How do I install Taskpilot?

Taskpilot is a local plugin. Install it using npm package: @reneturcios/taskpilot and add the generated configuration snippet to your AI app's MCP config file. Then restart your AI app.

Is Taskpilot safe to use?

Taskpilot scored 5.6/10 (moderate risk) in MCP Marketplace's automated security scan. It has 2 high or critical findings to review. It's listed, but review the security report on this page before installing.

What credentials does Taskpilot need?

Taskpilot requires the following credentials or environment variables: CODERIDE_API_KEY. You can find setup instructions on the server detail page.

What AI apps work with Taskpilot?

Taskpilot uses the Model Context Protocol (MCP) and works with any MCP-compatible AI app, including Claude, ChatGPT / Codex, Gemini, Copilot, Cursor, and more.

Back to Browse

Taskpilot MCP Server

by CloudCorpRecords

Developer ToolsModerate5.6MCP RegistryLocal

Free

Server data from the Official MCP Registry

Task and project management for AI coding agents: tasks, prompts, projects, next task.

About

Task and project management for AI coding agents: tasks, prompts, projects, next task.

Security Report

5.6

Moderate5.6Moderate Risk

taskpilot is a straightforward task and project management MCP server that calls a single configured API base URL with a Bearer key read from CODERIDE_API_KEY, and it fails closed when the key is missing. The code uses zod validation, encodes path parameters, and has no shell execution, eval, filesystem access, or hardcoded secrets. Remaining notes are minor: the base URL is overridable via env, and the dependencies are standard and expected, so the score stays in the good range. Supply chain analysis found 4 known vulnerabilities in dependencies (0 critical, 2 high severity). Package verification found 1 issue.

8 files analyzed · 7 issues found

Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.

Permissions Required

This plugin requests these system permissions. Most are normal for its category.

HTTP Network Access

Connects to external APIs or services over the internet.

env_vars

Check that this permission is expected for this type of plugin.

What You'll Need

Set these up before or after installing:

CODERIDE_API_KEYRequired

How to Install

Add this to your MCP configuration file:

{
  "mcpServers": {
    "io-github-cloudcorprecords-taskpilot": {
      "env": {
        "CODERIDE_API_KEY": "your-coderide-api-key-here"
      },
      "args": [
        "-y",
        "@reneturcios/taskpilot"
      ],
      "command": "npx"
    }
  }
}

Documentation

View on GitHub

From the project's GitHub README.

taskpilot

taskpilot gives AI coding agents a handle on their task board and their projects: fetch a task by its number, move it between statuses, pull the prompt that belongs to it, look projects up by slug or name, refresh a project's stored knowledge and diagram, start a project, list what is on the board, and ask which task comes next. One binary serves a command-line interface and a stdio MCP server.

An API key is required. Set CODERIDE_API_KEY before use; when it is missing or blank, every tool fails with an error before any request is made. The API base URL can be overridden with TASKPILOT_API_URL; when it is not set, calls go to https://api.coderide.ai.

Task numbers are the short human codes shown on the board, for example TCA-3. A task's status is one of to-do, in-progress, or done.

Install

npx @reneturcios/taskpilot list_projects

Or run the container image:

docker run -i ghcr.io/cloudcorprecords/taskpilot

The container defaults to the MCP server (see below). Pass CLI arguments to use it as a CLI instead.

CLI

The subcommands mirror the MCP tool names:

export CODERIDE_API_KEY=...

taskpilot get_task --number TCA-3
taskpilot get_task --number TCA-3 --status in-progress
taskpilot update_task --number TCA-3 --status done
taskpilot update_task --number TCA-3 --description "Revised scope notes"
taskpilot get_prompt --number TCA-3
taskpilot get_project --slug my-app
taskpilot get_project --name "My App"
taskpilot update_project --slug my-app --project-diagram "Web -> API -> DB"
taskpilot update_project --slug my-app --project-knowledge '{"stack":"typescript"}'
taskpilot start_project --slug my-app
taskpilot list_projects
taskpilot list_tasks --slug my-app
taskpilot next_task --number TCA-3

taskpilot --version

Results print the upstream JSON payload. Exit codes: 0 on success, 1 when a call fails (including a missing API key or an upstream API error), 2 for usage errors.

MCP server

One bin serves both faces. The mcp subcommand starts a stdio MCP server:

npx -y @reneturcios/taskpilot mcp

MCP client configuration:

{
  "mcpServers": {
    "taskpilot": {
      "command": "npx",
      "args": ["-y", "@reneturcios/taskpilot", "mcp"],
      "env": { "CODERIDE_API_KEY": "..." }
    }
  }
}

Tools

Tool	Input	What it does
`get_task`	`number` (required), `status`	Get a task by its number, optionally filtered by status.
`update_task`	`number` (required), `description`, `status`	Update a task's description and/or status.
`get_prompt`	`number` (required)	Get the prompt belonging to a task.
`get_project`	`slug`, `name`	Get a project by slug or by name.
`update_project`	`slug` (required), `project_knowledge`, `project_diagram`	Update a project's knowledge and/or diagram.
`start_project`	`slug` (required)	Start a project.
`list_projects`	(none)	List projects in the workspace.
`list_tasks`	`slug` (required)	List a project's tasks.
`next_task`	`number` (required)	Get the task that follows the given one.

status is one of to-do, in-progress, done. project_knowledge is a JSON object.

Development

npm install
npm run build   # tsc -> dist/
npm test        # node test runner over test/*.test.ts, no network (fake fetch fixtures)
npm run dev     # run the CLI from source via tsx

License

MIT — see LICENSE.

Reviews

No reviews yet

Be the first to review this server!

4.8

Local

MCP Marketplace

Free

by mcp-marketplace · Developer Tools

Search and install MCP servers from inside your AI client.