- Home
- MCP servers
- Convolut
Convolut
- javascript
0
GitHub Stars
javascript
Language
7 months ago
First Indexed
3 months ago
Catalog Refreshed
Documentation & install
Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.
Installation
Add the following to your MCP client configuration file.
Configuration
View docs{
"mcpServers": {
"expdal3-convolut-mcp": {
"command": "npx",
"args": [
"@convolut/convolut-mcp"
],
"env": {
"CONVOLUT_API_KEY": "your_api_key_here"
}
}
}
}You can run and connect the Convolut MCP Server to Claude Desktop or any MCP client to manage contexts and run AI-powered operations. This server acts as a bridge between your client and the Convolut API, enabling you to create, search, summarize, and export contexts through simple MCP calls.
How to use
Install the MCP server and configure your MCP client to talk to it. You can use a standard local setup where the MCP server runs as a stdio process, or you can connect via a remote setup if you prefer another deployment method. You will send natural language prompts that map to tools like create_context, search_contexts, consolidate_contexts, and more. Your MCP client will relay your request to the server, which then calls the Convolut API and returns results back to you. Typical tasks include saving conversations as contexts, performing semantic searches across contexts, generating actionable plans from multiple contexts, and exporting contexts in multiple formats.
How to install
Prerequisites: Node.js 18.0.0 or higher, and a valid Convolut API key.
Install the MCP server for quick setup
{
"mcpServers": {
"convolut": {
"command": "npx",
"args": ["@convolut/convolut-mcp"],
"env": {
"CONVOLUT_API_KEY": "your_api_key_here"
}
}
}
}
Alternative local start using a full path
{
"mcpServers": {
"convolut_fullpath": {
"command": "node",
"args": ["/full/path/to/convolut-mcp/stdio-client.cjs"],
"env": {
"CONVOLUT_API_KEY": "your_api_key_here"
}
}
}
}
Additional setup notes
If you are using Claude Desktop, place the MCP server configuration into your Claude desktop config file and restart Claude Desktop to begin using Convolut tools in your conversations.
Configuration and usage notes
- You need an API key from Convolut and you must set it in the environment for the MCP server to authorize requests.
- The MCP server provides access to the following capabilities: list_contexts, get_context, create_context, update_context, delete_context, search_contexts, consolidate_contexts, plan_from_contexts, export_contexts, get_raw_url, and get_context_stats.
Security considerations
Keep your API key secret. Do not share your configuration files with others. Rotate keys periodically and use environment variables to keep keys out of source control where possible.
Troubleshooting
If Claude Desktop or your MCP client cannot see tools, verify your MCP config is loaded, ensure your API key is valid, and restart the client. Check for network connectivity and ensure the server process is running with the correct environment variables.
Notes
The server provides a direct bridge between your client and the Convolut API, with no intermediate servers required. It follows the standard MCP flow: client → stdio → convolut-mcp (MCP Server) → HTTPS → api.convolut.app.
Tools you can use with this MCP server
You gain access to a suite of 11 tools to manage and operate on contexts, including creation, retrieval, updates, semantic searches, AI-powered consolidation, plan generation from contexts, export options, and context statistics.
Available tools
list_contexts
Search and filter contexts with advanced options to quickly locate the right context.
get_context
Retrieve a specific context by its ID to view details and metadata.
create_context
Create a new context with content and metadata for future retrieval and AI operations.
update_context
Update existing contexts with new content or metadata.
delete_context
Remove contexts by ID when they are no longer needed.
search_contexts
Perform semantic searches across your contexts to find relevant items based on meaning, not just keywords.
consolidate_contexts
AI-powered consolidation and summarization to merge and simplify multiple contexts into a cohesive summary.
plan_from_contexts
Generate actionable plans derived from multiple contexts to guide projects or tasks.
export_contexts
Export contexts in JSON, XML, TXT, or Markdown formats for external use.
get_raw_url
Generate temporary shareable URLs for contexts.
get_context_stats
Provide statistical analysis of your contexts and usage.