agent-task
AgentTask is a governed work platform where human teams and AI agents share one backlog. Hosted remote MCP server (streamable HTTP, OAuth 2.1 or org API keys) with 60+ tools for tasks, subtasks, projects, groups, labels, notes, comments, attachments, search, crews, and agent runs.
README
Agent Task — Claude plugin marketplace
A standalone, self-contained Claude Code plugin for Agent Task. Installing it wires up the
Agent Task MCP connection and adds intent-level slash commands (/start, /update, /report,
/organize, /init, /finish, /crews) plus the shared workflow skills — including crew
personas (assignable AI teammates) that /crews sync materializes as real Claude Code subagents
with enforced advise-mode tool restrictions.
This bundle is fully independent of the Agent Task product source — it only talks to the hosted MCP server. You never need the product repo to use it.
Install (Claude Code)
From this repo (once pushed to a Git host you can read):
/plugin marketplace add <owner>/<repo> # e.g. your-org/agent-task-plugin
/plugin install agent-task@agent-task
From a local copy (no GitHub needed — hand someone the folder/zip):
/plugin marketplace add /path/to/agent-task-plugin
/plugin install agent-task@agent-task
Restart Claude Code when prompted so the bundled MCP server connects.
Authenticate
The plugin connects to https://app.agent-task.com/v1/public/mcp. Pick one:
- OAuth (per-user, space-scoped) — recommended for interactive use. Remove the
Authorizationheader fromplugins/agent-task/.mcp.jsonand the client runs a browser login + consent flow on connect. - Org API key (org-wide) — export
AGENT_TASK_API_KEY=amk_…before installing.
Full walkthrough: docs/CONNECT_CLAUDE.md. Plugin details:
plugins/agent-task/README.md.
What's inside
.claude-plugin/marketplace.json # marketplace manifest (this repo IS the marketplace)
plugins/agent-task/ # the plugin: .mcp.json, commands/, skills/, manifest
docs/CONNECT_CLAUDE.md # end-user auth + connect guide
Publishing updates
Bump version in both .claude-plugin/marketplace.json and
plugins/agent-task/.claude-plugin/plugin.json, commit, and push. Users get it via
/plugin marketplace update agent-task.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.