Live 47 Actions

Wrike MCP Server
for AI Agents

Q: What AI frameworks and AI clients does the StackOne Wrike MCP server support?

The StackOne Wrike MCP server supports both. MCP clients (paste-and-go apps): Claude Desktop, Claude Code, Cursor, VS Code, Goose. Agent frameworks (code SDKs you build with): OpenAI Agents SDK, Anthropic, Vercel AI, Google ADK, CrewAI, Pydantic AI, LangChain, LangGraph, Azure AI Foundry.

Connect your AI agent to StackOne's Wrike MCP server and give it 47 MCP tools out of the box. Auth, tool execution, and security all managed.

Start Free Book Demo Read Docs →

Wrike MCP Server

Built by

StackOne

Coverage

47 Agent Actions

Create, read, update, and delete across Wrike — and extend your agent's capabilities with custom actions.

MCP Actions → Build Actions →

Authentication

Agent Tool Authentication

Per-user OAuth in one call. Your Wrike MCP server gets session-scoped tokens with zero credentials stored on your infra.

Agent Auth →

Security

Agent Protection

Every Wrike tool response scanned for prompt injection in milliseconds — 88.7% accuracy, all running on CPU.

Prompt Injection Defense →

Performance

Max Agent Context. Min Cost.

Free up to 96% of your agent's context window to enhance reasoning and reduce cost, on every Wrike call.

Tools Discovery →

What is the Wrike MCP Server?

A Wrike MCP server lets AI agents read and write Wrike data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Wrike MCP server ships with 47 pre-built actions, fully extensible via the Connector Builder — plus managed authentication, prompt injection defense, observability, and agent execution runtime. Connect it from MCP clients like Claude Desktop, Claude Code, Cursor, Goose, and VS Code, or from agent frameworks like OpenAI Agents SDK, LangChain, and Vercel AI SDK.

All Wrike MCP Tools

Every action from Wrike's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.

Comments

List Comments
Get all comments in current account
Get Comments
Get single or multiple comments by their IDs (up to 100)
Update Comment
Update a comment by ID (within 5 minutes of creation)
Delete Comment
Delete a comment by ID

Folder Comments

Create Folder Comment
Create a comment in a folder
List Folder Comments
Get comments for a specific folder

Task Comments

Create Task Comment
Create a comment in a task
List Task Comments
Get comments for a specific task

Contacts

List Contacts
List contacts of all users and user groups in current account
Get Contact
Get contact information for specified users and user groups by IDs

Custom Fields

Create Custom Field
Create a custom field in the account
List Custom Fields
Get all custom fields in current account
Get Custom Fields
Get custom fields by IDs (up to 100)

Folders

Create Folder
Create a folder within a folder
Copy Folder
Copy folder subtree and return parent folder subtree
Get Folder
Returns complete information about specified folders
Update Folder
Update folder properties including title, description, sharing, and project settings
Delete Folder
Move folder and descendants to Recycle Bin

Groups

Create Group
Create a new group in the account
Query Groups
Get all groups in the account
Get Group
Get complete information about a single group

Spaces

Create Space
Create a space in the account
Get Spaces
Returns a list of spaces in the account
Update Space
Update a space configuration
Delete Space
Delete a space by ID

Tasks

Create Task
Create a task in a folder
List Tasks
Search among all tasks in current account
Get Tasks
Retrieve multiple tasks by IDs (up to 100)
Delete Task
Delete a task by ID

Workflows

Create Workflow
Create a new workflow in account
Query Workflows
Returns list of workflows with custom statuses

Other (16)

List Access Roles
Retrieves a list of all access roles in the account
Query Accounts
Retrieves information about all accounts accessible to the user
Get Contact History
Query contact fields history for specified users by IDs
List Space Custom Fields
Get custom fields for a specific space
Get Folder Tree
Retrieves folders for the current account in tree or filtered mode
Get Folder History
Query folders fields history for finance-related changes
Get Space By ID
Returns information about a specific space by ID
List Folder Tasks
Search among tasks in a specific folder
List Space Tasks
Search among tasks in a specific space
Get Tasks History
Query task field change history for multiple tasks (up to 100)
List Space Workflows
Returns list of workflows for a specific space
Modify Account
Modify metadata for the current account
Modify Contact
Modify contact information for the requesting user by ID
Modify Custom Field
Modify an existing custom field
Modify Group
Modify an existing group by ID
Modify Workflow
Modify workflow or custom statuses

Set Up Your Wrike MCP Server in Minutes

One endpoint. Any framework. Your agent is talking to Wrike in under 10 lines of code.

MCP Clients

Agent Frameworks

Claude Desktop-

JSON

Claude Desktop Docs

{
  "mcpServers": {
    "stackone": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote@latest",
        "https://api.stackone.com/mcp?x-account-id=<account_id>",
        "--header",
        "Authorization: Basic <YOUR_BASE64_TOKEN>"
      ]
    }
  }
}

Check More Project Management MCP Servers

Smartsheet

189+ actions

Azure DevOps

185+ actions

Jira

147+ actions

136+ actions

136+ actions

134+ actions

133+ actions

All Project Management MCP Servers →

Platform Resources

MCP Code Mode: Keeping Tool Responses Out of Agent Context

Anthropic's code_execution processes data already in context. Custom MCP code mode keeps raw tool responses in a sandbox. 14K tokens vs 500.

11 min

Comparing BM25, TF-IDF, and Hybrid Search for MCP Tool Discovery

Benchmarking BM25, TF-IDF, and hybrid search for MCP tool discovery across 916 tools. The 80/20 TF-IDF/BM25 hybrid hits 21% Top-1 accuracy in under 1ms.

10 min

Indirect Prompt Injection Defense for MCP Tools: A Technical Guide

MCP tools that read emails, CRM records, and tickets are indirect prompt injection vectors. Here's how we built a two-tier defense that scans tool results in ~11ms.

12 min

MCP vs A2A: Architecture, Security, and When to Use Each

MCP vs A2A: what each protocol standardizes, how they differ, their shared security risks including indirect prompt injection, and when to use one, both, or a hybrid architecture.

12 min

MCP vs API: What 200+ Connector Builds Taught Us

MCP wraps APIs, it doesn't replace them. After building 200+ connectors that serve both, here's when each approach wins.

14 min read

Wrike MCP Server FAQ

Does StackOne have a Wrike MCP server?

Yes. StackOne offers a hosted Wrike MCP server with 47 pre-built actions, and every action is tested and QA'd by StackOne. Connect it to Claude, Cursor, and any other MCP client, or to any agent framework through the AI Action SDK. It ships with managed agent authentication, prompt injection defense, and tool discovery with server-side execution that preserve your agent's context window and keep reasoning performance.

Wrike MCP server vs direct API integration — what's the difference?

A Wrike MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Wrike. A Wrike MCP server is for AI agents — MCP clients like Claude and Cursor, plus framework agents built with OpenAI, LangChain, or Vercel AI — discovering and calling Wrike at runtime. StackOne provides both.

How does Wrike authentication work for AI agents?

Wrike authentication for AI agents works through a StackOne Connect Session. Create one via the dashboard or the SDK — you get an auth link and ready-to-paste config for Claude Desktop, Cursor, and other MCP clients. Your user authenticates their own Wrike account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via origin_owner_id.

Are Wrike MCP tools vulnerable to prompt injection?

Yes — Wrike MCP tools can be vulnerable to indirect prompt injection. Any tool that reads user-written content — documents, messages, tickets, records, or free-text fields — is a potential vector. StackOne Defender scans every tool response before it enters the agent's context — regex patterns in ~1ms, then a MiniLM classifier in ~4ms. 88.7% accuracy, CPU-only.

What is the context bloat of a Wrike agent and how do I avoid it?

Context bloat happens when Wrike tool schemas and API responses eat your Wrike agent's memory, preventing it from reasoning effectively. A single Wrike query can return a massive JSON response, and connecting multiple tools compounds the problem. Tools Discovery and Code Mode reduce context bloat — loading only relevant tools per query and keeping raw responses out of the agent's context.

Can I limit which actions my Wrike agent can access?

Yes — you can limit which actions your Wrike agent can access directly from the StackOne dashboard. Toggle actions on or off, or restrict them to specific accounts, with no code changes to your agent. Session tokens can be scoped to exact actions so if one leaks, exposure stays contained.

Can I create custom agent actions for my Wrike MCP server?

Yes — you can create custom agent actions for your Wrike MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Wrike's API, generate production-ready connector YAML, test against the live API, and validate before you ship.

When should I NOT use a Wrike MCP server?

Skip a Wrike MCP server if your integration is purely software-to-software — direct Wrike API integration is simpler when no AI agent is involved. For deterministic, compliance-critical operations (financial transactions, regulatory reporting), direct API gives you predictable behavior without agent-driven decision-making. MCP shines when AI agents need to dynamically discover and call Wrike actions at runtime.

What AI frameworks and AI clients does the StackOne Wrike MCP server support?

The StackOne Wrike MCP server supports both. MCP clients (paste-and-go apps): Claude Desktop, Claude Code, Cursor, VS Code, Goose. Agent frameworks (code SDKs you build with): OpenAI Agents SDK, Anthropic, Vercel AI, Google ADK, CrewAI, Pydantic AI, LangChain, LangGraph, Azure AI Foundry.

Put your AI agents to work

All the tools you need to build and scale AI agent integrations, with best-in-class connectivity, execution, and security.

Start Free Book Demo

Wrike MCP Serverfor AI Agents