Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@things3-mcp show my projects"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A deliberately small MCP server for the parts of Things used in daily work.
This project is based on hald/things-mcp. It was rebuilt around a much smaller tool and code surface rather than preserving the full upstream feature set.
list_projectsLists active Things projects.
Parameters: none.
Each result contains:
id: Project ID used by the other tools.
title: Project title.
list_tasksLists tasks from Today or from one project.
Parameters:
view (required): today or project.
project_id: Required when view is project; omit it for today.
Each result contains:
id: Task ID used by update_task.
title
notes
when: Scheduled date, when present.
status
project_id: null for a standalone task.
project: Project title, or null for a standalone task.
Examples:
list_tasks(view="today")
list_tasks(view="project", project_id="PROJECT_ID")create_taskCreates a standalone task or a task inside an existing project.
Parameters:
title (required)
project_id: Optional ID returned by list_projects.
when: Optional Things schedule such as today, tomorrow, or
YYYY-MM-DD.
notes: Optional task notes.
Examples:
create_task(title="Buy milk", when="today")
create_task(
title="Prepare meeting notes",
project_id="PROJECT_ID",
when="tomorrow",
notes="Cover the launch plan"
)Things does not return the new task ID through this URL operation. Call
list_tasks afterward when the ID is needed.
update_taskUpdates an existing task without moving it or changing unrelated Things data.
Parameters:
task_id (required): ID returned by list_tasks.
title: Replacement title.
notes: Replacement notes. Pass an empty string to clear them.
when: Replacement schedule.
status: open, completed, or canceled.
At least one change is required. Updating a task requires the Things authorization token described below.
Examples:
update_task(task_id="TASK_ID", notes="Updated context", when="tomorrow")
update_task(task_id="TASK_ID", status="completed")
update_task(task_id="TASK_ID", status="open")Related MCP server: Things MCP
The server does not expose search, deadlines, tags, areas, headings, checklists, project creation, task movement, bulk operations, or deletion.
macOS with Things 3 installed
Things URLs enabled in Things Settings
Updating tasks also requires the Things authorization token. Enable it under Things → Settings → General → Enable Things URLs → Manage.
Things requires a private authorization token before another app can modify an existing task. The token stays in Things and is read locally by this server; do not paste it into the MCP configuration or share it with an assistant.
On your Mac:
Open Things.
Go to Things → Settings → General.
Enable Things URLs.
Click Manage next to Things URLs.
Enable or generate the authorization token.
Creating tasks only requires Things URLs. Editing, completing, canceling, and reopening tasks require the authorization token.
Run directly from GitHub:
uvx --from git+https://github.com/snellingio/things3-mcp things-mcpOr clone the repository for local development:
git clone https://github.com/snellingio/things3-mcp.git
cd things3-mcp
uv sync --extra test
uv run things-mcpExample MCP configuration using GitHub:
{
"mcpServers": {
"things": {
"command": "uvx",
"args": [
"--from",
"git+https://github.com/snellingio/things3-mcp",
"things-mcp"
]
}
}
}Set THINGS_MCP_TRANSPORT=http to use HTTP instead of stdio. The optional
THINGS_MCP_HOST and THINGS_MCP_PORT variables default to 127.0.0.1 and
8000.
uv sync --extra test
uv run pytest
uv run ruff check .Create a task, optionally in a Things project.
| Name | Required | Description | Default |
|---|---|---|---|
| when | No | Optional Things schedule such as today, tomorrow, or YYYY-MM-DD. | |
| notes | No | Optional task notes. | |
| title | Yes | Task title. | |
| project_id | No | Optional ID returned by list_projects. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of disclosing behavioral effects. It only says 'create a task' and gives no details about prerequisites, side effects, return values, or error conditions. For a mutation operation, this is insufficient.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with no wasted words, making it very concise and front-loaded. However, it is almost too sparse, lacking any supporting context that would make it more useful.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with 4 parameters and no output schema, the description is too thin. It omits when to use the tool, how to obtain a project_id, what happens on success or failure, and any return value. The schema helps but the description doesn't provide enough surrounding context for an agent to use it confidently.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so each parameter already has a description. The description adds minimal value by mentioning optional project membership, but it doesn't elaborate on parameter relationships or expected formats beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool creates a task, with an optional project context. It distinguishes from siblings like list_tasks, list_projects, and update_task by using a specific verb and resource.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives. It doesn't mention that this is for new tasks, while update_task handles existing tasks, or that list_projects should be called first to obtain a project_id.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List active Things projects.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It clarifies that only active projects are listed, but does not disclose return format, ordering, pagination, or any side effects. 'List' implies read-only behavior, but more detail could be added.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single clear sentence of only 4 words. It is front-loaded and contains no extraneous information, earning every word.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (no params, no output schema), the description is complete. It clearly states the tool's purpose and scope. There are no hidden complexities or missing details that would prevent correct usage.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
There are zero parameters, which grants a baseline score of 4. The description does not need to explain any parameters because the input schema is empty, and the tool takes no arguments.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb 'List' and resource 'Things projects' with a clear scope ('active'), which fully distinguishes it from sibling tools like list_tasks. It unequivocally states what the tool does.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The active project filter implies when to use this tool, but there is no explicit guidance on when not to use it or which alternative to choose. Given the sibling tools are task-focused, the context is implied but not directly stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List tasks from Today or from one project.
| Name | Required | Description | Default |
|---|---|---|---|
| view | Yes | Use "today" for the Things Today list or "project" for one project. | |
| project_id | No | Required for the project view and omitted for the today view. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the behavioral burden. It states only the action and scope, but does not disclose whether the operation is read-only, what permissions are needed, what the return format is, or any limitations such as pagination or inclusion of completed tasks. This is a significant gap for a listing tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that is clear and to the point, with no wasted words. It effectively communicates the tool's core function in minimal space.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
While the tool is simple and the schema covers parameters well, there is no output schema and the description does not mention any behavioral context or return details. Given the simplicity, it is minimally adequate but lacks explicit guidance on what the agent should expect.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema covers both parameters with descriptions, achieving 100% schema description coverage. The tool description adds no extra parameter semantics beyond what the schema already provides, so the baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('List') and resource ('tasks') and clarifies the two possible scopes ('Today' or 'one project'). This clearly distinguishes it from sibling tools like list_projects (which lists projects) and create/update tasks.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies this tool is used to list tasks, but it does not explicitly state when to use it over alternatives like list_projects, nor mention exclusions. The schema clarifies the view parameter, but the tool-level description gives no direct when-to-use guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Update a task's basic fields or status.
| Name | Required | Description | Default |
|---|---|---|---|
| when | No | Optional replacement Things schedule. | |
| notes | No | Optional replacement notes. Pass an empty string to clear them. | |
| title | No | Optional replacement title. | |
| status | No | Optional open, completed, or canceled status. | |
| task_id | Yes | ID returned by list_tasks. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden of behavioral disclosure, but it only says 'Update a task's basic fields or status.' It does not disclose whether unspecified fields remain unchanged, whether the task must exist, or any error behavior. The mutation aspect is implied but not elaborated.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise sentence with no redundant wording. It effectively communicates the core purpose without unnecessary details.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has 5 parameters and no output schema, so the description should explain what a successful update returns (if anything) or any important behavioral side effects. It does neither. While the schema covers parameters, the description fails to provide crucial context for safe invocation, such as partial update behavior.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already provides detailed descriptions for all 5 parameters, so coverage is 100%. The description adds no additional parameter-level meaning beyond the generic phrase 'basic fields or status,' which adds little value over the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Update') and resource ('a task'), and mentions 'basic fields or status' which covers the schema's parameters. It distinguishes from siblings like list_tasks and create_task by virtue of the 'update' verb, though it doesn't explicitly name alternatives.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus create_task or list_tasks. There is no mention of prerequisites, such as needing an existing task_id, or when this tool is preferred over creating a new task.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v0.1.0create_tasklist_projectslist_tasksupdate_taskEach tool targets a distinct resource and action: listing tasks vs listing projects, creating vs updating tasks. Even though list_tasks and update_task both involve tasks, their purposes are clearly separated.
All tool names follow a consistent verb_noun pattern with lowercase and underscores: list_tasks, list_projects, create_task, update_task. No mixed conventions.
4 tools is well-scoped for a simple Things integration, covering core task interactions without unnecessary bloat. Each tool is useful and distinct.
The set covers listing, creating, and updating tasks, as well as listing projects. Missing delete operation, but update_task with status likely allows completing tasks, mitigating the gap.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
Official Todoist MCP server for AI assistants to manage tasks, projects, and workflows.
MCP server for generating rough-draft project plans from natural-language prompts.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/snellingio/things3-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
