Server facts
Context Portal MCP (ConPort)
Project
- Author
- GreatScottyMac
- Repository
- github.com/GreatScottyMac/context-portal
- License
- Apache-2.0
- Category
- Memory & Knowledge
Tech
- Runtime / language
- pythonPython
- Transports
- stdio
- Remote available
- No
- Authentication
- Not specified
Activity
- GitHub stars
- 767
- Last commit
- Data as of
Tags
- Knowledge Graph
- Project Memory
- Rag
- Semantic Search
- Sqlite
Overview
Context Portal MCP, also called ConPort, provides persistent project context for AI assistants and IDE tools. Instead of maintaining memory solely as text files, it stores structured records in a SQLite database for each workspace. The documented context includes decisions, progress, architectural patterns, product information, and custom data such as glossaries or specifications. Explicit links between records form a project knowledge graph. Vector storage and semantic search support retrieval-augmented workflows, while schema migrations are handled through Alembic. The main deployment mode uses standard input/output for integration with MCP-enabled development environments.
The recommended launch uses uvx to run the published package without manually managing a virtual environment. Workspace identity remains important: some IDEs do not expand their workspace variable, so the README offers absolute paths or per-call workspace identifiers as alternatives. When no launch-time workspace is supplied, the database initializes on the first tool call that provides one. The README also describes automatic workspace detection. Custom instruction sets for several assistants explain when to initialize memory, retrieve context, and record changes. A projectBrief.md file can bootstrap product context after the agent asks for approval to import it. Another strategy set focuses on sprint artifacts, flat categories, and valid full-text-search prefixes. These instructions complement the database rather than replacing the need to identify the correct workspace.
Install & configure
Requirements
- Python 3.8 or later recommended
- uv with uvx
- An MCP-compatible client that supplies workspace context
uvx --from context-portal-mcp conport-mcp --mode stdio --log-file ./logs/conport.log --log-level INFOUses the README's alternative without launch-time --workspace_id. Supply workspace_id on tool calls; database initialization then occurs on the first call. Absolute launch-time paths are another option. Some IDEs do not expand ${workspaceFolder}. No required environment variables are stated.
Examples are translated from the published configuration. Supply your own credentials and verify requirements in the upstream README. Remote connectors are shown only where a supported configuration format is known.
Config file · macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Use Settings → Developer → Edit Config when available. Do not assume a Linux configuration path; check the client documentation for your platform. Remote servers use the app’s connector flow when supported, not the local stdio file shown here. Merge this example with existing settings; do not overwrite unrelated servers.
{
"mcpServers": {
"context-portal": {
"command": "uvx",
"args": [
"--from",
"context-portal-mcp",
"conport-mcp",
"--mode",
"stdio",
"--log-file",
"./logs/conport.log",
"--log-level",
"INFO"
],
"env": {}
}
}
}Config file · Project: .cursor/mcp.json
User: ~/.cursor/mcp.json
The project path is relative to the workspace root. The tilde denotes your user home directory. Use Cursor’s MCP settings to confirm which configuration and scope your installed version is reading. Merge this example with existing settings; do not overwrite unrelated servers.
{
"mcpServers": {
"context-portal": {
"command": "uvx",
"args": [
"--from",
"context-portal-mcp",
"conport-mcp",
"--mode",
"stdio",
"--log-file",
"./logs/conport.log",
"--log-level",
"INFO"
],
"env": {}
}
}
}Config file · Workspace: .vscode/mcp.json
For user scope, use the “MCP: Open User Configuration” command if available. Do not guess a user configuration path across operating systems, profiles, containers, or remote workspaces; check the client documentation. Merge this example with existing settings; do not overwrite unrelated servers.
{
"servers": {
"context-portal": {
"type": "stdio",
"command": "uvx",
"args": [
"--from",
"context-portal-mcp",
"conport-mcp",
"--mode",
"stdio",
"--log-file",
"./logs/conport.log",
"--log-level",
"INFO"
],
"env": {}
}
}
}Config file · macOS/Linux: ~/.codeium/windsurf/mcp_config.json
Windows: %USERPROFILE%\.codeium\windsurf\mcp_config.json
Open the MCP configuration through Windsurf’s settings when possible to confirm the active file. Paths can differ in managed or future releases; check the client documentation if this location is not present. Merge this example with existing settings; do not overwrite unrelated servers.
{
"mcpServers": {
"context-portal": {
"command": "uvx",
"args": [
"--from",
"context-portal-mcp",
"conport-mcp",
"--mode",
"stdio",
"--log-file",
"./logs/conport.log",
"--log-level",
"INFO"
],
"env": {}
}
}
}Config file · Project scope: .mcp.json at the repository root
The project file uses mcpServers. For user scope, use claude mcp add --scope user rather than assuming .mcp.json in your home directory is the user configuration. Check the client documentation for managed settings and storage details. Merge this example with existing settings; do not overwrite unrelated servers.
{
"mcpServers": {
"context-portal": {
"type": "stdio",
"command": "uvx",
"args": [
"--from",
"context-portal-mcp",
"conport-mcp",
"--mode",
"stdio",
"--log-file",
"./logs/conport.log",
"--log-level",
"INFO"
],
"env": {}
}
}
}Examples are translated from the published configuration. Supply your own credentials and verify requirements in the upstream README. Remote connectors are shown only where a supported configuration format is known.
Tools
Source: repository README. Tool descriptions are a documented snapshot, not a live capability check.
| Tool | What it does |
|---|---|
| get_conport_schema | Discover exact ConPort tool names and parameter schemas dynamically. |
Names, permissions, and defaults can change. Check the current upstream documentation before granting access.
Use cases
- Retain architectural decisions across assistant sessions.
- Track tasks, progress, and project-specific terminology.
- Build linked project context for retrieval-augmented assistance.
- Bootstrap product context from an approved project brief.
Strengths
- Stores structured memory separately for each workspace.
- Combines explicit knowledge relationships with semantic search.
- Provides assistant-specific strategies and a generic discovery approach.
- Recommended uvx execution avoids manual environment management.
Limitations
- Some IDEs do not expand workspace variables as expected.
- Reliable agent use benefits from initialization and custom-instruction setup.
Frequently asked questions
Independent listing, not an affiliation or security review. Grant the least access needed and verify the upstream instructions before running code.
