Taskade projects, tasks and AI agents. Hosted OAuth server or local stdio package.
io.github.taskade/mcp-server — Model Context Protocol (MCP) Server
The Taskade MCP server (“Workspace MCP”, @taskade/mcp-server) lets you run a Taskade workspace from an AI client using the Model Context Protocol (MCP). It can be used as a hosted OAuth endpoint at https://www.taskade.com/mcp or locally via @taskade/mcp-server.
🛠️ Key Features
MCP server for Taskade workspaces
Hosted OAuth access at https://www.taskade.com/mcp
Local option: @taskade/mcp-server
Integrates via Model Context Protocol (MCP)
🚀 Use Cases
Connect Taskade to AI assistants such as Claude, Cursor, Windsurf, and VS Code
Enable workflow and workflow automation through AI agents
Use MCP tools to interact with Taskade-driven workflows
⚡ Developer Benefits
Uses MCP and related concepts such as model-context-protocol-server and mcp-tools
Includes topics referencing OpenAPI/OpenAPI code generation (openapi, openapi-codegen, openapi3, genesis)
⚠️ Limitations
Specific tool count and concrete tool/API details are not provided in the available source excerpt.
Set up Taskade for me: https://www.taskade.com/SKILL.md
Taskade is the AI-native workspace for projects, AI agents and automations. Taskade Genesis builds a running app from one prompt.
Connect Taskade to Claude, Claude Code, ChatGPT, Codex, Cursor, VS Code, GitHub Copilot, Gemini CLI, Windsurf and any other client of the Model Context Protocol.
Claude Code:claude mcp add --transport http taskade https://www.taskade.com/mcp
Hosted server:https://www.taskade.com/mcp (Streamable HTTP, OAuth). Nothing to install.
This repo holds the Taskade agent plugin and two packages:
MCP Server (@taskade/mcp-server): the local stdio server, for clients that cannot connect to a remote server.
OpenAPI Codegen: generate MCP tools from any OpenAPI spec, not only Taskade.
Agent plugin for Claude Code, Codex, Copilot, Gemini CLI and Cursor
The taskade plugin connects your AI tool to your Taskade workspace through the hosted server, and adds skills: a front door (taskade) and the job skills (getting-started, import-spreadsheet, fix-my-app, app-report, backup-my-app, plan-new-app). The skills tell the agent which tools to call, in which order, and what to check before it reports back.
Plan: MCP access is part of every paid Taskade plan (Starter and up). Sign in once with your Taskade account.
What it does: imports a spreadsheet into a project, fixes a Taskade Genesis app one checked change at a time, reports on your projects and automations, backs up an app to a folder, and plans a new app.
What stays in Taskade: the plugin cannot build an app, add fields to a project, or create or edit an automation. For those jobs, it writes the request for Taskade EVE. For a new app, it gives you a link that fills in the request and starts nothing. You publish an app and connect a domain in Taskade. For who can use an app, Taskade EVE proposes the setting and you apply it.
Host
Install
Claude Code
claude plugin marketplace add taskade/mcp, then claude plugin install taskade@taskade. Run /mcp, select taskade and sign in.
Codex
codex plugin marketplace add taskade/mcp, then codex plugin add taskade@taskade
npx skills add taskade/mcp installs the skills only. Then add the hosted server https://www.taskade.com/mcp to the agent and sign in (see the quick start).
VS Code: turn on the chat.plugins.enabled setting. Then run Chat: Install Plugin From Source from the Command Palette and enter https://github.com/taskade/mcp.
Cursor: the Cursor plugin taskade (.cursor-plugin/) in this repository adds the same hosted server and skills.
Claude directory: the directory listing reads the plugin from plugins/taskade/, a copy of the root plugin files. The other hosts read the root files.
To add only the hosted server to Codex, run codex mcp add taskade --url https://www.taskade.com/mcp, then codex mcp login taskade.
An initialize request without a token returns 401 on purpose. The 401 tells your client where to start the OAuth sign-in.
Claude (web, Desktop and mobile)
Select Connect in Claude at the top of this page to open Taskade AI in the Claude directory. To add the server as a custom connector instead:
In Claude, go to Customize > Connectors and select Add custom connector. On a Team or Enterprise plan, an Owner first adds the connector in Organization settings > Connectors (Add, then Custom).
Enter the name Taskade and the URL https://www.taskade.com/mcp, then select Add.
Select Connect, sign in to Taskade, and approve access.
In a chat, select + > Connectors and turn on Taskade.
If the dialog asks for an OAuth client, select Register automatically. The connector also works in Claude Desktop and the Claude mobile apps on the same account.
Claude Code
bash
claude mcp add --transport http taskade https://www.taskade.com/mcp
Then run /mcp in Claude Code and select taskade to sign in.
ChatGPT
ChatGPT connects to a remote MCP server as a custom connector in developer mode. It uses OAuth only.
In ChatGPT settings, turn on developer mode for apps and connectors.
Create a connector. Enter Taskade as the name and https://www.taskade.com/mcp as the server URL.
Select OAuth as the authentication. Sign in to Taskade and allow access.
Developer mode is available only on some ChatGPT plans, and its labels change often.
Cursor
Select Add to Cursor at the top of this page, or add this to ~/.cursor/mcp.json:
Every hosted tool declares MCP tool annotations. Claude can run a read-only tool without a confirmation, and it asks before a tool that deletes or replaces data.
get_flow_runs: reads the recent runs of one automation, newest first. Each run has its status and times. A failed run also names the failed step and a short error. It needs edit rights on automations.
run_flow: starts one run of an automation that is On and starts "When asked". Every run is real: it counts toward the monthly automation runs of the plan, and AI steps use credits.
The server also serves the resource taskade://getting-started, a short guide for the model.
Example prompts
Weekly review. "List my Taskade workspaces, read the Q4 Roadmap project, and give me the open tasks grouped by assignee."
Tools: list_spaces, list_projects, read_project.
Plan a launch. "Create a project called Website Launch in my Marketing workspace with tasks for copy, design, QA and launch day, and set the launch task to November 3."
Tools: list_spaces, create_project, create_task, set_task_date.
Build a support agent. "Create an agent called Help Bot in my Support workspace, add the FAQ project as its knowledge, then ask it how a customer resets a password."
Tools: create_agent, add_knowledge_project, prompt_agent.
Close out a sprint. "In the Sprint 42 project, mark every task that mentions 'shipped' as complete, then mark the project as completed."
Tools: list_tasks, complete_task, complete_project.
Edit a Taskade Genesis app. "In my CRM app, read app/src/App.tsx and change the page title to Acme CRM."
Tools: inspect_space, write_file.
Troubleshooting
Symptom
Cause and fix
401 Unauthorized on the first request
Expected. Your client must start the OAuth sign-in. If it does not, update the client or use an API token (see above).
list_spaces returns no workspaces
MCP access needs a paid plan on that workspace. Upgrade at taskade.com/pricing.
A tool returns "permission denied"
Your role in that workspace or project does not allow the action. Ask a workspace owner for access.
Claude shows "Authorization with the MCP server failed"
Remove the connector, add it again, and sign in to the correct Taskade account.
A local npx server fails with "TASKADE_API_KEY appears to be invalid"
Use the local package when your client supports only stdio servers, or when you need a tool that only the local package has, for example the webhook tools (subscribeWebhook, unsubscribeWebhook). It runs on your machine with npx and calls the Taskade public API over the network with a personal access token.
I want to...
Use
Where / auth
Use Taskade from Claude, Cursor, VS Code or another client that supports remote servers
Hosted server
https://www.taskade.com/mcp · OAuth 2.0 or API token · paid plans
Run Taskade tools in a client that supports only stdio, or use the webhook tools
Local package (@taskade/mcp-server)
npx · personal access token · needs network access to taskade.com
Let my Taskade agents reach Slack, Shopify or Gmail
The local package runs over stdio only. It has no HTTP or SSE mode. For a client that connects over HTTP, use the hosted server at https://www.taskade.com/mcp (see Taskade MCP server: quick start).
Local package tools (66)
The local package has its own tool names. They map to the Taskade public API v1 and v2.
Workspaces
Tool
Description
workspacesGet
List all workspaces
workspaceFoldersGet
List folders in a workspace
workspaceCreateProject
Create a project in a workspace
Projects
Tool
Description
projectGet
Get project details
projectCreate
Create a new project
projectCopy
Copy a project to a folder
projectComplete
Mark project as completed
projectRestore
Restore a completed project
projectMembersGet
List project members
projectFieldsGet
Get custom fields for a project
projectShareLinkGet
Get the share link
projectShareLinkEnable
Enable the share link
projectBlocksGet
Get all blocks in a project
projectTasksGet
Get all tasks in a project
listTasks
List tasks in a project, with a filter for open or completed tasks (API v2)
renameProject
Rename a project (API v2)
folderProjectsGet
List projects in a folder
Tasks
Tool
Description
taskGet
Get task details
taskCreate
Create one or more tasks
createTask
Create 1 to 20 tasks (API v2)
taskPut
Update a task
taskDelete
Delete a task
taskComplete
Mark task as complete
taskUncomplete
Mark task as incomplete
taskMove
Move a task within a project
taskAssigneesGet
Get task assignees
taskPutAssignees
Assign users to a task
taskDeleteAssignees
Remove assignees
taskGetDate
Get task due date
taskPutDate
Set task due date
taskDeleteDate
Remove task due date
taskNoteGet
Get task note
taskNotePut
Update task note
taskNoteDelete
Delete task note
taskFieldsValueGet
Get all field values
taskFieldValueGet
Get a specific field value
taskFieldValuePut
Set a text, number or Select field value
setTaskFieldValue
Set a text, number, Select or date field value (API v2)
taskFieldValueDelete
Delete a field value
AI Agents
Create, manage, and publish autonomous AI agents with custom knowledge and tools.
Tool
Description
folderAgentGenerate
Generate an AI agent from a text prompt
folderCreateAgent
Create an agent with custom configuration
folderAgentGet
List agents in a folder
agentGet
Get agent details
agentUpdate
Update agent configuration
deleteAgent
Delete an agent
agentPublicAccessEnable
Publish agent publicly
agentPublicGet
Get public agent details
agentPublicUpdate
Update public agent settings
agentKnowledgeProjectCreate
Add a project as agent knowledge
agentKnowledgeMediaCreate
Add media as agent knowledge
agentKnowledgeProjectRemove
Remove project from knowledge
agentKnowledgeMediaRemove
Remove media from knowledge
agentConvosGet
List agent conversations
agentConvoGet
Get conversation details
publicAgentGet
Get agent by public ID
Templates
Tool
Description
folderProjectTemplatesGet
List available project templates
projectFromTemplate
Create a project from a template
Media
Tool
Description
mediasGet
List media files in a folder
mediaGet
Get media details
mediaDelete
Delete a media file
Personal
Tool
Description
meProjectsGet
List all your projects
Agent Chat & Webhooks (API v2, beta)
Capabilities the v1 API doesn't have: hold a live conversation with an AI agent, and receive real-time events.
Tool
Description
promptAgent
Send a message to an AI agent and get its reply
listConversations
List an agent's conversations
getConversation
Get a conversation's messages
subscribeWebhook
Subscribe to real-time Taskade event webhooks
unsubscribeWebhook
Remove a webhook subscription
Why Taskade MCP?
Taskade MCP gives your AI assistant access to your workspace — projects, tasks, agents, knowledge bases, templates, and automations (on paid plans; some endpoints such as workspace listing are gated for free accounts). Instead of writing API code, describe what you need in natural language.
code
┌──────────────────────────────────────────────────────────┐
│ HOW TASKADE MCP WORKS │
└──────────────────────────────────────────────────────────┘
You (in Claude/Cursor/Windsurf):
"Create a support agent trained on our docs project"
↓
┌──────────────────────────────────┐
│ Taskade MCP Server │
│ (66 tools, 8 categories) │
└──────────────────────────────────┘
↓ ↓ ↓
folderCreateAgent agentKnowledge agentPublicAccess
(creates agent) (attaches docs) (publishes it)
↓
Result: Live AI chatbot trained on your data
What You Say
What Happens
"Show me all overdue tasks"
Reads projects → filters tasks → formats report
"Create a support agent trained on our docs"
Creates agent → attaches knowledge → publishes
"Set up next week's sprint from our template"
Copies template → populates tasks → assigns team
"Summarize the completed work in my Sprint project"
Reads completed tasks → generates a standup summary
Why MCP Instead of REST API?
REST API
MCP Server
Setup
Write HTTP client, handle auth, parse JSON
npx @taskade/mcp-server — one command
Interface
Code against endpoints
Natural language — describe what you need
Chaining
Manual orchestration
AI chains tools intelligently
Error handling
Write error handling code
AI interprets errors and retries
Why Taskade MCP Over Other MCP Servers?
Taskade MCP includes AI agent management (create, train, deploy agents), knowledge base training (attach docs, projects, media), and OpenAPI codegen (generate MCP tools from any API spec). 66 tools across 8 categories.
Agent Recipes
Recipe 1: Daily Standup Summarizer
Problem: Team standup notes scattered across Slack, email, and docs.
code
You: "Check my Taskade workspace for yesterday's completed tasks,
summarize them as a standup update, then create today's
priority tasks based on what's still open."
Claude uses:
1. meProjectsGet → find your active projects
2. projectTasksGet → pull tasks from each project
3. taskCreate → create today's priority tasks
Result: A formatted standup summary + fresh task list in Taskade.
Recipe 2: Knowledge Base Agent Builder
Problem: You have docs scattered across files and need an AI agent trained on them.
code
You: "Create an AI support agent called 'Help Bot' in my
Customer Success folder, train it on our Documentation
project, and publish it publicly."
Claude uses:
1. workspaceFoldersGet → find "Customer Success" folder
2. folderCreateAgent → create "Help Bot" with support instructions
3. agentKnowledgeProjectCreate → attach Documentation project
4. agentPublicAccessEnable → publish with shareable link
Result: Live AI chatbot trained on your docs, ready to embed.
Recipe 3: Sprint Planning Automation
Problem: Creating sprint projects manually every two weeks.
code
You: "Create a new sprint project from our 'Sprint Template',
name it 'Sprint 2026-W15', move the top 10 backlog
items into it, and assign them to the engineering team."
Claude uses:
1. folderProjectTemplatesGet → find "Sprint Template"
2. projectFromTemplate → create "Sprint 2026-W15"
3. projectTasksGet → get backlog items
4. taskMove → move top 10 tasks to new sprint
5. taskPutAssignees → assign engineering team members
Result: Sprint ready to go, fully populated and assigned.
Recipe 4: Competitive Intelligence Agent
Problem: You need an agent that monitors competitors and reports findings.
code
You: "Generate an AI agent that researches our top 5 competitors.
Train it on our Competitive Analysis project.
Name it 'Market Intel Agent'."
Claude uses:
1. folderAgentGenerate → generate agent from research prompt
2. agentKnowledgeProjectCreate → connect Competitive Analysis project
3. agentUpdate → refine instructions for research cadence
Result: AI research agent with domain knowledge, ready for briefings.
Recipe 5: Client Onboarding Pipeline
Problem: Each new client needs the same project structure, tasks, and materials.
code
You: "For our new client Acme Corp: create a project from
the 'Client Onboarding' template, add tasks for
kickoff meeting and SOW review, set due dates for
the next 2 weeks, then share the project link."
Claude uses:
1. projectFromTemplate → create "Acme Corp Onboarding"
2. taskCreate → add kickoff, requirements, SOW tasks
3. taskPutDate → set dates across next 2 weeks
4. projectShareLinkEnable → generate share link
Result: Client onboarding project live and shareable in 30 seconds.
Use Cases
Project Management with AI
Ask your AI assistant to manage your Taskade workspace:
"Show me all my projects and their status"
"Create a new project called Q1 Planning with tasks for each team"
"Move all overdue tasks to the Backlog project"
"Set due dates for all tasks in the Sprint project"
AI Agent Creation
Build and deploy AI agents directly from your editor:
"Create an AI agent called Customer Support Bot with knowledge from our docs project"
"Generate an agent for code review using this prompt: ..."
"Publish my agent publicly and give me the share link"
"Add our API documentation project as knowledge to the agent"
Template Workflows
Automate project creation from templates:
"List all templates in my workspace"
"Create 5 new client onboarding projects from the Client Template"
"Copy the Sprint Retrospective project for this week"
OpenAPI Codegen
Use our generator to build MCP tools from any OpenAPI spec — not just Taskade.
Works with any OpenAPI 3.0+ spec. Generate MCP tools for your own APIs in minutes.
What is Taskade?
Taskade (Y Combinator S19) is the AI-native workspace for building apps, deploying agents, and automating workflows from a single prompt. 150,000+ apps built.
Genesis Apps — Build complete apps from prompts. Dashboards, CRMs, portals, forms — deployed instantly. Try it →
AI Agents — Custom agents with built-in tools, persistent memory, multi-agent teams, public embedding
See open issues for planned features and improvements.
Recently shipped (v0.1.0): Agent chat (promptAgent) and webhook triggers, live now via the Taskade API v2 tool layer.
Automation tools: the hosted server lists automations, reads their runs and runs an automation that is On and starts "When asked" (list_automations, get_flow_runs, run_flow). Create, enable and manage automations through MCP are on the roadmap.
Hosted server. Taskade runs it on www.taskade.com. It reads and writes only the workspaces that your Taskade account can access and that are on a paid plan. The server does not read your chat history with the AI client. prompt_agent runs a Taskade agent, which can use its own tools, for example web search.
Agent plugin. The plugin holds skills (text files) and the address of the hosted server. It runs no code of its own. The backup skill writes workspace files to a local folder (./taskade-backup/ unless you name another one).
Local package. Your API token authorizes the server to call the Taskade public API (https://www.taskade.com/api/v1 and https://www.taskade.com/api/v2) on your behalf. The package sends your data to no other service. Keep the token in an environment variable, and never commit it.