Context Portal MCP Server

A database-backed Model Context Protocol (MCP) server for managing structured project context, designed to be used by AI assistants and developer

Local serverstdioPython

What is the Context Portal MCP server?

A database-backed Model Context Protocol (MCP) server for managing structured project context, designed to be used by AI assistants and developer tools within IDEs and other interfaces. That is what the context portal mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.

The short version

Context Portal (ConPort) is your project's memory bank. It's a tool that helps AI assistants understand your specific software project better by storing important information like decisions, tasks, and architectural patterns in a structured way. Think of it as building a project-specific knowledge base that the AI can easily access and use to give you more accurate and helpful responses.

Getting it running

Configuration on PyPI is all you need. Most clients run it directly, so configuration is a few lines and a restart.

The tools it exposes

The server publishes 14 tools. What each one is for:

  • get_product_context — Retrieves the overall project goals, features, and architecture
  • update_product_context — Updates the product context. Accepts full content (object) or patch_content (object) for partial updates (use DELETE as a value in patch to
  • get_active_context — Retrieves the current working focus, recent changes, and open issues
  • update_active_context — Updates the active context. Accepts full content (object) or patch_content (object) for partial updates (use DELETE as a value in patch to remove
  • log_decision — Logs an architectural or implementation decision
  • Args — summary (str, req), rationale (str, opt), implementation_details (str, opt), tags (list[str], opt)
  • get_decisions — Retrieves logged decisions
  • search_decisions_fts — Full-text search across decision fields (summary, rationale, details, tags)
  • delete_decision_by_id — Deletes a decision by its ID
  • log_progress — Logs a progress entry or task status
  • get_progress — Retrieves progress entries
  • update_progress — Updates an existing progress entry

What it needs from you

Before you begin, ensure you have the following installed: - Python: Version 3.8 or higher is recommended. - Download Python - Ensure Python is added to your system's PATH during installation (especially on Windows). - uv: (Highly Recommended) A fast Python environment and package manager. Using uv significantly simplifies virtual environment

Things to watch

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Context Portal.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

How it compares

This sits in the monitoring and observability group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Context Portal's toolset — get_product_context, update_product_context, get_active_context and 11 more — is a fair guide to whether it matches your workflow. It is maintained by GreatScottyMac; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Available tools

ToolWhat it does
get_product_contextRetrieves the overall project goals, features, and architecture.
update_product_contextUpdates the product context. Accepts full content (object) or patch_content (object) for partial updates (use __DELETE__ as a value in patch to remove a key).
get_active_contextRetrieves the current working focus, recent changes, and open issues.
update_active_contextUpdates the active context. Accepts full content (object) or patch_content (object) for partial updates (use __DELETE__ as a value in patch to remove a key).
log_decisionLogs an architectural or implementation decision.
Argssummary (str, req), rationale (str, opt), implementation_details (str, opt), tags (list[str], opt).
get_decisionsRetrieves logged decisions.
search_decisions_ftsFull-text search across decision fields (summary, rationale, details, tags).
delete_decision_by_idDeletes a decision by its ID.
log_progressLogs a progress entry or task status.
get_progressRetrieves progress entries.
update_progressUpdates an existing progress entry.
delete_progress_by_idDeletes a progress entry by its ID.
log_system_patternLogs or updates a system/coding pattern.

How to install the Context Portal MCP server

{
  "mcpServers": {
    "conport": {
      "command": "uvx",
      "args": [
        "--from",
        "context-portal-mcp",
        "conport-mcp",
        "--mode",
        "stdio",
        "--workspace_id",
        "${workspaceFolder}",
        "--log-file",
        "./logs/conport.log",
        "--log-level",
        "INFO"
      ]
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

Before you begin, ensure you have the following installed: - Python: Version 3.8 or higher is recommended. - Download Python - Ensure Python is added to your system's PATH during installation (especially on Windows). - uv: (Highly Recommended) A fast Python environment and package manager. Using uv significantly simplifies virtual environment

Example prompts to try

  • Use Context Portal to get product context.
  • Use Context Portal to update product context.
  • Use Context Portal to get active context.

Frequently asked questions

It connects Context Portal to MCP-compatible AI assistants such as Claude and Cursor, exposing 14 tools (get_product_context, update_product_context, get_active_context, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Context Portal directly.