Project MCP Server
@tejpalvirk
About Project MCP Server
MCP server for project management
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"project": {
"command": "npx",
"args": [
"-y",
"github:tejpalvirk/project"
]
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is Project MCP Server?
Project MCP Server is an MCP server that provides tools for managing project knowledge graphs, enabling structured representation of projects, tasks, milestones, resources, and team members. It helps project managers track progress, manage risks, allocate resources, and make informed decisions.
How to use Project MCP Server?
Install it with npx -y github:tejpalvirk/project, globally via npm install -g github:tejpalvirk/project, or via Docker. Configure it in claude_desktop_config.json under mcpServers.project. Use tools like startsession, loadcontext, buildcontext, and endsession to interact with the project knowledge graph. Storage paths can be customized with environment variables MEMORY_FILE_PATH (default ./project/memory.json) and SESSIONS_FILE_PATH (default ./project/sessions.json).
Key features of Project MCP Server
- Persistent project context across multiple sessions
- Session management with unique IDs and progress tracking
- Real‑time project health, risk, and issue status monitoring
- Task dependency visualization to identify bottlenecks
- Milestone progress and resource allocation tracking
- Decision logging, team member management, and timeline analysis
Use cases of Project MCP Server
- Maintain context continuity across project planning and review sessions
- Onboard new team members by loading full project context
- Document meeting outcomes and session results with structured data
- Visualize task dependencies, critical paths, and risk mitigation
- Optimize resource allocation and prioritize high‑priority work
FAQ from Project MCP Server
What entity types does Project MCP Server support?
It supports 16 entity types: project, task, milestone, resource, teamMember, note, document, issue, risk, decision, dependency, component, stakeholder, change, status (inactive/active/complete), and priority (high/low).
How is data persisted between sessions?
Data is stored in two files: a knowledge graph (memory.json by default) and session history (sessions.json by default). Paths can be customized via MEMORY_FILE_PATH and SESSIONS_FILE_PATH environment variables.
What tools are available for managing the knowledge graph?
Tools include startsession, loadcontext, endsession, buildcontext (create entities/relations/observations), deletecontext, and advancedcontext (search, graph retrieval, status/priority/sequence queries).
How can I analyze project risks or task sequences?
Domain‑specific functions like getProjectRisks, getTaskDependencies, getTaskSequence, getProjectHealth, and getPriorityItems are built into the server and can be invoked via MCP.
Frequently asked questions
What entity types does Project MCP Server support?
It supports 16 entity types: project, task, milestone, resource, teamMember, note, document, issue, risk, decision, dependency, component, stakeholder, change, status (inactive/active/complete), and priority (high/low).
How is data persisted between sessions?
Data is stored in two files: a knowledge graph (`memory.json` by default) and session history (`sessions.json` by default). Paths can be customized via `MEMORY_FILE_PATH` and `SESSIONS_FILE_PATH` environment variables.
What tools are available for managing the knowledge graph?
Tools include `startsession`, `loadcontext`, `endsession`, `buildcontext` (create entities/relations/observations), `deletecontext`, and `advancedcontext` (search, graph retrieval, status/priority/sequence queries).
How can I analyze project risks or task sequences?
Domain‑specific functions like `getProjectRisks`, `getTaskDependencies`, `getTaskSequence`, `getProjectHealth`, and `getPriorityItems` are built into the server and can be invoked via MCP.
Basic information
More Other MCP servers
Codelf
unbugA search tool helps dev to solve the naming things problem.

Peekaboo MCP – lightning-fast macOS screenshots for AI agents
steipetePeekaboo is a macOS CLI & optional MCP server that enables AI agents to capture screenshots of applications, or the entire system, with optional visual question answering through local or remote AI models.
Mcp
browsermcpBrowser MCP is a Model Context Provider (MCP) server that allows AI applications to control your browser
Awesome Mlops
visengerA curated list of references for MLOps
AutoBrowser MCP
autobrowser-aiBrowser MCP is a Model Context Provider (MCP) server that allows AI applications to control your browser
Comments