Skip to content
Remote MCP · OAuth · 11 tools

Task Management MCP Server: Secure AI Agent Access to Jira, Asana, Monday, Linear, and Notion

Connect Claude, ChatGPT, and Cursor to Jira, Asana, Monday, Linear, and Notion through one remote MCP server. OAuth, per-board controls, and a data firewall on every item read and write.

Connect to Claude

Free tier · No credit card required

What is the Tasks MCP server?

The task management MCP server lets AI agents work with boards, issues, and tasks through the Model Context Protocol. Connect a client like Claude, ChatGPT, or Cursor to one remote endpoint at https://mcp.porteden.com/tasks and the agent works across Jira, Asana, Monday, Linear, and Notion through a single, provider-agnostic tool set.

PortEden's server exposes tools to list providers and boards, read and search items, create and update items, manage comments, and delete items. What makes it different from a generic Jira or Asana MCP is the data firewall in front of those tools: PortEden inspects every tool-call request, applies your access policy, and redacts sensitive content in the response before the agent ever sees it.

The result is secure task management for AI agents. You decide whether a client can only read or can also create and update items, scope it to specific boards, redact sensitive fields, and review every call in an audit log. OAuth handles authentication, so there is no static key to leak.

Tasks MCP tools

Every tool can be allowed or denied per client. Access levels are enforced at the firewall on each call.

These are the 11 tools documented today. PortEden's live Tasks server is expanding, and newer tools will appear here as they are documented.

ToolAccessWhat it does
tasks_list_providersreadList which task providers are connected.
tasks_list_boardsreadList boards or projects from a task provider.
tasks_get_boardreadGet a single board with its groups and column definitions.
tasks_list_itemsreadList items (tasks or issues) on a board.
tasks_get_itemreadGet a single item with all fields and column values.
tasks_search_itemsreadSearch items across all accessible boards.
tasks_list_commentsreadList comments on an item.
tasks_create_itemcreateCreate a new item on a board.
tasks_add_commentcreateAdd a comment or update to an item.
tasks_update_itemwriteUpdate an item's fields.
tasks_delete_itemdeleteDelete an item permanently.

Connect Tasks to Claude, ChatGPT, Cursor, and more

Point any MCP-compatible client at the remote URL and sign in to PortEden once with OAuth.

# Claude Web or Desktop, then Settings, Connectors, Add custom connector
https://mcp.porteden.com/tasks 
 
# Authenticate to PortEden once with OAuth. Claude can now call the
# task tools across every connected provider under your policy.

Available on Claude Pro, Team, and Enterprise. The same flow works for Claude Cowork.

The security-first Tasks MCP

PortEden is the data firewall for AI.

Granular access control

Decide exactly what each AI client can do across your task tools. Keep an agent read-only, allow creating items but never deleting them, or scope a connection to specific boards, so an agent only touches the work it should.

  • Read-only by default: deny tasks_create_item, tasks_update_item, tasks_add_comment, and tasks_delete_item for a reporting agent.
  • Per-board scope: pin a client to one project and block every other board.
  • Create but never delete: allow tasks_create_item while denying tasks_delete_item.
Learn more about granular access control

Data redaction

PortEden runs a redaction pass on every tool response before it leaves the firewall. Sensitive fields in items and comments are replaced with stable placeholders, so the agent can triage and summarize work without the raw content entering the model's context.

  • Strip PII, customer names, and secrets from item descriptions and comments before the agent sees them.
  • Mask assignee email addresses while keeping status and due dates readable.
  • Round-trip updates are de-redacted server-side, so an edit aimed at a placeholder lands on the right item.
Learn more about data redaction

Audit trail

Every task tool call is recorded: which client, which user, which tool, the arguments passed, the policy decision, and the redacted response. Export it or stream it to your SIEM for review.

  • See exactly which boards an agent read and which items it created, updated, or deleted, with timestamps.
  • Reconstruct any tool call: the request, the rule that fired, and the response returned.
  • Stream to Splunk, Datadog, or S3 for retention and review.
Learn more about audit trail

RBAC and policy groups

Bind each MCP connection to a user or role with a scoped, revocable token. Group policies by team so a new hire inherits the right board access on day one, and revocation is instant and server-side.

  • Issue per-user tokens scoped to the verbs, providers, and boards that role needs.
  • Apply one policy group across a team instead of editing rules client by client.
  • Revoke a token server-side the moment a contract ends, with no provider account round-trip.
Learn more about rbac and policy groups

Set up the secure Tasks MCP in minutes

1

Add the connector

In your AI client, add a custom connector or HTTP MCP server pointing at https://mcp.porteden.com/tasks.

2

Authenticate with OAuth

Sign in to PortEden once and connect Jira, Asana, Monday, Linear, or Notion. The client never holds your provider tokens.

3

Set your task policy

Choose read-only or read-write, scope to specific providers and boards, and turn on redaction for sensitive fields.

4

Verify in the audit log

Run a prompt, then watch the tool calls land in your PortEden audit log with the rule that fired on each one.

Works with every MCP client
Claude DesktopClaude WebChatGPTCursorWindsurfClineZed

Tasks MCP FAQ

What is the task management MCP server?
It is a remote MCP (Model Context Protocol) server that lets MCP-compatible AI clients like Claude, ChatGPT, and Cursor work with boards, issues, and tasks through a single hosted endpoint at https://mcp.porteden.com/tasks. One provider-agnostic tool set covers Jira, Asana, Monday, Linear, and Notion, and PortEden puts a data firewall in front of every tool so you control what the AI can see and do.
Which task tools does this MCP server support?
Jira, Asana, Monday.com, Linear, and Notion, through one shared set of tools. The same tasks_list_boards and tasks_create_item calls work across every connected provider, so you do not need a separate MCP per tool. You connect each provider once through PortEden's OAuth flow.
How do I connect Claude to Jira or Asana using MCP?
In Claude Web or Desktop, open Settings, then Connectors, then Add custom connector, and paste https://mcp.porteden.com/tasks. Authenticate to PortEden once with OAuth and connect Jira, Asana, or any supported provider. Claude can then call the task tools. The same URL works in ChatGPT Connectors and in Cursor's MCP settings.
Can I give an AI agent read-only access to my boards?
Yes. Deny tasks_create_item, tasks_update_item, tasks_add_comment, and tasks_delete_item in your policy and the agent keeps the read tools (list providers, list and get boards, list, get, and search items, list comments). You can also allow creating items while denying deletes, or scope the agent to a single board.
Is the task management MCP server secure?
That is the whole point of PortEden. The connection uses OAuth, so there is no static key to leak. Every tool call passes through a policy decision, sensitive fields in items and comments are redacted before the agent sees them, and every call is written to an audit log. You can keep a client read-only and scope it to specific boards.
What task tools does the MCP server expose?
The documented set is eleven tools: tasks_list_providers, tasks_list_boards, tasks_get_board, tasks_list_items, tasks_get_item, tasks_search_items, and tasks_list_comments for reading; tasks_create_item and tasks_add_comment for new content; tasks_update_item for changes; and tasks_delete_item for removal. Each tool can be allowed or denied per client.
Which AI clients work with the task management MCP server?
Any MCP-compatible client. That includes Claude Desktop, Claude Web, ChatGPT (via Connectors), Cursor, Windsurf, Cline, and Zed. Point the client at the remote URL and authenticate once.
Does it cost anything to use the task management MCP server?
There is a free tier that covers 1,000 tool calls per month. Paid plans raise the limit. A tool call is one MCP request, so a search returning 50 items is one call, not 50. See the pricing page for current limits.

Keep Exploring

Connect Tasks to AI, without leaking the underlying data.

Five-minute setup over OAuth. The free tier covers 1,000 tool calls per month.

See pricing