set_grade
Set a participant's grade in a grade item, as the gradebook's single view does: a manual item takes it; an activity's or a category's is overridden (until override false takes it off). Also feedback and excluding it from the totals. The grade as text: points ("7.5"), a scale item, or "none" to em...
This record as markdown: /tools/falkenslab-moodle-mcp/set-grade.md
What set_grade does on Moodle
AI agents use set_grade 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 |
|---|---|---|---|
user | string | — | The participant's alias, as the reading tools give it when the server pseudonymizes |
grade | string | — | |
itemId | integer | Yes | The grade item, as get_gradebook_setup or get_grader_report gives it |
userId | integer | — | The participant's user id, when the server shows names |
courseId | integer | Yes | |
excluded | boolean | — | Exclude it from the totals |
feedback | string | — | No aliases in it, since the student reads it |
override | boolean | — | false: take an activity's or category's override off |
Parameters from the server's own tool schema.
Why set_grade is rated Medium
An AI agent can call set_grade 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.
Attacks that exploit this kind of access
The rule that runs set_grade 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 set_grade, this is the rule to start with:
set_grade 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 set_grade call is checked against it from then on.
Questions about set_grade
Set a participant's grade in a grade item, as the gradebook's single view does: a manual item takes it; an activity's or a category's is overridden (until override false takes it off). Also feedback and excluding it from the totals. The grade as text: points ("7.5"), a scale item, or "none" to empty it. Students may see it: 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.
set_grade accepts 8 parameters: user, grade, itemId, userId, courseId, excluded, feedback, override. Required: itemId, courseId. 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 set_grade: 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.
set_grade 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 set_grade 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 set_grade. 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.
set_grade 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