Skip to main content
Glama
Convolut MCP Server

Convolut MCP Server

by expdal3

Convolut MCP Server

npm version License: MIT

Official Model Context Protocol (MCP) server for Convolut Context Bank, enabling seamless integration with Claude Desktop and other MCP clients.

Features

šŸš€ 11 Powerful Tools for context management and AI-powered operations:

Context Management

  • list_contexts - Search and filter contexts with advanced options

  • get_context - Retrieve specific context by ID

  • create_context - Create new context with content and metadata

  • update_context - Update existing contexts

  • delete_context - Delete contexts by ID

AI-Powered Operations

  • search_contexts - Semantic search across your contexts

  • consolidate_contexts - AI-powered context consolidation and summarization

  • plan_from_contexts - Generate actionable plans from multiple contexts

Export & Integration

  • export_contexts - Export to JSON, XML, TXT, or Markdown formats

  • get_raw_url - Generate temporary shareable URLs

  • get_context_stats - Statistical analysis of your contexts

Related MCP server: MyChatArchive MCP Server

Quick Start

Installation

npm install -g @convolut/convolut-mcp

Claude Desktop Setup

  1. Get your Convolut API key from https://convolut.app

  2. Add to your Claude Desktop configuration file:

Windows: %APPDATA%\\Claude\\claude_desktop_config.json macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "convolut": {
      "command": "npx",
      "args": ["@convolut/convolut-mcp"],
      "env": {
        "CONVOLUT_API_KEY": "your_api_key_here"
      }
    }
  }
}
  1. Restart Claude Desktop

  2. Start using Convolut tools in your conversations! šŸŽ‰

Usage Examples

Search Your Contexts

"Search for contexts about machine learning"

Claude will use the search_contexts tool to find relevant contexts in your Convolut library.

Create New Context

"Save this conversation as a new context titled 'API Integration Discussion'"

Claude will use create_context to save the conversation to your Convolut account.

Generate Plans

"Analyze these project contexts and create an actionable plan"

Claude will use consolidate_contexts and plan_from_contexts to analyze multiple contexts and generate structured plans.

Manual Installation

If you prefer to install locally:

# Clone or download the package
git clone https://github.com/expdal3/convolut-mcp.git
cd convolut-mcp

# Install dependencies (none required - pure Node.js!)
npm install

# Test the installation
CONVOLUT_API_KEY=your_key_here node stdio-client.cjs

Then use the full path in your Claude Desktop config:

{
  "mcpServers": {
    "convolut": {
      "command": "node", 
      "args": ["/full/path/to/convolut-mcp/stdio-client.cjs"],
      "env": {
        "CONVOLUT_API_KEY": "your_api_key_here"
      }
    }
  }
}

API Key Setup

Get Your API Key

  1. Sign up at https://convolut.app

  2. Navigate to Settings → API Keys

  3. Generate a new API key

  4. Copy the key (format: convolut_sk_...)

Environment Variables

You can also set the API key as an environment variable:

# Windows
set CONVOLUT_API_KEY=your_api_key_here

# macOS/Linux  
export CONVOLUT_API_KEY=your_api_key_here

Architecture

Claude Desktop (or other MCP Client) → stdio → convolut-mcp (MCP Server) → HTTPS → api.convolut.app

This MCP server provides a direct, efficient bridge between Claude Desktop and the Convolut API, with no intermediate servers required.

Requirements

  • Node.js 18.0.0 or higher

  • Convolut API key

  • Claude Desktop (or any MCP-compatible client)

Supported Platforms

  • āœ… Windows 10/11

  • āœ… macOS 12+

  • āœ… Linux (Ubuntu 20.04+)

Troubleshooting

Claude Desktop Not Seeing Tools

  1. Verify your claude_desktop_config.json syntax is correct

  2. Check that your API key is valid

  3. Restart Claude Desktop completely

  4. Check Claude Desktop logs for errors

API Key Issues

Error: CONVOLUT_API_KEY environment variable is required
  • Ensure your API key is set in the Claude Desktop config

  • Verify the API key format starts with conair_sk_

  • Check for typos in the configuration file

Connection Issues

  • Verify internet connectivity

  • Check if your firewall blocks HTTPS requests

  • Ensure Node.js version is 18.0.0 or higher

Development

Project Structure

convolut-mcp/
ā”œā”€ā”€ stdio-client.cjs       # Main MCP server entry point
ā”œā”€ā”€ utils/
│   └── api-client.cjs     # Convolut API client
ā”œā”€ā”€ tools/
│   ā”œā”€ā”€ contexts.cjs       # Context management tools
│   ā”œā”€ā”€ ai-tools.cjs       # AI-powered operations  
│   └── export.cjs         # Export and statistics
ā”œā”€ā”€ types/
│   └── convolut.cjs       # Type definitions
└── README.md

Contributing

  1. Fork the repository

  2. Create a feature branch

  3. Make your changes

  4. Test thoroughly

  5. Submit a pull request

License

MIT License - see LICENSE file for details.

Support


Made with ā¤ļø by the Convolut team

Available Tools

11 tools
consolidate_contextsC

Merge multiple contexts using AI to create a consolidated summary or composition

Inputs: context_ids (required), consolidation_type (required), custom_prompt.

create_contextC

Create a new context with title, content, tags, and metadata

Inputs: title (required), content (required), tags, category, +2 more.

delete_contextC

Delete a context permanently by its ID

Inputs: context_id (required).

export_contextsC

Export contexts in various formats (JSON, XML, TXT, Markdown) for integration with other systems

Inputs: context_ids (required), format (required), include_metadata.

get_contextB

Retrieve a specific context by its ID, including full content and metadata

Inputs: context_id (required).

get_context_statsB

Get statistical information about contexts including counts, categories, and usage metrics

Inputs: date_range, group_by.

get_raw_urlA

Generate a temporary raw URL for a context that can be accessed without authentication (expires in 10 minutes)

Inputs: context_id (required).

list_contextsC

Search and filter contexts with advanced options including keywords, tags, categories, and date ranges

Inputs: limit, offset, contain, category, +4 more.

plan_from_contextsC

Analyze contexts and generate actionable plans using AI

Inputs: context_ids (required), planning_prompt.

search_contextsC

Perform semantic search across contexts to find relevant information

Inputs: query (required), limit, category, tags.

update_contextC

Update an existing context with new title, content, tags, or metadata

Inputs: context_id (required), title, content, tags, +2 more.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.5/5.0

    Scored across 11 tools

    Disambiguation5/5

    Every tool has a clearly distinct purpose with no ambiguity. For example, create_context, get_context, update_context, and delete_context form distinct CRUD operations, while consolidate_contexts, plan_from_contexts, and search_contexts each serve unique AI-driven functions. The descriptions clearly differentiate overlapping tools like list_contexts (filtering) and search_contexts (semantic search).

    Naming Consistency5/5

    All tool names follow a consistent verb_noun pattern using snake_case, such as create_context, delete_context, and get_context_stats. There are no deviations in naming conventions, making the set predictable and readable. This uniformity aids in agent selection and understanding of tool purposes.

    Tool Count5/5

    With 11 tools, the count is well-scoped for a context management server, covering core operations without bloat. Each tool earns its place by addressing specific needs like CRUD, search, export, and AI analysis. This aligns with typical server scopes of 3-15 tools, ensuring comprehensive coverage without overwhelming complexity.

    Completeness5/5

    The tool surface provides complete CRUD/lifecycle coverage for context management, including create, get, update, delete, list, and search. It extends beyond basics with AI features (consolidate, plan), utilities (export, raw URL), and analytics (stats), leaving no obvious gaps. Agents can perform end-to-end workflows without dead ends.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      Connects AI assistants to Logseq knowledge graphs to read, write, and search pages, blocks, and journals via the Model Context Protocol. It features 17 tools for full graph management, including CRUD operations, batch block insertion, and full-text search.
      23 npm
      Apache 2.0
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables semantic search across your local AI conversation history (ChatGPT, Claude, etc.) and provides tools to retrieve context, capture thoughts, and get profile summaries.
      72
      AGPL 3.0