Definition: Taskade as MCP Server is the side of the Model Context Protocol implementation where Taskade exposes its workspace — projects, tasks, documents, agents, automations — as a set of MCP tools that any external AI client can call. Connect Claude Desktop, Cursor, VS Code, or any custom MCP-capable agent to https://www.taskade.com/mcp, sign in once via OAuth2 + PKCE, and the external agent can now list your spaces, browse a space's projects, agents, and automations, and edit your Genesis app source — all through a single standardized interface.
This is the direction Taskade offers. The mirror direction — an MCP client that calls out to tools hosted on someone else's server — is part of the same protocol, but Taskade agents do not call out to external MCP servers on any plan. To reach other systems from inside Taskade, the working paths are the 100+ integrations and the 34 built-in tools available to AI agents.
Why This Exists
Every AI tool wants to be your primary interface. Most fail because they cannot see the work you actually do. The Model Context Protocol — Anthropic's open standard, donated to the Linux Foundation in late 2025 — fixes this by giving every AI client a uniform way to reach every tool and workspace.
For Taskade users, MCP Server means your Taskade workspace is no longer trapped behind Taskade's UI. Open Claude Desktop, ask "What's on my Q2 roadmap in Taskade?", and Claude reaches into your actual workspace to answer. Open Cursor, point it at a Taskade Genesis app, and let it read the project and edit the app's source files. The workspace travels with you to whichever AI client you prefer.
Architecture
The external client speaks MCP over HTTP with Server-Sent Events. Authentication uses OAuth2 with PKCE — the modern, browser-based, proof-of-authenticity pattern Taskade uses across its web app. Once signed in, the client sees Taskade's tool catalog and can invoke tools over the same connection.
The Tool Catalog
Taskade's hosted MCP Server currently exposes exactly three tools, each backed by the same Virtual File System (VFS) that Taskade EVE uses internally when building Taskade Genesis apps:
| Tool | What It Does | Typical Use |
|---|---|---|
list_spaces |
Enumerate the workspaces the authenticated user can access (read-only) | "Show me all my Taskade spaces" |
inspect_space |
Browse a space as a virtual filesystem — projects, agents, automations, media (read-only) | "What's in my Q2 roadmap?" |
write_file |
Create or update files in the Genesis app source (the app/ directory) |
"Write a README for this app" |
Reading across the workspace is handled by inspect_space, which exposes projects, agents, and automations as a browsable, read-only virtual filesystem. The only write surface is write_file, and it is scoped to a Genesis app's source — the app/ directory — not arbitrary projects or tasks. Because the backing store is the same VFS as Taskade EVE's, source edits made by an external client trigger the same update events that Taskade's own agents respond to. Consistency is automatic.
If you need the full read-write surface over projects, tasks, agents, and automations, that lives in the separate local @taskade/mcp-server package, which wraps the Taskade v1 API and exposes 50+ tools. The hosted server at https://www.taskade.com/mcp is intentionally the smaller, OAuth-gated three-tool surface described here.
What This Enables
Claude Desktop as a Taskade cockpit. Pin Taskade's MCP connection in Claude Desktop and use Claude's reasoning across your full workspace without switching apps.
Cursor editing Taskade Genesis app source. Let Cursor read a Taskade Genesis app via inspect_space, propose source edits, and apply them with write_file — the same developer loop as editing a local codebase.
VS Code as a hybrid IDE. Run VS Code against both your code and your Taskade docs. One agent sees both.
Custom agents for enterprise. Build a custom MCP client that queries both your internal databases and your Taskade projects in a single agent turn. Compliance-friendly, audit-logged, and federated.
Plan Access
The hosted MCP Server is in Beta and available on every paid plan (Starter and up). If you do not see MCP in your Taskade settings, check pricing for the current paid tiers.
Security Considerations
Taskade's MCP Server uses:
- OAuth2 + PKCE — the external client never sees your password, and connects with a Bearer token carrying the
mcpscope (Personal Access Tokens are rejected on the hosted server) - Per-session tokens — revocable from your Taskade settings
- Scope enforcement — the client can only browse spaces, projects, agents, and automations your account has access to, and the only write surface is your Genesis app source
- Audit log — every MCP-initiated source edit lands in your workspace activity feed
If you want to revoke access, open your Taskade settings and disconnect the MCP session. The external client immediately loses its connection.
MCP Server vs MCP Client
MCP defines two roles, and every connection pairs one of each. A server publishes a tool catalog and waits to be called. A client discovers those tools and invokes them mid-turn.
Taskade fills the server role. Claude Desktop, Cursor, and VS Code are the clients: they sign in over OAuth2 + PKCE, read Taskade's catalog, and call list_spaces, inspect_space, and write_file against your workspace. Direction of travel is external → Taskade, the external client holds the tokens, and the tools on offer are Taskade's. That side is live on every paid plan.
The client role — a Taskade agent discovering tools on someone else's MCP server and calling them during a task — is not available on any plan. Nothing in Taskade connects out to third-party MCP servers today. To reach other systems from inside Taskade, use the 100+ integrations or the 34 built-in tools every AI agent already carries.
Related Concepts
- Model Context Protocol — The underlying standard
- Taskade as MCP Client — The client role, which Taskade does not offer
- Tool Use — What MCP enables at the behavior level
- Function Calling — The wire format underneath
- Agentic AI — Why MCP matters
- Taskade EVE — Uses the same VFS the MCP tools expose
- Taskade Genesis Apps — What gets built on top
Frequently Asked Questions About Taskade as MCP Server
What is Taskade as MCP Server?
Taskade as MCP Server exposes your Taskade workspace — projects, tasks, documents, agents — as tools that any Model Context Protocol-compatible AI client (Claude Desktop, Cursor, VS Code) can call. Sign in once via OAuth2, and external agents can browse your workspace read-only and edit your Genesis app source.
How do I connect Claude Desktop to Taskade?
Open Claude Desktop, go to integrations or MCP settings, add Taskade's MCP endpoint (https://www.taskade.com/mcp), and complete the OAuth2 + PKCE sign-in flow. Claude Desktop will then list Taskade tools in its tool catalog and can call them during conversations.
What tools does Taskade MCP expose?
The hosted server exposes exactly three tools: list_spaces (enumerate the workspaces you can access, read-only), inspect_space (browse a space's projects, agents, automations, and media as a read-only virtual filesystem), and write_file (create or update files in a Genesis app's source app/ directory). For full read-write access to projects and tasks, use the separate local @taskade/mcp-server package, which wraps the v1 API with 50+ tools.
Is MCP available on every Taskade plan?
MCP Server is available on every paid plan (Starter and up). Check your plan on pricing for current eligibility.
How secure is Taskade MCP Server?
Authentication uses OAuth2 with PKCE — no password sharing, a Bearer token scoped to mcp (Personal Access Tokens are rejected), revocable per-session tokens, scope-enforced read-only browsing of your accessible workspaces with writes limited to your Genesis app source, and full audit logs for every MCP-initiated source edit.