What can you do with this server?

This server provides a single universal zenkit(method, path, body) tool for direct, raw access to the Zenkit API, supporting any current or future endpoint. * Explore workspaces: List all workspaces and their associated lists/projects, or fetch details for a specific workspace * Browse list fields: Retrieve field definitions (names, UUIDs, types, and predefined category values) for any list * Read entries: Fetch entries from any list with pagination support (limit/skip) * Create entries: Add new entries with titles, descriptions, and custom field properties (text, numbers, arrays, category dropdowns) * Update entries: Modify existing entries (title and/or specific field values) via PATCH * Delete entries: Remove entries from any list by UUID * Category/dropdown management: Set predefined category values using their numeric IDs * Full HTTP method support: Use GET, POST, PATCH, PUT, and DELETE for any valid Zenkit API endpoint The pass-through design replaces multiple specialized tools with one consistent interface, ensuring compatibility with both current and future Zenkit API endpoints.

How do I use mcp-zenkit?

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@mcp-zenkit List all my Zenkit collections" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

mcp-zenkit

by wbgrds

Overview Schema Source Related Servers Discussions Admin

JavaScript

Remote

Zenkit MCP Server (Raw API)

Direct Zenkit API access for Claude Desktop. Full control via single universal tool.

Installation

Option 1: Automated Installation (Recommended)

Using Node.js:

curl -O https://raw.githubusercontent.com/wbgrds/mcp-zenkit/main/install.js
node install.js

Using Bash:

bash <(curl -s https://raw.githubusercontent.com/wbgrds/mcp-zenkit/main/install.sh)

In Claude Code:

Open this repo in Claude Code
Say: "Run install.js"
Provide your Zenkit API key
Done!

The installer will:

Clone the repository
Install Node dependencies
Create .env with your API key
Build TypeScript → JavaScript
Test the MCP server
Output Claude Desktop configuration

Option 2: Manual Installation

# 1. Clone repo
git clone https://github.com/wbgrds/mcp-zenkit.git
cd mcp-zenkit

# 2. Install dependencies
npm install

# 3. Build TypeScript
npm run build

# 4. Create .env with your API key
echo "ZENKIT_API_KEY=your-api-key" > .env

Configure Claude Desktop

Find your configuration file:

macOS/Linux:

~/.config/Claude/claude_desktop_config.json

Windows:

%APPDATA%\Claude\claude_desktop_config.json

Edit or create it with:

{
  "mcpServers": {
    "zenkit": {
      "command": "node",
      "args": ["/path/to/mcp-zenkit/dist/index.js"],
      "env": {
        "ZENKIT_API_KEY": "your-zenkit-api-key"
      }
    }
  }
}

Replace /path/to/mcp-zenkit with your actual installation path.

Get your API key: https://zenkit.com/en/user/profile/developer/

Restart Claude Desktop after configuration.

Related MCP server: Vikunja MCP Server

Usage

Single tool: zenkit(method, path, body)

Get Workspaces

zenkit('GET', '/workspaces')

Response: All workspaces + lists

Get Lists in Workspace

zenkit('GET', '/workspaces/123')

Get List Fields (Elements)

zenkit('GET', '/lists/123/elements')

Returns: Field names, UUIDs, types, predefined values (for categories)

List Entries

zenkit('POST', '/lists/123/entries', {
  limit: 100,
  skip: 0
})

Create Entry

zenkit('POST', '/lists/123/entries', {
  title: "My Task",
  description: "Optional description",
  properties: {
    "field-uuid-1": "value",
    "field-uuid-2": 123,
    "field-uuid-3": ["array", "of", "values"]
  }
})

To find field UUIDs: zenkit('GET', '/lists/123/elements')

Update Entry

zenkit('PATCH', '/lists/123/entries/entry-uuid', {
  title: "Updated Title",
  properties: {
    "field-uuid": "new-value"
  }
})

Delete Entry

zenkit('DELETE', '/lists/123/entries/entry-uuid')

Architecture

Version 2.0 (Approach B: Raw API)

One universal tool zenkit(method, path, body)
Direct pass-through to Zenkit API
No abstraction layer, no hidden logic
Token-based auth = full account control

What changed from v1:

Removed: zenkit_create_entry, zenkit_update_entry, zenkit_get_entries, etc.
Added: Single zenkit tool for all operations
Benefit: Works for any Zenkit API endpoint (present + future)

API Reference

Full Zenkit API docs: https://zenkit.com/api/

Common Endpoints

Operation	Method	Path	Body
List workspaces	GET	`/workspaces`	—
Get workspace	GET	`/workspaces/{id}`	—
List entries	POST	`/lists/{id}/entries`	`{limit, skip}`
Get fields	GET	`/lists/{id}/elements`	—
Create entry	POST	`/lists/{id}/entries`	`{title, properties}`
Update entry	PATCH	`/lists/{id}/entries/{uuid}`	`{title, properties}`
Delete entry	DELETE	`/lists/{id}/entries/{uuid}`	—

Examples

Workflow: Create and Update

1. zenkit('GET', '/workspaces')
   → Find workspace ID

2. zenkit('GET', '/lists/123/elements')
   → Find field UUIDs you need

3. zenkit('POST', '/lists/123/entries', {
     title: 'New Task',
     properties: { 'field-uuid': 'value' }
   })
   → Create entry, get entry UUID back

4. zenkit('PATCH', '/lists/123/entries/entry-uuid', {
     title: 'Updated Task'
   })
   → Update the entry

Working with Categories (Dropdowns)

When predefinedValues are present in get_list_fields response, they are category options:

{
  "name": "Status",
  "uuid": "a1b2c3d4-...",
  "predefinedValues": [
    { "id": 1, "name": "Draft" },
    { "id": 2, "name": "In Progress" },
    { "id": 3, "name": "Done" }
  ]
}

Use the id value when setting properties:

zenkit('POST', '/lists/123/entries', {
  title: 'Task',
  properties: {
    'a1b2c3d4-...': 2  // ← Category ID for "In Progress"
  }
})

Troubleshooting

Problem	Cause	Solution
"ZENKIT_API_KEY is required"	Environment variable missing	Check `claude_desktop_config.json`, restart Claude
"npm: command not found"	Node.js not installed	Install Node.js >= 18 from nodejs.org
"Git clone fails"	Git not installed	Install Git
"Claude doesn't see tool"	Config not reloaded	Restart Claude Desktop completely
"Zenkit API error 404"	Wrong path or resource doesn't exist	Use `zenkit('GET', '/workspaces')` to discover IDs
"Field UUID not found"	UUID is incorrect	Get correct UUIDs via `zenkit('GET', '/lists/123/elements')`

Environment Variables

ZENKIT_API_KEY (required): Zenkit API token
ZENKIT_API_BASE (optional): Override API base URL (default: https://base.zenkit.com/api/v1)

Development

# Install dependencies
npm install

# Build TypeScript
npm run build

# Run locally (requires ZENKIT_API_KEY env var)
ZENKIT_API_KEY=xxx npm run start

License

MIT

Support

Zenkit API docs: https://zenkit.com/api/
Issues: https://github.com/wbgrds/mcp-zenkit/issues

Complete Documentation

README.md – Installation & Quick Start
CHANGELOG.md – Version History & Migration Guide (v1 → v2)
TOOL_REFERENCE.md – Comprehensive Tool Usage & Examples
Zenkit API Docs – Official API Reference

Available Tools

1 tool

zenkitB

Raw Zenkit API access. Complete control over any Zenkit operation via direct API calls. Pass method, path, and optional body.

ParametersJSON Schema

Name	Required	Description
`body`	No	Request body for POST/PATCH/PUT operations (optional for GET/DELETE)
`path`	Yes	Zenkit API path (e.g., /workspaces, /lists/123/entries, /lists/123/elements). Full path without base URL.
`method`	Yes	HTTP method

TDQS

B3.4/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description does not disclose any behavioral traits such as destructiveness, idempotency, or error handling. Without annotations, this is a significant gap for a raw API tool that can perform arbitrary operations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three concise sentences with no wasted words. The purpose is front-loaded effectively.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Missing key information: no mention of return value format, error handling, authentication, or preconditions. For a raw API tool with no output schema, more context is needed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3. The description merely repeats parameter names without adding meaningful context beyond the schema descriptions. No additional format or constraint details.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it provides raw access to the Zenkit API with complete control over any operation. This is a specific and unambiguous purpose, distinguishing it as a low-level gateway.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit when-to-use or when-not-to-use guidance is given. It implies advanced usage via 'Complete control' but lacks alternatives or context for choosing this tool over higher-level abstractions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

1 tool updatev1.0.0Jul 12, 2026
- First observedzenkit

Deploy Server

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A3.7/5.0

Scored 2026-07-12 04:50 across 1 tool

Disambiguation5/5

Only one tool exists, so there is no possibility of confusion between tools. The tool's purpose is clearly defined as raw API access.

Naming Consistency5/5

With only one tool named 'zenkit', there is no inconsistency. The name matches the server's domain and is clear.

Tool Count3/5

A single tool for a server providing Zenkit access feels thin. While the tool is powerful, it lacks specialization, making the set minimal.

Completeness5/5

The tool provides raw API access to all Zenkit operations, offering complete coverage of the domain. No obvious gaps exist.

Maintenance

ActivityStale

ResponsivenessNo issues

Resources

GitHub Repository

Need Help?

Related Servers

Related MCP Connectors

Astravue MCPOAuth
com.astravue
Manage projects, tasks, time tracking, and team collaboration through natural language.
Project Management Workplace & Productivity
312
kesslerio-attio-mcp-server-betaOAuth
ai.smithery
Streamline your Attio workflows using natural language to search, create, update, and organize com…
Customer Data Platforms App Automation Workplace & Productivity
269
SuperlistOAuth
io.github.superlistapp
Manage Superlist tasks and lists in plain language from any MCP-compatible AI agent.
Project Management Workplace & Productivity
2
mcp A
com.googleapis.firestore
Interact with your Google Cloud Firestore resources using natural language commands.
Databases Cloud Platforms Search
232

Related MCP Servers

Focalboard MCP Server
Project Management App Automation Workplace & Productivity
gmjuhasz
F
license
A
quality
D
maintenance
Enables task and board management in Focalboard through natural language, supporting board operations, card creation/updates, and column movements with automatic authentication and user-friendly property names.
Updated a year ago (2025-11-03 15:36 UTC)
10
4
-
Vikunja MCP Server
Project Management Workplace & Productivity
Wosh-i
A
license
B
quality
D
maintenance
Enables interaction with Vikunja task management instances through natural language. Supports comprehensive project and task operations including CRUD, assignments, labels, comments, relations, and attachments.
Updated 6 months ago (2026-04-06 17:39 UTC)
33
16 npm
2
MIT
mcp-server-interview
Project Management Workplace & Productivity
matilarrazabal
F
license
C
quality
D
maintenance
Enables managing todo lists and tasks through natural language, supporting creation, status changes, and deletion.
Updated a year ago (2025-06-24 19:37 UTC)
7
-
Nextcloud Task MCP Server
Project Management Workplace & Productivity
Vando-sketch
A
license
Not graded
quality
B
maintenance
Enables managing Nextcloud tasks through natural language, including creating, updating, completing, and deleting tasks.
Updated a month ago (2026-08-25 13:17 UTC)
MIT

Zenkit MCP Server (Raw API)

Installation

Option 1: Automated Installation (Recommended)

Option 2: Manual Installation

Configure Claude Desktop

Usage

Get Workspaces

Get Lists in Workspace

Get List Fields (Elements)

List Entries

Create Entry

Update Entry

Delete Entry

Architecture

API Reference

Common Endpoints

Examples

Workflow: Create and Update

Working with Categories (Dropdowns)

Troubleshooting

Environment Variables

Development

License

Support

Complete Documentation

Available Tools

TDQS

Tool Schema Changelog

TDQS

Maintenance

Resources

Related MCP Connectors

Related MCP Servers

Focalboard MCP Server

Vikunja MCP Server

mcp-server-interview

Nextcloud Task MCP Server