Todoist MCP Server

find-tasks

Read-onlyIdempotent

Search Todoist tasks using text, project, section, labels, responsible user, or saved filters to retrieve matching items quickly.

Instructions

Find tasks by text search, project/section/parent container, responsible user, labels, a raw Todoist filter string, or a saved filter by ID or name (filterIdOrName). At least one filter must be provided.

Input Schema

TableJSON Schema

Name	Required	Description
`limit`	No	The maximum number of tasks to return.
`cursor`	No	The cursor to get the next page of tasks (cursor is obtained from the previous call to this tool, with the same parameters).
`filter`	No	A raw Todoist filter query string (e.g. "today", "p1", "##Work", "(today \| overdue) & p1"). Combined with other filters using AND. Cannot be used with projectId, sectionId, parentId, or filterIdOrName.
`labels`	No	The labels to filter the tasks by
`parentId`	No	Find subtasks of this parent task.
`projectId`	No	Find tasks in this project. Project ID should be an ID string, or the text "inbox", for inbox tasks.
`sectionId`	No	Find tasks in this section.
`searchText`	No	The text to search for in tasks.
`filterIdOrName`	No	The ID or name of a saved Todoist filter. The filter's query will be fetched and used to find tasks. Cannot be used with the `filter` parameter, projectId, sectionId, or parentId.
`labelsOperator`	No	The operator to use when filtering by labels. This will dictate whether a task has all labels, or some of them. Default is "or".
`responsibleUser`	No	Find tasks assigned to this user. Can be a user ID, name, or email address. The current user also includes unassigned tasks.
`responsibleUserFiltering`	No	How to filter by responsible user when responsibleUser is not provided. "assigned" = only tasks assigned to others; "unassignedOrMe" = only unassigned tasks or tasks assigned to me; "all" = all tasks regardless of assignment. Default value will be `unassignedOrMe`.

Output Schema

TableJSON Schema

Name	Required	Description
`tasks`	Yes	The found tasks.
`hasMore`	Yes
`nextCursor`	No
`totalCount`	Yes	The total number of tasks in this page.
`appliedFilters`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv13.3.1Sep 22, 2026

TDQS

A3.5/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds the mandatory-filter behavior, but does not disclose what happens when no filter is passed or any response/pagination behavior; the output schema presumably covers return structure.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The entire description is a single, dense sentence that front-loads the action and resource, lists the relevant filter dimensions, and states the key constraint. There is no redundancy or filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's 12 parameters, a fully populated schema, annotations, and an output schema, the description provides a sufficient high-level mental model and the one critical cross-parameter constraint. It is slightly incomplete only because it does not address sibling-tool differentiation or when an alternative should be used.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The description adds value by stating the at-least-one-filter invariant, which is not enforced in the schema, and by grouping the 12 parameters into meaningful filter categories that help an agent reason about valid calls.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource — 'Find tasks by...' — and enumerates the many filter dimensions (text, project/section/parent, responsible user, labels, raw filter, saved filter), making its scope immediately clear. It does not explicitly distinguish itself from siblings like find-tasks-by-date or find-completed-tasks, so it stops short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The only usage guidance is the constraint 'At least one filter must be provided,' which is a call requirement, not a when-to-use guideline. With close siblings such as find-tasks-by-date and find-completed-tasks present, the description gives no direction on when to choose this tool over an alternative.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.