io.github.Contextual-Laboratories/contextual
Persistent memory for AI coding agents: local-first semantic search, dependency graphs, git history.
Install
Add this to your client's MCP configuration (Claude Desktop: claude_desktop_config.json; Cursor: .cursor/mcp.json; VS Code and others use the same "mcpServers" shape).
contextual-engineclaude mcp add contextual -e 'CONTEXTUAL_LOG_LEVEL=<CONTEXTUAL_LOG_LEVEL>' -- uvx contextual-engine==1.0.2 --client --workspace
{
"mcpServers": {
"contextual": {
"command": "uvx",
"args": [
"contextual-engine==1.0.2",
"--client",
"--workspace"
],
"env": {
"CONTEXTUAL_LOG_LEVEL": "<CONTEXTUAL_LOG_LEVEL>"
}
}
}
}
Environment variables
CONTEXTUAL_LOG_LEVELPython logging level as an integer (e.g. 10=DEBUG, 20=INFO). Defaults to INFO.
Frequently asked questions
What is io.github.Contextual-Laboratories/contextual?
Persistent memory for AI coding agents: local-first semantic search, dependency graphs, git history.
How do I install io.github.Contextual-Laboratories/contextual?
It runs on your machine. In Claude Code: claude mcp add contextual -e 'CONTEXTUAL_LOG_LEVEL=<CONTEXTUAL_LOG_LEVEL>' -- uvx contextual-engine==1.0.2 --client --workspace. For other clients, paste the JSON configuration from this page into their MCP settings.
Does io.github.Contextual-Laboratories/contextual need an API key?
Its registry entry lists no required key or secret. Some features may still need an account with the service it connects to.
Who maintains io.github.Contextual-Laboratories/contextual?
It is published by Contextual-Laboratories. AI.tn lists it but does not maintain or endorse it.
From the official MCP Registry. Listing is not an endorsement: review a server's code and permissions before giving it access to your data.