cortex-cloud-docs-mcp-server
The Cortex Cloud Docs MCP Server provides search and indexing capabilities for Cortex Cloud's official documentation and API references.
Search official Cortex Cloud documentation using
search_cortex_docsSearch Cortex Cloud API documentation using
search_cortex_api_docsSearch across all indexed documentation using
search_all_docsIndex Cortex Cloud documentation using
index_cortex_docs(with optional page limits)Index Cortex Cloud API documentation using
index_cortex_api_docs(with optional page limits)Check indexing status and cache statistics using
get_index_status
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., "@cortex-cloud-docs-mcp-server how do I set up authentication for the Cortex Cloud API?"
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.
Cortex Cloud Docs MCP Server
A Model Context Protocol (MCP) server that provides search access to Cortex Cloud documentation. This server allows Claude and other MCP-compatible clients to search through Cortex Cloud's official documentation and API references.
Features
Search across Cortex Cloud documentation
Search Cortex Cloud API documentation
Caching system for improved performance
Real-time indexing of documentation sites
Related MCP server: s2-streamstore
Installation
Option 1: From PyPI (Recommended)
No installation needed! Just use uvx in your Claude Desktop configuration.
Installing via Smithery
To install cortex-cloud-docs-mcp-server for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @clarkemn/cortex-cloud-docs-mcp-server --client claudeOption 2: Development Installation
Prerequisites
Python 3.12 or higher
uv package manager
Install uv
curl -LsSf https://astral.sh/uv/install.sh | shClone and Setup
git clone https://github.com/clarkemn/cortex-cloud-docs-mcp-server.git
cd cortex-cloud-docs-mcp-server
uv syncUsage
With Claude Desktop
Add this server to your Claude Desktop configuration file:
Location: ~/Library/Application Support/Claude/claude_desktop_config.json (macOS)
Option 1: Direct from PyPI (Recommended)
{
"mcpServers": {
"Cortex Cloud Docs": {
"command": "uvx",
"args": ["cortex-cloud-docs-mcp-server@latest"],
"env": {},
"transport": "stdio"
}
}
}Option 2: Local Development
{
"mcpServers": {
"Cortex Cloud Docs": {
"command": "uv",
"args": ["run", "python", "server.py"],
"cwd": "/path/to/cortex-cloud-docs-mcp-server",
"env": {},
"transport": "stdio"
}
}
}Replace /path/to/cortex-cloud-docs-mcp-server with the actual path to where you cloned this repository.
Manual Testing
You can test the server manually:
echo '{"jsonrpc": "2.0", "id": 1, "method": "initialize", "params": {"protocolVersion": "2024-11-05", "capabilities": {}, "clientInfo": {"name": "test", "version": "1.0"}}}' | uv run python server.pyAvailable Tools
The server provides these MCP tools:
index_cortex_docs(max_pages: int = 50)- Index Cortex Cloud documentation (call this first)index_cortex_api_docs(max_pages: int = 50)- Index Cortex Cloud API documentationsearch_cortex_docs(query: str)- Search Cortex Cloud documentationsearch_cortex_api_docs(query: str)- Search Cortex Cloud API documentationsearch_all_docs(query: str)- Search across all indexed documentationget_index_status()- Check indexing status and cache statistics
Development
Running the server
uv run python server.pyInstalling dependencies
uv syncProject structure
cortex-cloud-docs-mcp-server/
├── server.py # Main MCP server implementation
├── pyproject.toml # Project configuration
├── uv.lock # Dependency lock file
└── README.md # This fileLicense
MIT License - see LICENSE file for details.
Contributing
Fork the repository
Create a feature branch
Make your changes
Test with Claude Desktop
Submit a pull request
Troubleshooting
Server not starting in Claude Desktop
Ensure
uvis installed and in your PATHVerify the path to the project directory is correct
Check Claude Desktop logs for specific error messages
Missing dependencies
Run uv sync to ensure all dependencies are installed.
Documentation not found
The server needs to index documentation first. Use the index_cortex_docs or index_cortex_api_docs tools before searching.
Available Tools
6 toolsget_index_statusA
Check how many documents are currently cached.
Inputs: no named parameters. Returns: result
index_cortex_api_docsA
Index Cortex Cloud API documentation. Call this first before searching.
Inputs: max_pages. Returns: result
index_cortex_docsA
Index Cortex Cloud documentation. Call this first before searching.
Inputs: max_pages. Returns: result
search_all_docsC
Search across all Cortex Cloud documentation sites.
Inputs: query (required). Returns: result
search_cortex_api_docsC
Search Cortex Cloud API documentation
Inputs: query (required). Returns: result
search_cortex_docsB
Search Cortex Cloud documentation
Inputs: query (required). Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 6 tools
Multiple tools have unclear boundaries and overlapping purposes. The distinction between 'index_cortex_api_docs' and 'index_cortex_docs' is ambiguous, as is the difference between 'search_cortex_api_docs' and 'search_cortex_docs'. This overlap could lead to misselection by agents, especially since the descriptions don't clearly differentiate the scopes or use cases for these similar tools.
All tool names follow a consistent verb_noun pattern with snake_case, such as 'get_index_status', 'index_cortex_api_docs', and 'search_all_docs'. This predictability makes the tool set easy to parse and understand, with no deviations in naming conventions across the six tools.
With 6 tools, the count is well-scoped for a documentation server focused on indexing and searching. Each tool appears to serve a distinct operational role, such as checking status, indexing specific doc types, and searching across various scopes, making the set appropriately sized without being overly complex or too sparse.
The tool surface covers core workflows for indexing and searching documentation, with tools for status checks, indexing different doc types, and searching across scopes. A minor gap exists in lacking explicit update or delete operations for cached documents, but agents can likely work around this by re-indexing, so the coverage is largely complete for the server's purpose.
Maintenance
Related MCP Connectors
The official MCP server for Capawesome documentation and Capawesome Cloud.
Unofficial MCP server for the Capacitor documentation, plugin list and blog.
Official MCP server for Certifier to issue, manage, and track certificates and badges.
Related MCP Servers
- MIT
- AlicenseNot gradedqualityAmaintenanceOfficial MCP server for the s2.dev serverless stream platform135 npm37MIT
- AlicenseBqualityCmaintenanceMCP server for asking questions about Prisma Cloud documentation63MIT
- AlicenseBqualityDmaintenanceMCP server for codewiki.google — AI-powered wiki documentation for open-source repositories. Search repos, fetch wiki content, and ask questions about any repo.388 npm19MIT