Context Portal MCP (ConPort) is a database-backed Model Context Protocol server that serves as a project memory bank, storing structured context like decisions, tasks, and architectural patterns to enhance AI assistant capabilities through semantic search and RAG.
Retrieves the overall project goals, features, and architecture.
Updates the product context, accepting full content or patch_content for partial updates.
Retrieves the current working focus, recent changes, and open issues.
Updates the active context, accepting full content or patch_content for partial updates.
Logs an architectural or implementation decision.
Retrieves logged decisions with optional filtering and limits.
Performs full-text search across decision fields.
Deletes a decision by its ID.
Logs a progress entry or task status.
Retrieves progress entries with optional filtering.
Updates an existing progress entry.
Deletes a progress entry by its ID.
Logs or updates a system/coding pattern.
Retrieves system patterns with optional tag filtering.
Deletes a system pattern by its ID.
Stores or updates a custom key-value entry under a category.
Retrieves custom data with optional category and key filters.
Deletes a specific custom data entry.
Performs full-text search within the 'ProjectGlossary' custom data category.
Performs full-text search across all custom data values, categories, and keys.
Creates a relationship link between two ConPort items.
Retrieves items linked to a specific item.
Retrieves version history for Product or Active Context.
Provides a summary of recent ConPort activity.
Retrieves the schema of available ConPort tools and their arguments.
Exports ConPort data to markdown files.
Imports data from markdown files into ConPort.
Logs multiple items of the same type in a single call.
{
"mcpServers": {
"conport": {
"command": "uvx",
"args": [
"--from",
"context-portal-mcp",
"conport-mcp",
"--mode",
"stdio",
"--workspace_id",
"${workspaceFolder}",
"--log-file",
"./logs/conport.log",
"--log-level",
"INFO"
]
}
}
}