OpenProject CE MCP Server

Overview Schema Source Related Servers Discussions Admin

List time entries

list_time_entries

Read-onlyIdempotent

List filtered time entries with optional accurate totals to determine how much time was spent on a specific work package, project, user, or date range.

Instructions

List logged time, filtered server-side, with an optional accurate total.

Answers "how much time went into this ticket?" or "how much did the team spend on project X in June?". Filters combine with AND, so project_id + user='me' + a date range is one call.

Returns the standard list envelope: items of {id, hours, spent_on, comment, user, activity, work_package, project} plus pagination. hours is a float (1.5 = 1h30), never an ISO duration. With sum_hours=true, the envelope also carries sums.total_hours over all matches and a groups bucket per activity with its own count/sums.total_hours — both over the whole filtered set, so never add pages up yourself.

Pitfalls. Without view-all-time-entries you see only your own entries, so a small total may mean "not allowed to see" rather than "nobody booked time". work_package_id scopes to that one work package — child work packages are not included; a parent's roll-up needs a query per child. Summing stops at 2000 entries, noted in notes; narrow the range or project rather than trusting the number.

Cross-references: book time with log_time; correct with update_time_entry, remove with delete_time_entry; activity ids/names from get_project_metadata; the work package from get_work_package.

Input Schema

TableJSON Schema

Name	Required	Description
`page`	No	1-based page number.
`user`	No	Whose time to list: numeric user id, or 'me'. Omit for everyone you're permitted to see.
`to_date`	No	Latest spent-on date, ISO YYYY-MM-DD, inclusive.
`fetch_all`	No	Aggregate every page into one result instead of page 1. Capped at 500 items (noted when it bites); mutually exclusive with page. sum_hours already reads every entry regardless.
`from_date`	No	Earliest spent-on date, ISO YYYY-MM-DD, inclusive; combine with to_date for a range (either bound optional).
`page_size`	No	Entries per page (max 100); the instance may clamp lower, reported in pagination.
`sum_hours`	No	Accurate total over every matching entry (not just this page), broken down per activity. One request per 100 matches, capped at 2000 (noted if hit). Leave false for rows only.
`project_id`	No	Only entries in this project (numeric id or identifier; from list_projects), including project-level entries with no work package.
`activity_id`	No	Only entries booked on this activity; ids are instance-specific, from get_project_metadata(project_id=...).
`work_package_id`	No	Only entries on this work package; ids from search_work_packages / list_work_packages.

Output Schema

TableJSON Schema

Name	Required	Description
`sums`	No	Present only when show_sums was requested.
`items`	No	The page of results.
`notes`	No	Degradation markers: capped aggregations, unavailable modules, …
`groups`	No	Present only when group_by was requested.
`pagination`	Yes	Total/page/page_size/has_more.

Schema Changelog

Changes observed during successful MCP inspections.

Changed8 schema fields changedv0.3.2Sep 24, 2026

changedInput schema / properties / activity_id / description

Previous value: -"Only entries booked on this activity. Activity ids are instance-specific and come from get_project_metadata(project_id=...)."New value: +"Only entries booked on this activity; ids are instance-specific, from get_project_metadata(project_id=...)."

changedInput schema / properties / fetch_all / description

Previous value: -"Aggregate every page of rows into one result instead of returning page 1. Capped at 500 items with a note when the cap bites; mutually exclusive with page. sum_hours already reads every matching entry for its total, with or without fetch_all."New value: +"Aggregate every page into one result instead of page 1. Capped at 500 items (noted when it bites); mutually exclusive with page. sum_hours already reads every entry regardless."

changedInput schema / properties / from_date / description

Previous value: -"Earliest spent-on date, ISO YYYY-MM-DD, inclusive. Combine with to_date for a range; either bound may be omitted for an open-ended one."New value: +"Earliest spent-on date, ISO YYYY-MM-DD, inclusive; combine with to_date for a range (either bound optional)."

changedInput schema / properties / page_size / description

Previous value: -"Entries per page (max 100); the instance may clamp it lower and the returned pagination reports what actually came back."New value: +"Entries per page (max 100); the instance may clamp lower, reported in pagination."

changedInput schema / properties / project_id / description

Previous value: -"Only entries in this project (numeric id or identifier, from list_projects). Includes project-level entries that have no work package."New value: +"Only entries in this project (numeric id or identifier; from list_projects), including project-level entries with no work package."

changedInput schema / properties / sum_hours / description

Previous value: -"Compute an accurate total over EVERY matching entry (not just this page) and break it down per activity. Costs one request per 100 matches and is capped at 2000 entries — a cap hit is reported in 'notes'. Leave false when you only need rows."New value: +"Accurate total over every matching entry (not just this page), broken down per activity. One request per 100 matches, capped at 2000 (noted if hit). Leave false for rows only."

changedInput schema / properties / user / description

Previous value: -"Whose time to list: a numeric user id, or the literal 'me' for the token owner. Omit for everyone you are allowed to see — on most instances that is only your own entries unless you hold the view-all-time-entries permission."New value: +"Whose time to list: numeric user id, or 'me'. Omit for everyone you're permitted to see."

changedInput schema / properties / work_package_id / description

Previous value: -"Only entries booked on this work package. Ids come from search_work_packages / list_work_packages. The filter name differs between OpenProject versions; this tool probes the instance and uses the right one."New value: +"Only entries on this work package; ids from search_work_packages / list_work_packages."

First observedv0.1.0Aug 12, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false. The description adds substantial behavioral detail: the sum_hours behavior (capped at 2000, one request per 100 matches), the permission pitfall (only own entries without view-all-time-entries), and the work_package_id exclusion of child work packages. These are not in the annotations and are critical for correct usage.

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

Conciseness4/5

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

The description is fairly long but well-structured: it front-loads the purpose, then explains output envelope, then pitfalls, then cross-references. Each paragraph adds essential information without redundancy. It is appropriately detailed for a complex tool with 10 parameters and nuanced behaviors.

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

Completeness5/5

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

Given the tool's complexity (10 params, sum behavior, permission pitfalls, pagination caps) and the existence of an output schema (which covers return format), the description is remarkably complete. It covers filtering, summing, permission caveats, the 2000-entry cap, and provides cross-references to related tools. Nothing an agent needs to call it correctly is missing.

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?

The schema descriptions cover 100% of parameters, so the baseline is 3. The description adds meaningful nuance beyond the schema: it explains that filters combine with AND, that sum_hours reads all entries regardless of page, and details the work_package_id behavior (no children). This extra context justifies a score above baseline, though it doesn't add per-parameter semantics for every field.

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

Purpose5/5

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

The description clearly states the tool lists logged time with server-side filtering and an optional total. It gives concrete examples (e.g., 'how much time went into this ticket?') and specifies the scope (filtered, with AND combination). While it doesn't explicitly name a sibling for differentiation, the purpose is unambiguous and aligns with the title.

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

Usage Guidelines4/5

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

The description provides clear usage context with example questions and explains filter combination (AND). It also cross-references related tools (log_time, update_time_entry, delete_time_entry) and notes permission implications. However, it does not explicitly state when to avoid this tool or when an alternative would be better, though the cross-references partially cover this.

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

Deploy Server