Business operationsPublic source

Task MCP Server

A task & work-management platform for ADK-Rust Enterprise operations agents. 20 MCP tools covering task lists, tasks with a status workflow, priority and due dates, assignment, dependencies (with cycle + blocker…

Open the source Read the official guide ↗

What it gives an agent

A purpose-built capability behind one MCP connection.

The server owns its domain logic and publishes a tool contract an MCP client can discover. ADK-Rust can load that contract into an agent, normalize each schema for the chosen model provider, and keep the connection lifecycle outside the agent’s business logic.

Lists & tasks — task lists by category; tasks with priority, assignee, due date, tags, and a status workflow (todo → blocked → in_progress → done / cancelled).

Dependencies — add_dependency builds a DAG with cycle prevention; a task with unfinished dependencies is Blocked and can't be started/completed. Completing a task unblocks its dependents.

Recurrence — completing a daily/weekly/monthly task spawns the next occurrence (due date advanced, checklist reset).

Checklists & comments — sub-item checklists per task and a comment thread.

Analytics — overdue (past-due open tasks, most overdue first), workload (open tasks per assignee), and list_summary (status mix + completion %).

Architecture

How Task MCP Server fits into an agent system.

The model never needs the implementation details or credentials of the system behind the server. It sees reviewed tool definitions. The MCP client handles discovery and calls, while the server keeps ownership of validation, policy, and communication with its domain system.

ADK-Rust agent

Chooses a capability from the reviewed tool catalog.

→

MCP client

Discovers schemas, sends calls, and receives typed content.

→

Task MCP Server

Validates the request and owns 20 documented tool contracts.

→

Domain system

Keeps the API, data, credentials, and business rules behind the server.

Connection: stdio · Server framework: ADK MCP SDK + rmcp

Task MCP Server architecture diagram from its official repository

Tool catalog

What can an agent ask Task MCP Server to do?

Each tool has a stable name, a human-readable purpose, and a JSON input contract discovered during MCP initialization. Risk classes come from the project’s registry manifest when one is available.

20 named tools

create_list

Create a task list

internal write

get_list

Get a task list

read only

list_lists

List task lists by category

read only

list_summary

List task counts by status + completion %

read only

create_task

Create a task

internal write

get_task

Get a task by id

read only

list_tasks

List tasks by list/status/assignee

read only

update_task

Update title/description/priority/due date

internal write

assign_task

Assign a task to someone

internal write

set_status

Set task status (blocker-gated; spawns recurrence)

internal write

add_dependency

Add a dependency (cycle-checked, may block task)

internal write

add_checklist_item

Add a checklist item to a task

internal write

Governance

Understand the effect of every tool.

A server connection inherits the authority of its credentials and deployment environment. The declarations below come from this project’s README and MCP registry manifest; your application still decides which tools an agent receives and where approval is required.

11 internal write9 read only

Two writes are gated (requires_approval): delete_task (destructive — removes a task and its comments; refused if other tasks depend on it) and bulk_reassign (mass reassignment with broad…
Workflow integrity — blocker gating prevents starting blocked work; dependency cycles are rejected; delete is refused while dependents exist. Everything is on the audit trail (audit_log).
Reads are read_only. Sample data is fictitious.

MCP surface

What the current documentation declares.

MCP can carry tools, resources, prompts, structured results, progress, cancellation, and long-running work. This record highlights the modern protocol features explicitly mentioned by this repository.

Completion

Long-running tasks

ADK MCP SDKrmcpRegistry manifest

Install and connect

Follow the project’s documented starting point.

Install the server in the environment that owns its credentials and domain access. Add it to your MCP host, verify the discovered tools, and narrow the toolset before giving it to a production agent.

Install

cargo install mcp-task

ADK-Rust connection shape

let toolset = McpToolset::from_stdio(
    "mcp-task",
    ["mcp-task"],
).await?;

let agent = LlmAgentBuilder::new("agent")
    .tools(toolset.tools().await?)
    .build()?;

Commands and configuration are extracted from the public README. Confirm prerequisites, environment variables, and release-specific options in the official documentation before deployment.

Official documentation

Continue with the project maintainers’ source of truth.

This page provides an approachable map of the server. The repository remains authoritative for exact schemas, prerequisites, configuration, examples, tests, releases, and security updates.

Overview ↗README.md CHANGELOG ↗CHANGELOG.md Architecture ↗docs/architecture.svg Issues and support ↗github.com issues

Keep exploring