Context Repo DocsMCP Server
Connect your AI assistant to Context Repo with the Model Context Protocol (MCP) to manage prompts, documents, collections, and search 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. The current hosted tool set. Zero tab-switching.
Tools Overview
The hosted MCP Server defines the tools available to every connection,
including the search and fetch aliases used by ChatGPT. The
context-repo-mcp v3 command is a stdio bridge to that same hosted endpoint,
so its tool schemas and behavior update with the hosted server rather than a
separate package implementation.
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 canonical document fields with no-op detection and optional revision/lease inputs |
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.
The safe document revision and lease parameters described here come from the
hosted https://contextrepo.com/mcp endpoint and pass through the
context-repo-mcp v3 stdio bridge unchanged.
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.
Safe Document Updates
get_document returns the canonical document revision, content hash, change
time, and ETag. update_document and restore_document_version accept
expectedRevision, idempotencyKey, leaseId, and leaseFence.
When you provide expectedRevision, the MCP Server fetches the current
document in the same MCP invocation, compares its revision, and forwards
the exact ETag from that response as If-Match. It never invents an ETag from
the number or reuses one from an earlier call. A mismatch returns a typed
REVISION_MISMATCH error instead of overwriting newer content.
Changed writes return a compact acknowledgement with the document ID,
revision, content hash, change time, and noop status. Exact unchanged updates
return noop: true. If document coordination is enabled, first obtain a lease
through the REST API and pass its ID and fence with an idempotency key.
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 use the hosted tool set. The stdio npm package forwards to the same endpoint and does not maintain a separate inventory.
Grok uses the dedicated https://contextrepo.com/grok-mcp compatibility endpoint so its first request receives an OAuth challenge. It exposes the same 29 hosted tools as /mcp. Follow the Grok integration guide instead of the generic client setup.
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.
Grok
Add Context Repo as a custom connector with hosted OAuth sign-in.
Grok Bot
Add Context Repo as a Grok Bot plugin with hosted OAuth sign-in.
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 the current hosted 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
Reference for the current hosted MCP tools, with parameters, types, and usage examples organized by category.