Context11 MCP Server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Context11 MCP Server search for project requirements"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Context11 MCP Server
An MCP (Model Context Protocol) server that provides access to your Context11 knowledge base for AI assistants.
Installation
npm install context11-mcpRelated MCP server: Convolut MCP Server
Configuration
Environment Variables
Variable | Description | Required |
| Your Context11 API key (starts with | Yes |
| API base URL (default: | No |
Claude Desktop
Add to your claude_desktop_config.json:
{
"mcpServers": {
"context11": {
"command": "npx",
"args": ["-y", "context11-mcp"],
"env": {
"CONTEXT11_API_KEY": "ctx11_your_api_key_here"
}
}
}
}Local Development
For local testing against a development server:
{
"mcpServers": {
"context11": {
"command": "npx",
"args": ["-y", "context11-mcp"],
"env": {
"CONTEXT11_API_KEY": "ctx11_your_api_key_here",
"CONTEXT11_URL": "http://localhost:3000"
}
}
}
}From Source
{
"mcpServers": {
"context11": {
"command": "node",
"args": ["/path/to/context11-mcp/dist/index.js"],
"env": {
"CONTEXT11_API_KEY": "ctx11_your_api_key_here"
}
}
}
}Tools
search_context
Search the company knowledge base for relevant context, guidelines, and rules.
Parameters:
Name | Type | Description |
| string | What to search for in the knowledge base |
| number | Maximum number of results (default: 10) |
Example:
{
"query": "brand guidelines",
"limit": 5
}get_document
Get the full content of a specific document by ID.
Parameters:
Name | Type | Description |
| string | Document ID from search results |
Example:
{
"id": "abc123"
}list_folders
List all folders in the workspace.
Parameters: None
Example Response:
Found 2 folder(s):
- **Engineering** (ID: abc123)
Documents: 5, Subfolders: 2
- **Marketing** (ID: def456)
Documents: 3, Subfolders: 0list_documents
List all documents in a specific folder.
Parameters:
Name | Type | Description |
| string | The folder ID to list documents from |
Example:
{
"folderId": "abc123"
}read_document
Read a document's full content by ID.
Parameters:
Name | Type | Description |
| string | The document ID to read |
Example:
{
"documentId": "abc123"
}update_document
Update a document's title and/or content. Content must be in Tiptap JSON format.
Parameters:
Name | Type | Description |
| string | The document ID to update |
| string | (Optional) New title for the document |
| string | (Optional) New content in Tiptap JSON format |
Example:
{
"documentId": "abc123",
"title": "Updated Title",
"content": "{\"type\":\"doc\",\"content\":[{\"type\":\"paragraph\",\"content\":[{\"type\":\"text\",\"text\":\"Hello world\"}]}]}"
}Development
# Install dependencies
npm install
# Build
npm run build
# Watch mode
npm run devLicense
MIT
Available Tools
6 toolsget_documentB
Get the full content of a specific document by ID
Inputs: id (required).
list_documentsA
List all documents in a specific folder
Inputs: folderId (required).
list_foldersA
List all folders in the workspace
Inputs: no named parameters.
read_documentB
Read a document's full content by ID
Inputs: documentId (required).
search_contextB
Search the company knowledge base for relevant context, guidelines, and rules
Inputs: query (required), limit.
update_documentA
Update a document's title and/or content. Content must be in Tiptap JSON format.
Inputs: documentId (required), title, content.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 6 tools
The tools get_document and read_document are nearly identical—both retrieve full document content by ID—causing clear ambiguity. Other tools are distinct, but this overlap creates confusion over which to use.
Tool names follow a consistent verb_noun pattern (search_, get_, list_, read_, update_). However, the use of both 'get' and 'read' for the same operation is a minor inconsistency that disrupts the pattern.
With 6 tools, the server is well-scoped for a document/knowledge base management purpose. Each tool, apart from the get/read duplication, occupies a clear functional role, and the count is neither sparse nor bloated.
The surface covers search, listing, reading, and updating documents, but lacks create and delete operations. This is a significant gap for a document management server, as users cannot add or remove documents through the tools.
Maintenance
Related MCP Connectors
Securely search and manage workspace context files for AI agents and teams.
Intelligent context infrastructure for AI teams: knowledge graph, sessions, tasks, documents.
Bring your Knacco library into your AI tool: browse, search, read guides and download files.
Shared, permission-aware company context for AI agents, with provenance, approvals and audit.
Related MCP Servers
- AlicenseAqualityDmaintenanceProvides tools for retrieving and processing documentation through vector search, enabling AI assistants to augment their responses with relevant documentation context.71MIT
- AlicenseAqualityDmaintenanceEnables seamless integration with Convolut Context Bank for AI-powered context management, search, consolidation, and export operations. Provides 11 powerful tools for creating, managing, and analyzing contexts with semantic search and automated planning capabilities.1119 npmMIT
- AlicenseNot gradedqualityDmaintenanceEnables to search and retrieve chunks from a fictional library's documentation through three tools (kb_search, kb_fetch, kb_sources), allowing LLMs to perform RAG queries via the Model Context Protocol.MIT
- FlicenseNot gradedqualityDmaintenanceEnables AI agents to access Contractor Scale internal context, including client background, meeting transcripts, and team summaries, via three tools: list_clients, get_client_context, and get_meetings.-