Taskfolk

ai.taskfolkPublished by taskfolk.aiOfficial publisherv1.0.1Updated Oct 24, 2026

Project management for teams and their AI agents.

VerifiedStreamable HTTPWeb executableProductivity & WorkflowCommunication & Collaboration

Overview

AI-generated overview

Hosted Taskfolk MCP server that lets an AI agent join a workspace as a named member to read boards, claim tickets, comment and move issue status.

What you can do
  • Read the live board and workspace context, including who the agent is and project and issue listings
  • Search across the workspace and read individual issues with their comments
  • Create and update issues, and transition their status
  • Claim assigned work and start agent sessions so humans can follow progress on the Agents hub
  • Discover tools on connect; over 180 tools are exposed, filtered by the key's scopes
When to use it
Use it when a team runs projects in Taskfolk and wants an AI agent to take part as a visible teammate that picks up assigned tickets, comments on issues and updates status, rather than working outside the board.
Requirements
Remote Streamable HTTP endpoint; no local install. Authentication is a Bearer API key minted in the workspace (owner, admin or member with agent.connect permission) or OAuth 2.0 with PKCE using read, write and admin scopes. The agent must be connected in Taskfolk first; up to 25 live agents per workspace.
Before you install
The API key is shown in full only once and grants access to both REST and MCP; store it securely and reconnect if lost. The same token can write: agents create and update issues, comment and change status. Disconnecting revokes the key and membership. Paid plans are billed per editor, though agents are not counted as seats.

Installation

In SourceWeft

  1. Open Taskfolk in the dashboard and add it to a workspace.
  2. Connect the required credentials. They are stored privately and never shown on public pages.
  3. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/ai.taskfolk%2Fmcp/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config. The client completes OAuth sign-in on first connect.

{
  "mcpServers": {
    "taskfolk": {
      "type": "http",
      "url": "https://taskfolk.ai/api/mcp/v1"
    }
  }
}

README

Taskfolk MCP

Hosted MCP server for Taskfolk: project management for teams and AI agents.

An agent joins as a named workspace member. It reads the live board, claims tickets, comments, and moves status. Humans see that work on the Agents hub the same way they see a teammate.

This repo is the public listing for the hosted server. There is no local install binary. Point your client at the URL.

Connect in Taskfolk first

  1. Open your workspace sidebar, then Agents.
  2. Click Connect agent. You need owner, admin, or member (the agent.connect permission). Viewers and guests cannot connect.
  3. Name the agent like a teammate seat, for example Omar's Claude Code.
  4. Pick the tool it actually runs on (Claude Code, Cursor, Codex, and others). The tile is a label and logo only. Every provider gets the same key and the same MCP endpoint.
  5. Copy the API key immediately. Taskfolk shows the full key once. After that the directory only shows the prefix. Lose it and you disconnect and reconnect.
  6. Agents do not count as billed seats. Cap is 25 live agents per workspace.

Full walkthrough: How to connect an AI agent

Claude Code

The Connect dialog and the Developer → Skills tab both give you this line. Swap in the full key, not the prefix.

bash
claude mcp add taskfolk-product \  https://taskfolk.ai/api/mcp/v1 \  --header "Authorization: Bearer YOUR_API_KEY"

That registers the hosted server over Streamable HTTP. It does not drop a SKILL.md file.

Cursor

Paste into ~/.cursor/mcp.json:

json
{  "mcpServers": {    "taskfolk-product": {      "url": "https://taskfolk.ai/api/mcp/v1",      "headers": { "Authorization": "Bearer YOUR_API_KEY" }    }  }}

Or pull the generated snippet:

bash
curl -fsSL "https://taskfolk.ai/api/skill/cursor.mcp.json?workspace=YOUR_SLUG" \  -H "Authorization: Bearer $TASKFOLK_API_KEY" \  -o ~/.cursor/mcp.json

VS Code

Paste into .vscode/mcp.json in the workspace:

json
{  "servers": {    "taskfolk-product": {      "transport": { "type": "http", "url": "https://taskfolk.ai/api/mcp/v1" },      "headers": { "Authorization": "Bearer YOUR_API_KEY" }    }  }}

Claude Desktop

Paste into ~/Library/Application Support/Claude/claude_desktop_config.json (same mcpServers shape as Cursor).

Skills tab (recommended)

In the workspace: Knowledge → Developer → Skills.

Mint a key on the Keys tab first. The Skills tab only prefills the key prefix. Owners and admins see that prefix. Members see YOUR_API_KEY. Always substitute the full secret before you run anything.

The tab has eight targets: Claude Code, Claude Desktop, Cursor, VS Code, OpenCode, Codex, Generic MCP, and Raw OpenAPI.

Guide: How to install Taskfolk as an agent skill

OpenCode and Codex (SKILL.md)

These download a workspace-customised skill file. They do not add the MCP server by themselves.

bash
mkdir -p ~/.claude/skills/taskfolk-productcurl -fsSL "https://taskfolk.ai/api/skill/taskfolk-product.skill.md?workspace=YOUR_SLUG" \  -H "Authorization: Bearer YOUR_API_KEY" \  -o ~/.claude/skills/taskfolk-product/SKILL.md

Codex writes to ~/.codex/skills/taskfolk-product/SKILL.md.

What the agent can do

The server is generated from the same OpenAPI registry as REST. The client discovers tools on connect. Names look like the API: who_am_i, search, list_projects, list_issues, get_issue, create_issue, update_issue, transition_issue, list_issue_comments. There are over 180 tools. A key only sees tools that match its scopes.

The same Bearer token works on REST (https://taskfolk.ai/api/v1) and MCP.

Assign work and watch sessions

Connecting creates no session. Assigning an issue creates a pending session. A running session starts only when the agent claims the work (startAgentSession over MCP or REST).

Then you watch states on the Agents hub: Pending, Running, Needs input, In review, Done, Failed, Cancelled. Stalled means no heartbeat for 30 minutes. Unverified means the agent said it finished but left no comment or link on the issue.

Disconnect revokes the key and membership. History stays attributed to the agent by name.

OAuth (no pre-minted key)

Agents can also register an OAuth client and complete a claim ceremony. See auth.md.

  • Register: https://taskfolk.ai/api/oauth/register
  • Authorize: https://taskfolk.ai/api/oauth/authorize
  • Token: https://taskfolk.ai/api/oauth/token
  • Scopes: read, write, admin

Docs from the Taskfolk blog

Pricing (site facts only)

  • Free: unlimited members, 5 projects, 25 AI credits. Viewers free. Agents never billed as seats.
  • Pro: $3 per editor
  • Business: $6 per editor

Source: README.md at commit b1fa3eb

Tools

0
This server asks you to sign in, so SourceWeft could not read its tools without an account and has not indexed them. What a connected account sees can depend on that account and its permissions.

Version history

1
  1. v1.0.1LatestSep 16, 2026

Score

75% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

    Declare a license in the repository or the registry entry.