LimeSurvey MCP Server

Set question properties

limesurvey_set_question_properties

Instructions

Update question properties. Writable fields: title, preg, other, mandatory, encrypted, question_order, scale_id, same_default, relevance, question_theme_name, modulename, same_script, question, help, script. NOT writable through RemoteControl (the call is rejected before any request is sent): attributes, question_attributes, questionattributes, answers, answeroptions, answer_options, subquestions, defaultvalues, default_values, conditions, qid, gid, sid, parent_qid, type, question_l10ns. Question attributes, answer options and subquestions can only be changed by re-importing the question (limesurvey_import_question, or limesurvey_import_group / limesurvey_import_survey, all with import_data_path) or in the LimeSurvey admin UI; limesurvey_replace_question swaps a question of an inactive survey for the question in a .lsq file (inactive surveys only). Localized texts (question, help, script) are written with a language: {"language": "de", "question": "..."} or {"questionl10ns": {"de": {"question": "..."}}}. question, help and script are localized: pass them with data.language (or the language parameter); the server moves them into questionl10ns[language], so the other text fields are never blanked (LimeSurvey's legacy form would reset a field you did not send to an empty string). question_order is refused for questions that have legacy condition dependencies, and the group is renumbered after each change. Keys LimeSurvey does not report back are returned in warnings. Verified against the LimeSurvey 6.17.11 source; older releases may differ.

Calls LimeSurvey RemoteControl method set_question_properties. Authentication uses the configured service account; do not provide a session key.

Input Schema

Name	Required	Description	Default
`data`	Yes	Question property names mapped to new values.
`language`	No	LimeSurvey language code; null uses the survey default.
`question_id`	Yes	Numeric question ID.
`response_format`	No	Output format. JSON preserves the complete structured result; Markdown is optimized for reading.	json

Output Schema

Name	Required	Description	Default
`method`	Yes
`result`	Yes
`warnings`	No
`truncated`	No
`truncation_message`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv1.6.0Oct 14, 2026

addedOutput schema / properties / warnings

Added value: +{
+  "items": {
+    "$ref": "#/definitions/__schema0"
+  },
+  "type": "array"
+}

First observedv1.3.1Jul 29, 2026

TDQS

A4.9/5.0

Behavior5/5

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

Goes well beyond the annotations: names the rejected-before-send behavior, the question_order refusal for legacy condition dependencies, group renumbering after each change, warnings for unreported keys, the legacy-form field-blanking risk for localized texts, and a source-version caveat (6.17.11). Idempotency is declared false in annotations but the description adds the mutation consequences that matter for invocation.

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?

Dense and front-loaded: the writable list precedes the non-writable list, then the alternative paths. It is long, but nearly every sentence carries operational detail; only minor tightening (e.g. repeated field aliases like attributes/question_attributes and answers/answeroptions) could shrink it without loss.

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?

An output schema exists so return values need no explanation, and the description completes the remaining picture: auth uses the configured service account with no session key, the underlying RemoteControl method, mutation side effects, and version sensitivity. An agent has everything needed to call this correctly.

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

Parameters5/5

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

Schema coverage is 100%, but the schema itself is an opaque generically-typed object; the description compensates by enumerating the writable keys, spelling out the localized-text shapes ({"language":"de","question":"..."} vs questionl10ns), and noting the language parameter moves text into questionl10ns[language].

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?

Opens with a specific verb+resource ('Update question properties') and immediately bounds the scope with an explicit writable-field list. It is clearly distinguishable from its sibling limesurvey_get_question_properties and from the import/replace tools it names.

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

Usage Guidelines5/5

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

Explicitly states what CANNOT be written via this call and routes the agent to concrete alternatives (limesurvey_import_question, limesurvey_import_group/survey with import_data_path, admin UI, limesurvey_replace_question with the inactive-survey caveat). It also tells the agent the call is rejected before any request is sent, which is actionable when/when-not guidance.

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

Deploy Server