How do I install Astravue MCP?

Copy the http config for Cursor, Claude Desktop, Claude Code, or VS Code on this page. It uses the publisher's install, not a PlugMCP proxy.

Does Astravue MCP need an API key?

No required environment variable is listed on this record.

What transport does Astravue MCP use?

Astravue MCP is reached over HTTP.

When was Astravue MCP last checked?

Last checked 2026-11-10. Manage projects, tasks, time tracking, and team collaboration through natural language.

Astravue MCP server

Astravue MCP Server

The Astravue MCP Server is a cloud-based bridge between your Astravue workspace and compatible AI tools. Once configured, it enables those tools to interact with your spaces, projects, tasks, time entries, and custom fields in real time. All actions are authenticated via OAuth 2.0 and respect the user's existing access controls.

With the Astravue MCP Server, you can:

Search and browse spaces, projects, and tasks without switching tools.
Create and update tasks, subtasks, checklists, and comments through natural language.
Track time with live timers or manual entries and generate timesheet reports.
Manage custom fields including dropdowns, dates, currencies, and more.
Automate workflows like sprint planning, status reporting, and bulk task updates.

It's designed for project managers, developers, and teams who use AI-powered IDEs or assistants and want to manage work without context switching.

Full product documentation lives at docs.astravue.com.

Astravue is a verified and reviewed integration in the Claude Connectors Directory.

Supported Clients

All clients connect to the same endpoint: https://api.astravue.com/mcp You will be asked to sign in to Astravue in your browser the first time you connect.

Client	Docs	Transport
Claude Code	MCP setup	Streamable HTTP
Claude Desktop	Connectors Directory	Streamable HTTP
Claude.ai (Web)	Connectors Directory	Streamable HTTP
Claude Mobile	Connectors Directory	Streamable HTTP
Cursor	MCP setup	Streamable HTTP
VS Code	MCP setup	Streamable HTTP
Windsurf	MCP setup	Streamable HTTP
Cline	MCP setup	Streamable HTTP
JetBrains IDEs

Setup Instructions

Claude Connectors Directory (recommended)

Astravue is available as a verified connector across Claude.ai, Claude Desktop, Claude Mobile, Claude Code, and Cowork.

In Claude.ai or Claude Desktop, go to Customize → Connectors.
Click +, browse the Connectors Directory, and search for Astravue.
Select Astravue, click Connect, then sign in to Astravue and approve access.
Start a new conversation and enable Astravue from the + → Connectors menu.

When Claude Code is authenticated with your Claude.ai subscription, the connector is available automatically. Run /mcp to confirm it is connected. Claude Code sessions using an API key, Bedrock, or Vertex do not load Claude.ai connectors; use the direct connection command below instead.

Claude Code

The Connectors Directory provides the verified MCP connection. For eight guided project-management workflows as well, install the Astravue plugin. A direct MCP connection remains available for API-key, Bedrock, Vertex, and custom setups.

Option A — Install as a Claude Code plugin (recommended)

The plugin bundles the MCP server with eight pre-built skills that automate common project management workflows. It is listed in Anthropic's community plugin marketplace.

Inside Claude Code, run:

/plugin marketplace add anthropics/claude-plugins-community
/plugin install astravue@claude-community
/reload-plugins

Alternatively, install directly from this repository:

/plugin marketplace add AstravueOrg/astravue-mcp-server
/plugin install astravue@astravue
/reload-plugins

After install, run /mcp to confirm astravue is connected, then open /plugin and switch to the Installed tab to view the bundled skills.

See Anthropic's plugin discovery docs for installation scopes (user, project, local).

Option B — Install only the MCP server

If you only want the raw MCP server without the bundled skills, run:

claude mcp add --transport http astravue https://api.astravue.com/mcp

Your browser will open automatically. Sign in with your Astravue account and click Approve.

To confirm the connection, run /mcp in a new Claude Code session. You should see astravue listed with a green connected status.

Add the --scope project flag to create a .mcp.json file in your project root:

claude mcp add --transport http --scope project astravue https://api.astravue.com/mcp

Commit .mcp.json to your repository so teammates automatically get the connection.

Claude Desktop

Go to Customize → Connectors in Claude Desktop.
Click +, browse the directory, and search for Astravue.
Select Astravue, click Connect, then sign in and approve access.

If Connectors is not available in your Claude Desktop version, edit:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "astravue-mcp": {
      "type": "http",
      "url": "https://api.astravue.com/mcp"
    }
  }
}

Save the file and restart Claude Desktop.

Claude.ai (Web)

Go to claude.ai → Customize → Connectors.
Click +, browse the directory, and search for Astravue.
Select Astravue, click Connect, then sign in and approve access.

Claude Mobile (iOS / Android)

Claude Mobile uses the same connector ecosystem as Claude.ai. Connect Astravue from the mobile Connectors Directory, or connect it once on Claude.ai or Claude Desktop and use the same Claude account on mobile.

Cursor

Go to Cursor Settings → Tools & MCP
Click New MCP Server — this opens your mcp.json file
Add the following configuration:

{
  "mcpServers": {
    "astravue-mcp": {
      "url": "https://api.astravue.com/mcp"
    }
  }
}

Save the file. Your browser will open — sign in with your Astravue account and click Approve.

Create a .cursor/mcp.json file in your project root with the same config above. This scopes the connection to that project only.

VS Code

Add a .vscode/mcp.json file to your project root:

{
  "servers": {
    "astravue-mcp": {
      "type": "http",
      "url": "https://api.astravue.com/mcp"
    }
  }
}

Open Command Palette (Cmd+Shift+P on macOS, Ctrl+Shift+P on Windows), run MCP: List Servers, and click Start next to astravue-mcp.
Authenticate with your Astravue account in the browser.

Add this to your User Settings (JSON):

{
  "mcp": {
    "servers": {
      "astravue-mcp": {
        "type": "http",
        "url": "https://api.astravue.com/mcp"
      }
    }
  }
}

Windsurf

Open the Windsurf MCP config file:
- macOS / Linux: ~/.codeium/mcp_config.json
- Windows: C:\Users\[username]\.codeium\mcp_config.json
- Or go to Settings → Tools → Windsurf Settings → Add Server
Add the following:

{
  "mcpServers": {
    "astravue-mcp": {
      "serverUrl": "https://api.astravue.com/mcp"
    }
  }
}

If you already have other servers in your config, add astravue-mcp alongside them inside the existing mcpServers object — don't replace the entire file.

Reload Windsurf and authenticate with your Astravue account.

Cline

Click the Cline icon in the VS Code sidebar → click the menu (⋮) in the top right → select MCP Servers.
Go to the Remote Servers tab and fill in:
- Server Name: astravue-mcp
- Server URL: https://api.astravue.com/mcp
- Transport Type: Streamable HTTP
Click Add Server. Your browser will open — sign in and click Approve.

Click Configure MCP Servers in the Configure tab to open cline_mcp_settings.json and add:

{
  "mcpServers": {
    "astravue-mcp": {
      "url": "https://api.astravue.com/mcp",
      "type": "streamableHttp"
    }
  }
}

JetBrains (IntelliJ, WebStorm, PyCharm, etc.)

Go to Settings → Tools → AI Assistant → Model Context Protocol (MCP)
Click Add → Select Streamable HTTP → Paste:

{
  "mcpServers": {
    "astravue-mcp": {
      "url": "https://api.astravue.com/mcp"
    }
  }
}

Click OK, then Apply. Sign in with your Astravue account in the browser.

Gemini CLI

Copy gemini-extension.json from this repository to your Gemini CLI extensions directory, or add the server URL to your Gemini MCP configuration.

Other MCP Clients

For any client that supports Streamable HTTP + OAuth 2.0:

Setting	Value
Server URL	`https://api.astravue.com/mcp`
Transport	Streamable HTTP
Authentication	OAuth 2.0 (Authorization Code + PKCE)

If your client only supports SSE transport, run:

npx -y mcp-remote@latest https://api.astravue.com/mcp

Point your client to the local mcp-remote process instead of the Astravue URL.

How It Works

Astravue MCP exposes workspace operations as tools that AI assistants can call. Each tool performs a specific action in your Astravue workspace such as creating projects, managing tasks, logging time, or retrieving reports.

When an AI assistant receives a request, it selects the appropriate tool based on the user's prompt and executes it with the required parameters.

Authentication: All tools require an active authenticated session. If a tool call fails with 401 Unauthorized, reconnect your AI client to refresh your session.

Destructive actions: Some tools perform destructive actions such as deleting tasks, projects, or spaces. Most AI clients require confirmation before executing these operations. Always review actions before approving them.

Permissions

Astravue MCP respects the same role-based access control as the Astravue web app. Every tool call is executed as your authenticated user with your existing permissions. You cannot access or modify anything through MCP that you cannot access in the app.

Organization Roles

Role	MCP Access
Account Admin	Full access to all spaces, projects, and tasks across the organization
Admin	Full access to all spaces, projects, and tasks across the organization
Manager	Can manage spaces and projects they are a member of
Member	Can read and write within spaces and projects they belong to
Guest	Read-only. Cannot perform any write operations through MCP

Space-Level Permissions

Action	Required Role
List spaces, view space details	Space Member
Create, update, delete a space	Org Admin or Manager

Project-Level Permissions

Action	Required Role
List tasks, view project details	Project Member
Create or update tasks	Project Member
Add project members, delete project	Project Admin
Manage custom fields, statuses	Project Admin

Task-Level Permissions

Action	Required Role
View tasks, comments, checklists	Project Member
Create tasks, add comments, log time	Project Member
Delete a task	Task Owner, Task Creator, or Project Admin
Delete a comment	Comment Creator or Org Admin

If a tool call returns 403 Access Denied, it means your account does not have the required role for that action. Contact your workspace admin to update your permissions.

Example Workflow

A user asks an AI assistant:

"Create a new sprint called Sprint 5 and add tasks for login, payments, and API docs."

The AI assistant may execute these tools:

astravue_create_project — creates the Sprint 5 project
astravue_bulk_create_tasks — creates the three tasks in one call
astravue_update_task — sets priorities or due dates as needed

This allows complex project setup to be completed from a single conversation.

Available Tools

The Astravue MCP Server provides 87 tools across the following categories.

Tool	Description	Example Prompt
`astravue_list_spaces`	Lists all spaces in your organization	"Show me all my spaces"
`astravue_get_space`	Gets details of a specific space including its projects	"What projects are in the Design space?"
`astravue_create_space`	Creates a new space	"Create a space called Product Development"
`astravue_update_space`	Updates a space name or settings	"Rename the Marketing space to Growth"
`astravue_delete_space`	Permanently deletes a space and all its contents	"Delete the archived Test space"

Tool	Description	Example Prompt
`astravue_list_projects`	Lists all projects within a space	"List all projects in the Engineering space"
`astravue_get_project`	Gets full details of a specific project	"What's the current status of Sprint 3?"
`astravue_create_project`	Creates a new project inside a space	"Create a project called Q2 Roadmap in the Product space"
`astravue_update_project`	Updates a project's name, status, priority, or health	"Mark Sprint 1 as completed"
`astravue_delete_project`	Permanently deletes a project and all its tasks	"Delete the duplicate Onboarding project"
`astravue_add_project_member`	Adds an existing workspace member to a project	"Add [email protected] to the Backend project"

Tool	Description	Example Prompt
`astravue_list_project_tasks`	Lists all tasks within a project	"Show all open tasks in Sprint 2"
`astravue_get_task`	Gets full task details	"What's the status of the login bug task?"
`astravue_find_tasks`	Searches tasks by keyword across all projects	"Find all tasks related to payments"
`astravue_create_task`	Creates a task in a project	"Create a high priority task: Fix authentication bug"
`astravue_update_task`	Updates task fields	"Assign the API docs task to Sarah"
`astravue_delete_task`	Deletes a task	"Delete the duplicate checkout task"
`astravue_move_task`	Moves a task from one project to another	"Move the login task from Sprint 1 to Sprint 2"
`astravue_duplicate_task`	Creates a copy of an existing task	"Duplicate the API integration task with all subtasks"
`astravue_create_personal_task`	Creates a personal task not tied to any project	"Remind me to review the design doc by Friday"
`astravue_bulk_create_tasks`	Creates multiple tasks in one call	"Create these 10 sprint tasks with owners and priorities"
`astravue_bulk_update_tasks`	Updates multiple tasks at once	"Set all 5 sprint tasks to In-Progress"
`astravue_bulk_delete_tasks`

Tool	Description	Example Prompt
`astravue_list_subtasks`	Lists subtasks under a parent task	"Show the subtasks of the authentication feature"
`astravue_create_subtask`	Creates a new subtask	"Add a subtask: Write unit tests under the API task"
`astravue_update_subtask`	Updates a subtask's title, status, or priority	"Mark the unit tests subtask as done"
`astravue_delete_subtask`	Deletes a subtask	"Delete the duplicate subtask under the API task"

Tool	Description	Example Prompt
`astravue_get_task_comments`	Lists comments on a task	"Show me all comments on the login bug task"
`astravue_add_task_comment`	Adds a comment to a task	"Comment on the API task: Blocked pending design review"
`astravue_update_task_comment`	Edits an existing comment	"Update my comment to say: Unblocked, ready for review"
`astravue_delete_task_comment`	Deletes a specific comment	"Delete my last comment on the API task"

Tool	Description	Example Prompt
`astravue_get_task_checklists`	Gets all checklist items on a task	"Show the checklist on the deployment task"
`astravue_create_checklist_item`	Adds a new checklist item	"Add a checklist item: Run integration tests"
`astravue_update_checklist_item`	Updates a checklist item's title or completion state	"Mark 'Run integration tests' as done"
`astravue_delete_checklist_item`	Deletes a checklist item	"Remove the 'Update changelog' item from the checklist"

Tool	Description	Example Prompt
`astravue_add_dependency`	Links two tasks with a blocking relationship	"Database schema must complete before API implementation"
`astravue_list_dependencies`	Shows all dependencies for a task	"What does the API implementation task depend on?"
`astravue_remove_dependency`	Removes a dependency link	"Remove the dependency between design and implementation"

Tool	Description	Example Prompt
`astravue_list_tags`	Lists all tags available in your organization	"What tags do we have?"
`astravue_add_tag_to_task`	Adds an existing tag to a task	"Tag the login task as 'urgent'"
`astravue_remove_tag_from_task`	Removes a tag from a task	"Remove the 'blocked' tag from the deployment task"

Tool	Description	Example Prompt
`astravue_list_attachments`	Lists all attachments on a task	"What files are attached to the design task?"
`astravue_delete_attachment`	Deletes an attachment from a task	"Remove the old mockup file from the design task"

Tool	Description	Example Prompt
`astravue_start_timer`	Starts a timer on a task	"Start tracking time on the API documentation task"
`astravue_stop_timer`	Stops the active timer	"Stop my timer"
`astravue_get_active_timers`	Lists running timers	"Do I have any active timers?"
`astravue_log_manual_time`	Logs a time entry with a specific duration	"Log 2 hours on the API documentation task"
`astravue_log_time_range`	Logs time with a start and end time	"Log time from 9am to 11:30am on the backend refactor"
`astravue_get_task_time_entries`	Lists time entries for a task	"How much time was logged on the backend refactor?"
`astravue_get_project_time_entries`	Lists all time entries across a project	"Show all time logged in Sprint 2"
`astravue_get_project_time_summary`	Gets billable vs non-billable time totals	"How many total hours were spent on the Backend project?"
`astravue_get_timesheet_report`	Generates a timesheet report	"Show my timesheet for this week"
`astravue_delete_time_entry`	Deletes a time entry	"Delete the accidental time entry from yesterday"

Tool	Description	Example Prompt
`astravue_get_custom_fields`	Lists all custom fields for a project	"What custom fields are on the Backend project?"
`astravue_create_custom_field`	Creates a new custom field	"Add a custom field called Story Points to Sprint 2"
`astravue_set_custom_field_value`	Sets a custom field value on a task	"Set Story Points to 5 on the login task"
`astravue_create_custom_field_option`	Adds a dropdown option to a custom field	"Add option 'Critical' to the Severity field"
`astravue_list_custom_field_options`	Lists all options for a dropdown field	"What options are available for the Priority field?"
`astravue_delete_custom_field`	Deletes a custom field from a project	"Remove the Story Points field from Sprint 1"
`astravue_delete_custom_field_option`	Deletes a specific option from a dropdown field	"Remove the 'Trivial' option from the Severity field"

Tool	Description	Example Prompt
`astravue_list_task_statuses`	Lists all available statuses for tasks	"What statuses are available in Sprint 2?"
`astravue_list_project_statuses`	Lists status groups configured for a project	"Show the status workflow for the Backend project"
`astravue_create_task_status`	Creates a new task status	"Add a status called 'In Review' to Sprint 2"
`astravue_update_task_status`	Updates a task status name or configuration	"Rename 'In Progress' to 'Working'"
`astravue_delete_task_status`	Deletes a task status from a project	"Remove the 'Blocked' status from Sprint 1"

Tool	Description	Example Prompt
`astravue_list_filters`	Lists saved filters	"Show me my saved filters"
`astravue_create_filter`	Creates a saved filter	"Create a filter for all high priority tasks assigned to me"
`astravue_update_filter`	Updates a saved filter	"Update my overdue filter to include medium priority"
`astravue_delete_filter`	Deletes a saved filter	"Delete the old sprint filter"

Tool	Description	Example Prompt
`astravue_list_overdue_tasks`	Lists overdue tasks assigned to the current user	"Show me everything overdue"
`astravue_list_scheduled_tasks`	Lists upcoming tasks with due dates	"What tasks are due this week?"

Tool	Description	Example Prompt
`astravue_list_notifications`	Lists unread notifications	"What notifications do I have?"
`astravue_mark_notification_read`	Marks notifications as read	"Mark all my notifications as read"

Tool	Description	Example Prompt
`astravue_get_workspace_members`	Lists workspace members	"Who are the members of my workspace?"
`astravue_get_member_by_email`	Finds a member by email	"Find the profile for [email protected]"
`astravue_get_current_user`	Returns the authenticated user's profile	"Who am I logged in as?"

Tool	Description	Example Prompt
`astravue_preview_task_list`	Opens an interactive task list view for a project	"Show me the task board for Sprint 2"
`astravue_preview_my_tasks`	Opens a view of all tasks assigned to the current user	"Show me my tasks"
`astravue_preview_project_overview`	Opens a project overview with completion, health, and attention items	"Give me an overview of the Backend project"

Available Prompts

The Astravue MCP Server provides 15 prompts — pre-built workflows that guide your AI assistant through common project management tasks.

Prompt	Description	Arguments
`daily_standup`	Generate a structured daily standup update for the current user based on their tasks	—
`project_status_report`	Generate a professional project status report tailored for executive, stakeholder, or team audience	—
`weekly_team_digest`	Generate a weekly digest summarising what shipped, what is at risk, and what is coming up	—
`task_breakdown`	Suggest a subtask decomposition for a complex task to make it actionable	—
`overdue_action_plan`	Generate a prioritised recovery plan for the current user's overdue tasks	—
`sprint_planner`	Plan a sprint: select tasks by priority, estimate workload, assign owners, and define the sprint goal	`sprintGoal` (required)
`risk_assessment`	Identify at-risk projects and tasks: overdue items, off-track projects, unassigned high-priority work, and deadline conflicts	—
`time_tracking_report`	Generate a time tracking and effort summary for the current user across tasks	—
`meeting_agenda_generator`	Generate a structured meeting agenda based on current tasks, blockers, and project status	`meetingType` (optional): `standup`, `sprint_review`, `planning`, `retrospective`, `stakeholder_update`
`retrospective_summary`	Generate a sprint or project retrospective: what went well, what did not, and action items

Available Resources

The Astravue MCP Server provides 6 resources — context data that AI assistants can attach to conversations for richer, more accurate responses.

Static Resources

Resource URI	Name	Description
`astravue://user/me`	Current User Profile	The authenticated user's profile: ID, name, email, and organisation role. Read at session start to establish user context before assigning tasks or personalising any response.
`astravue://org/members`	Organisation Members	All active members of the organisation with user IDs, names, emails, and roles. Use to resolve teammate names to numeric IDs before any task assignment operation.
`astravue://org/spaces`	Organisation Spaces	All spaces the current user is a member of. Use to discover space IDs before calling project or task tools.
`astravue://dashboard/overview`	Dashboard Overview	Current user's task count summary: total, pending, completed, and overdue. Use for a quick org health snapshot.

Resource Templates

Template URI	Name	Description
`astravue://spaces/{spaceId}/projects`	Projects in Space	All projects within a given space. Replace `{spaceId}` with the numeric space ID.
`astravue://spaces/{spaceId}/projects/{projectId}/overview`	Project Overview	Full details of a specific project. Replace `{spaceId}` and `{projectId}` with numeric IDs.

Skills

This repository includes ready-to-use skills that automate common project management workflows:

Skill	Description
Sprint Planning	Analyzes backlog, overdue tasks, and dependencies to build a prioritized sprint plan
Status Report	Generates executive project status reports covering progress, budget, and risks
Time Tracking	Guides timer usage, manual time logging, and timesheet report generation
Custom Fields	Creates, configures, and manages custom fields and dropdown options
Breaking Down Work	Decomposes a goal, feature, or epic into a structured task tree with dependencies
Capturing Meeting Actions	Extracts action items from meeting notes or transcripts and creates owned, dated tasks
Mapping Dependencies	Maps task dependencies, finds the critical path, and detects circular dependencies
Triaging Overdue Work	Reviews overdue and at-risk tasks and proposes reschedule, reassign, or close actions

Skills are available automatically when using the Claude Code or Cursor plugin.

Data and Security

All traffic is encrypted via HTTPS using TLS 1.2 or later.
OAuth 2.0 authentication ensures secure access control.
Data access respects your workspace role and project-level permissions.
The MCP server never stores credentials — authentication is handled per session.

For more details, see SECURITY.md.

Rate Limits

Astravue MCP enforces rate limits to ensure platform stability.


Requests per user per minute	100
Bulk task create limit	100 tasks per call

If the limit is exceeded, the server returns HTTP 429 Too Many Requests. Wait 60 seconds before retrying.

Troubleshooting

Sign out of Astravue at app.astravue.com, sign back in, then reconnect your AI client.

Your OAuth session expired. Reconnect your client to trigger a new sign-in flow.

Ensure your client supports Streamable HTTP transport. Clients that only support SSE must use the mcp-remote bridge (see Other MCP Clients).

OAuth tokens expire periodically. Your client should refresh automatically. If it does not, reconnect once.

FAQ

No. Astravue MCP works on all plans including free.

Yes. Each user authenticates with their own Astravue account.

Astravue MCP only has access to resources your account already has permission to access. All actions are performed as your authenticated user.

No. OAuth 2.0 is required so every action is tied to an authenticated user.

Most AI clients ask for confirmation before executing write operations. Check your client's tool approval settings.

Contributing

We welcome contributions. See CONTRIBUTING.md for guidelines.

Code of Conduct

This project follows the Contributor Covenant.

License

This project is licensed under the Apache License 2.0.

Support

Open an issue on GitHub
Email [email protected]
Visit help.astravue.com