redmine-mcp

Overview Schema Source Related Servers Score Discussions Admin

Search Redmine

search

Read-onlyIdempotent

Search visible Redmine content across projects, issues, wiki pages, and more. Filter by type, scope, open issues, or attachments to find matching results without modifying data.

Instructions

Search visible global Redmine content through GET /search.json for the configured API user. The optional query maps to Redmine's q parameter. Supports only Redmine's documented offset, limit, scope, all_words, titles_only, result-type flags, open_issues, and attachments controls; project_id, page, include, and internal or administrator-only controls are rejected. Redmine defaults to 25 results and caps the limit at 100. Results preserve Redmine's upstream order and expose only id, title, type, url, description, and datetime. Unsafe result URLs are omitted, and this read never changes Redmine data.

Input Schema

TableJSON Schema

Name	Required	Description
`news`	No	Include news results
`limit`	No	Number of matching results to return. Redmine defaults to 25 and caps this at 100.
`query`	No	Search text. Redmine sends this as q and accepts multiple space-separated terms.
`scope`	No	Search scope: all, my_project, my_projects, bookmarks, or subprojects. The legacy my_project value is sent as Redmine's current my_projects value.
`issues`	No	Include issue results
`offset`	No	Number of matching results to skip
`messages`	No	Include message results
`projects`	No	Include project results
`all_words`	No	Require every query term. Redmine defaults this to true.
`documents`	No	Include document results
`changesets`	No	Include changeset results
`wiki_pages`	No	Include wiki-page results
`attachments`	No	Attachment search mode: 0 for descriptions only, 1 for descriptions and attachments, or only for attachments only
`open_issues`	No	Restrict issue results to open issues
`titles_only`	No	Search titles only

Output Schema

TableJSON Schema

Name	Required	Description	Default
`paging`	Yes
`filters`	Yes
`results`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Sep 10, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Annotations already signal read-only, open-world, idempotent, non-destructive behavior, and the description adds meaningful detail: Redmine's 25-result default, 100 limit, upstream ordering, exposed fields, omission of unsafe URLs, and the guarantee that the read never mutates data. This goes well beyond the structured hints.

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 description is dense but efficient; each sentence earns its place. It front-loads the core purpose and endpoint, then adds restrictions, defaults, and result behavior without filler or repetition beyond what is necessary.

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?

For a 15-parameter search tool with no required parameters, the description covers endpoint, scope, supported/rejected controls, pagination defaults, result shape, and safety. The rich output schema and detailed input schema carry the remaining burden, so nothing essential 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?

Schema coverage is 100%, so the baseline is 3. The description adds value by explaining how 'query' maps to Redmine's q parameter, grouping supported controls, explicitly listing rejected parameters, and documenting defaults/caps that are not fully captured in individual schema descriptions.

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 names a specific verb ('Search'), resource ('visible global Redmine content'), and endpoint (GET /search.json). It clearly distinguishes this tool from the sibling listing tools by emphasizing global content search and explicit scope restrictions.

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?

It gives clear context for when to use this tool: searching visible global Redmine content. It also states which Redmine controls are rejected (project_id, page, include, internal/admin-only), giving useful boundaries, though it does not explicitly name alternative sibling tools.

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