MCP.Market

Vaiz MCP server

by vaiz.com·com.vaiz/mcp·v1.1.2·1 stars
No reviews yet

Connect AI assistants to your Vaiz workspace: tasks, projects, boards, documents and milestones.

C60/100grade C
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
C60/100

full report

Adoption
Growing

1 stars43 downloads/wk

Reviews

Write one

Nobody has reviewed Vaiz yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Vaiz tools (33, 3 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • create_milestonewrite action

    Create a new milestone in a board. The description field is a short plain-text summary (NOT Markdown). To add rich document content, use edit_document_content after creation.

  • create_taskwrite action

    Create a new task in the Vaiz workspace

  • create_task_commentwrite action

    Create a new comment on a task by database ID or HRID (e.g., "PRJ-123")

  • current_user

    Get detailed information about current authenticated user

  • edit_document_content

    Edit the document content (description) of a task, milestone, or standalone document. Can append to existing content or replace it entirely.

  • edit_task

    Edit an existing task in the Vaiz workspace

  • get_automations

    Get all automations (workflows) for a specific board

  • get_board

    Get detailed information about a specific board by ID

  • get_document

    Get detailed information about a USER document in workspace. For SYSTEM help, use read_resource!

  • get_document_comments

    Get all comments for a specific document

  • get_document_history

    Get history of changes for a specific document

  • get_member

    Get detailed information about a specific workspace member by ID

  • get_milestone

    Get detailed information about a specific milestone by ID

  • get_notifications

    Get user notifications with filtering and pagination support

  • get_project

    Get detailed information about a specific project by ID

  • get_project_history

    Get history of all activities in a specific project across the workspace

  • get_task

    Get detailed information about a specific task by database ID or HRID (e.g., "PRJ-123")

  • get_task_comments

    Get all comments for a specific task by database ID or HRID (e.g., "PRJ-123")

  • get_task_history

    Get history of changes for a specific task

  • get_tasks

    Get a filtered list of tasks with pagination. Supports filtering by board, project, assignees, completion status, priorities, milestones, types, and creator. Examples: - My tasks: get_tasks(assignees: [myMemberId]) - All uncompleted: get_tasks(completed: false) - High priority: get_tasks(priorities: ["3"]) - Specific board: get_tasks(boardId: "...") - By type: get_tasks(types: ["typeId1", "typeId2

  • get_user_history

    Get history of all activities performed by a specific user in the current workspace

  • list_boards

    List all accessible boards in the current space, optionally filtered by project. Examples: - All boards: list_boards() - Boards in project: list_boards(projectId: "...")

  • list_members

    List all members in the current space

  • list_milestones

    List all milestones in the current space, optionally filtered by board or project

  • list_projects

    List all projects in the current space

  • list_resources

    List all available MCP resources (dictionaries, workspace data, etc.)

  • list_spaces

    List all available spaces (spaces) for the current user

  • ping

    Simple ping tool for testing

  • read_resource

    Read content of a specific MCP resource by name. For knowledge base articles, use "vaiz-help-" prefix + article name from the index.

  • search

    Search for entities in YOUR workspace (tasks, projects, users, comments, boards, USER documents). NOT system documentation!

  • select_space

    Select a space to work with

  • set_task_blocker

    Toggle a blocker relationship between two tasks. Direction is relative to taskId: "blockers" = tasks that block taskId, "blocking" = tasks that taskId blocks. taskId and blockerTaskId accept database IDs or HRIDs (e.g. "PRJ-21").

  • space_info

    Get detailed information about current space and user permissions

Public scan report

scanner v0.1.9 · 2026-09-26 · same rubric, same numbers if you re-run it

1 high
  • Code scan17 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitystatic API keys via environment variables6/15
  • Maintenancerepository archived0/15
  • Maintainer identitynamespace and repository owner differ; GitHub account older than a year; website matches verified namespace8/10

Findings (1)

  • highRepository is archivedmaint.archived
Overall 60/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Vaiz compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
60/100
higher than 15% of 48,255 servers
Tools
33
the typical server has 7
Tools that change things
9%
typical: 0%. Fewer write tools means less an agent can break
GitHub stars
1
more than 65% of 28,688 servers
Downloads a week
43
more than 35% of 12,191 servers with a package

What its tools let an agent do: 27 read · 3 create · 3 change

Install Vaiz in Claude Code, Cursor or VS Code

Runs npx -y vaiz-mcp on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add mcp -- npx -y vaiz-mcp
Add to Cursor

What the publisher says

From the Vaiz repository's README, as published. We do not edit it. Read it on GitHub

vaiz-mcp

DEPRECATED. This package is no longer maintained and this repository is archived.

Vaiz now provides a hosted MCP server at https://api.vaiz.com/mcp with OAuth. You no longer need a local npx proxy or a VAIZAPITOKEN.

Cursor users: install the official Vaiz plugin from the Cursor Marketplace — https://github.com/vaizcom/vaiz-cursor-plugin

Any MCP client: point it at the remote server directly.

json

{

"mcpServers": {

"Vaiz": { "url": "https://api.vaiz.com/mcp" }

}

}

Then authenticate when prompted (in Cursor: Settings → Tools & MCPs → Authenticate).

Guide: https://vaiz.com/help/tutorials/how-to-connect-vaiz-to-mcp · Support: https://vaiz.com/support

Existing installations of vaiz-mcp keep working for now, but will not receive updates or security fixes. Please migrate.

The original documentation is kept below for reference.

MCP (Model Context Protocol) client for Vaiz — connect Cursor/Claude to your Vaiz workspace.

Installation

npm install -g vaiz-mcp

Or use directly via npx:

npx vaiz-mcp

Configuration

Environment Variables

Cursor Configuration

Create or edit ~/.cursor/mcp.json:

{
  "mcpServers": {
    "vaiz": {
      "command": "npx",
      "args": ["vaiz-mcp@latest"],
      "env": {
        "VAIZ_API_TOKEN": "your-api-key",
        "VAIZ_SPACE_ID": "your-space-id"
      }
    }
  }
}

Or after global installation (npm install -g vaiz-mcp):

{
  "mcpServers": {
    "vaiz": {
      "command": "vaiz-mcp@latest",
      "env": {
        "VAIZ_API_TOKEN": "your-api-key",
        "VAIZ_SPACE_ID": "your-space-id"
      }
    }
  }
}

Claude Desktop Configuration

Add to claudedesktopconfig.json:

{
  "mcpServers": {
    "vaiz": {
      "command": "npx",
      "args": ["vaiz-mcp@latest"],
      "env": {
        "VAIZ_API_TOKEN": "your-api-key",
        "VAIZ_SPACE_ID": "your-space-id"
      }
    }
  }
}

Usage

After configuration, Cursor/Claude will automatically connect to your Vaiz workspace and gain access to:

  • 🔍 Search tasks, projects, users
  • 📋 Task management (create, edit, comments)
  • 📊 View boards and projects
  • 👥 Team member information
  • 📝 Work with documents and milestones

Debugging

To enable debug output, add the VAIZ_DEBUG variable:

{
  "mcpServers": {
    "vaiz": {
      "command": "npx",
      "args": ["vaiz-mcp@latest"],
      "env": {
        "VAIZ_API_TOKEN": "your-api-key",
        "VAIZ_DEBUG": "true"
      }
    }
  }
}

Debug messages will be output to stderr.

Programmatic Usage

You can also use the library programmatically:

import { createVaizMCPClient } from 'vaiz-mcp';

const client = createVaizMCPClient({
  apiKey: 'your-api-key',
  spaceId: 'your-space-id',
});

// Initialize connection
const initResult = await client.initialize();

// Get list of tools
const tools = await client.listTools();

// Call a tool
const result = await client.callTool('search', { 
  query: 'important task',
  entityType: 'task' 
});

Development

# Clone the repository
git clone https://github.com/vaiz/vaiz-mcp.git
cd vaiz-mcp

# Install dependencies
npm install

# Build the project
npm run build

# Run in development mode
npm run dev

Platforms

License

MIT

Nothing above is checked by us. What we check is on the safety report.

Vaiz: common questions

Is Vaiz MCP server safe?
With care: it is graded C, so read the findings first (60/100). Read the Vaiz safety report
How do I install Vaiz?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Vaiz need an API key?
Yes. The registry entry asks for VAIZ_API_TOKEN.
Is Vaiz maintained?
The last commit was 46 days ago (2026-09-19). The latest release is v1.1.2.
How does Vaiz compare with other MCP servers?
safety score 60/100 (higher than 15% of 48,255 servers); tools 33 (the typical server has 7); tools that change things 9% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.