Manage Astravue spaces, projects, tasks, subtasks, comments, and team membership through an MCP-compatible AI client.
Copy the AI prompt to install this server into Claude Code, Cursor, or another agent ā or use 1-click editor setup below.
š” Paste the JSON block into your client's configuration file under mcpServers, then restart the application.
Inspect callable tools, capabilities, and parameters exposed to AI agents by Astravue MCP.
astravue_list_spacesLists all spaces in your organization
astravue_get_spaceGets details of a specific space including its projects
astravue_create_spaceCreates a new space
astravue_update_spaceUpdates a space name or settings
astravue_delete_spacePermanently deletes a space and all its contents
astravue_list_projectsLists all projects within a space
Astravue MCP MCP server gives AI clients access to an Astravue workspace. The listed operations cover the main hierarchy of an Astravue organization: spaces contain projects, projects contain tasks, and tasks can contain subtasks and comments.
You can browse spaces and projects, retrieve detailed records, and search for tasks across projects. Write operations support creating, updating, moving, duplicating, and deleting tasks. The server also supports personal tasks, project membership changes, task counts, subtasks, and task comments.
Destructive actions are available for spaces, projects, and tasks. Deleting a space removes its contents, while deleting a project removes its tasks, so clients should request confirmation before invoking those operations where appropriate.
The server is cloud-based and exposes the MCP endpoint at https://api.astravue.com/mcp. Clients connect using Streamable HTTP rather than running a local process. On the first connection, the user signs in to Astravue in a browser and approves access.
Authentication uses OAuth 2.0. Requests operate with the user's existing Astravue permissions, so the server does not provide access beyond what that account can already access. The MCP client then presents the available Astravue operations to the AI assistant for natural-language requests.
The Astravue MCP MCP server can support both read and write workflows. Examples include finding overdue or incomplete work through task counts, creating several tasks in one call, changing several tasks together, moving a task between projects, or adding a comment to an existing task.
Use the client's MCP configuration to add the shared endpoint:
Claude Code can add the server directly with:
Claude Desktop, Claude.ai, and Claude Mobile can connect through the Astravue entry in Claude's Connectors Directory. The README also documents direct setup for Cursor, VS Code, Windsurf, Cline, JetBrains IDEs, and Gemini CLI. After connecting, complete the browser sign-in and approval flow.
Claude Code users can alternatively install the Astravue plugin. That option bundles the MCP connection with eight pre-built project-management skills; installing only the MCP server provides the raw tool connection without those bundled skills.
The server requires an Astravue account and an approved OAuth connection. Its effective access is limited by the connected user's Astravue permissions.
The documented connection is remote and uses Streamable HTTP; the provided setup material does not describe a local stdio deployment or server-specific environment variables. The listed MCP tools focus on spaces, projects, tasks, subtasks, and comments. Although the broader README mentions time entries and custom fields, those capabilities are not represented in the supplied tool list and should be verified before depending on them.
Factual signals from GitHub, npm, and our automated checks ā not a rating.
No reviews yet ā be the first to share how this listing worked for you.
Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
[](https://allmcps.com/mcp/astravue-mcp-2)<a href="https://allmcps.com/mcp/astravue-mcp-2"><img src="https://allmcps.com/api/badge/astravue-mcp-2?style=directory" alt="Astravue MCP on AllMCPs" /></a>