What data does Developer MCP Server persist?
It persists a knowledge graph of entities (projects, components, features, etc.) and their relationships, plus session data. Storage paths are configurable via environment variables.
@tejpalvirk
Basic information
MCP server to help developers manage project context across sessions
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"developer": {
"command": "npx",
"args": [
"-y",
"github:tejpalvirk/developer"
]
}
}
}Starts a new development session and provides information about recent sessions, active projects, high-priority tasks, and upcoming milestones.
Loads detailed context for an entity (project, component, feature, task, etc.) and tracks this context loading as part of the current session.
Performs a structured analysis of the development session through multiple stages (summary, achievements, task updates, new tasks, project status) and records this information in the persistent knowledge graph.
Creates new entities, relations, or observations in the knowledge graph.
Removes entities, relations, or observations from the knowledge graph.
Retrieves information from the knowledge graph with different query types (graph, search, nodes, related, decisions, milestone).
A context management system for software development teams that maintains persistent context across coding sessions, tracking project structure, dependencies, and progress. It is designed for software development teams.
Install via npm (npx github:tejpalvirk/developer), global install (npm install -g github:tejpalvirk/contextmanager/developer), or Docker. Configure in Claude Desktop via claude_desktop_config.json. Use environment variables MEMORY_FILE_PATH and SESSIONS_FILE_PATH to customize data storage. Invoke tools like startsession, loadcontext, endsession, buildcontext, deletecontext, advancedcontext.
It persists a knowledge graph of entities (projects, components, features, etc.) and their relationships, plus session data. Storage paths are configurable via environment variables.
It can be run via npx from GitHub, installed globally via npm, or used as a Docker container. Configuration for Claude Desktop is provided.
Node.js is required for the npm-based installation. Docker is required for the Docker method. No other dependencies are mentioned.
Data is stored in files specified by `MEMORY_FILE_PATH` (default `./developer/memory.json`) and `SESSIONS_FILE_PATH` (default `./developer/sessions.json`). Paths can be absolute or relative.
The README does not mention transport or authentication. It is designed for use with MCP clients like Claude Desktop, presumably using stdio transport.

Ask Claude or ChatGPT what Shopify theme optimization tasks are pending on your store, a remote MCP server for TaskerArmy Agent accounts.

Free MCP server for software end-of-life intelligence: EOL dates, support status, and the 0-100 EOL Risk Score across 480+ tracked products. Agents can check a single version, pull a product's full lifecycle schedule, or
Gives AI agents public URLs (tunnels) for localhost, live HTTP traffic inspection, snapshot publishing, and access control. Part of LocalCan, the ngrok alternative for Mac, Windows and Linux. Free plan.
Query your team's drift, vulnerability, and migration data from any AI assistant. Vibgrate MCP connects Cursor, Claude, ChatGPT, Windsurf, or VS Code to Vibgrate Cloud: 51 tools for DriftScores, CVEs and EOL runtimes, up

Windframe MCP gives your AI the design taste needed to create consistent, production-ready UI that feels intentionally designed. Available at https://windframe.dev/mcp
Comments