update_question
Change a question of a bank through its type's form, with create_question's inputs: only what's given changes (a list given, such as answers, pairs, choices, items, drags, markers, drops or a wildcard's values, replaces the question's). Saving makes a new version with its own id, the one returned...
This record as markdown: /tools/falkenslab-moodle-mcp/update-question.md
What update_question does on Moodle
AI agents use update_question to create or update resources in Moodle, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Moodle environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
name | string | — | |
sets | integer | — | Calculated types: how many sets of values (10 by default) |
text | string | — | The question text (HTML) |
drags | array | — | ddimageortext: the draggable items |
drops | array | — | ddimageortext, ddmarker: where the items or markers go |
image | string | — | ddimageortext, ddmarker: the background image, an absolute local path |
items | array | — | ordering: the items, in the right order |
pairs | array | — | match, ddmatch: each question and its answer; an answer without a question is a distractor |
bankId | integer | Yes | The bank's id (a course module id), as list_question_banks gives it |
choose | integer | — | randomsamatch: how many short-answer questions of the category it draws |
fields | object | — | Any other field of the type's form, by name |
answers | array | — | Multichoice, shortanswer and numerical answers |
Parameters from the server's own tool schema.
Why update_question is rated Medium
An AI agent can call update_question faster than any human can review: one bad instruction and it creates or modifies resources in Moodle by the hundred, each call as confident as the last.
Risk signalsAccepts freeform code/query input (coderunner.testCases[].code) · High parameter count (68 properties)
Attacks that exploit this kind of access
The rule that runs update_question safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Moodle, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For update_question, this is the rule to start with:
update_question stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Moodle, apply this rule, and every update_question call is checked against it from then on.
Questions about update_question
Change a question of a bank through its type's form, with create_question's inputs: only what's given changes (a list given, such as answers, pairs, choices, items, drags, markers, drops or a wildcard's values, replaces the question's). Saving makes a new version with its own id, the one returned, which quizzes using the latest version get from then on. Changes the bank: confirm with the person first. It is categorised as a Write tool in the Moodle MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
update_question accepts 12 parameters: name, sets, text, drags, drops, image, items, pairs, bankId, choose, fields, answers. Required: bankId. The full parameter table on this page comes from the server's own tool schema.
Register the Moodle MCP server in PolicyLayer and add a rule for update_question: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Moodle. Nothing to install.
update_question is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the update_question rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for update_question. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
update_question is provided by the Moodle MCP server (@falkenslab/moodle-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Moodle, and thousands of servers like it.
This server
Across the catalogue