and deep_expand to navigate through the document's structure without loading everything at once.
Reasoning (1 tool)
| Tool | Description |
|---|---|
reason | Ask a question and get a synthesized, cited answer composed across your documents — with inline citations, an explicit list of gaps, and any conflicts between sources (read-only) |
Reasoning sits one layer above Deep Search: instead of returning ranked chunks for you to read, reason gathers the most relevant evidence and composes a single cited answer. Use it when you want an answer, not a result list.
Authentication
The MCP Server supports two authentication methods:
- Sign in with Context Repo (primary) — When you connect through a supported client like Cursor or Claude Desktop, you'll sign in with your Context Repo account through a hosted OAuth flow. This is the recommended method and happens automatically during setup.
- API Key (fallback) — Generate an API key from Dashboard > Settings > API Keys and pass it as the authentication token. This works with any MCP-compatible client and is useful for programmatic access.
Both methods give you access to the full tool set. The web-hosted endpoint exposes all 29 tools (the 27 power tools plus the search/fetch Apps SDK aliases) to every connected client; the stdio npm package exposes the 27 power tools.
Get Started
Ready to connect your AI assistant?
Cursor
One-click setup with automatic configuration.
Claude Desktop
JSON config for macOS and Windows.
VS Code
Connect through VS Code's MCP support.
Windsurf
Set up Context Repo in Windsurf.
Other Clients
Generic setup for any MCP-compatible client via stdio or Streamable HTTP.
Tools Reference
Full parameter details for all 27 tools.
Content Formats
Context Repo accepts both Markdown and HTML as first-class content. Markdown is optimized for agent consumption — lower tokens, faster generation, cheaper embeddings. HTML is optimized for human viewing — rich visuals, styled layouts, shareable reports.
Tools Reference
Complete reference for all 27 MCP tools (29 including ChatGPT Apps SDK aliases) — exact parameters, types, and usage examples organized by category.