get_course_logs
Read a course's logs, newest first, as its logs report lists them: by a user (an alias when the server pseudonymizes), an activity, a kind of action and a time span, a page at a time: limit entries (50 by default) after skipping offset; more says whether there are others. Each entry: when, who, w...
This record as markdown: /tools/falkenslab-moodle-mcp/get-course-logs.md
What get_course_logs does on Moodle
AI agents call get_course_logs to retrieve information from Moodle without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
from | string | — | ISO 8601 |
user | string | — | The participant's alias, as the reading tools give it when the server pseudonymizes |
limit | integer | — | How many entries (50 by default) |
until | string | — | ISO 8601 |
action | string | — | |
offset | integer | — | How many entries to skip first, newest first (0 by default) |
userId | integer | — | The participant's user id, when the server shows names |
courseId | integer | Yes | |
activityId | integer | — | |
includeDescriptions | boolean | — | Also each entry's description, Moodle's sentence about it (longer; default false) |
Parameters from the server's own tool schema.
Why get_course_logs is rated Low
Even though get_course_logs only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Risk signalsHigh parameter count (10 properties)
Attacks that exploit this kind of access
The rule that runs get_course_logs 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 get_course_logs, this is the rule to start with:
get_course_logs is read-only, so it stays allowed. 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 get_course_logs call is checked against it from then on.
Questions about get_course_logs
Read a course's logs, newest first, as its logs report lists them: by a user (an alias when the server pseudonymizes), an activity, a kind of action and a time span, a page at a time: limit entries (50 by default) after skipping offset; more says whether there are others. Each entry: when, who, who it was about, where, what happened (Moodle's longer description only with includeDescriptions). Never IP addresses. It is categorised as a Read tool in the Moodle MCP Server, which means it retrieves data without modifying state.
get_course_logs accepts 10 parameters: from, user, limit, until, action, offset, userId, courseId, activityId, includeDescriptions. Required: 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 get_course_logs: 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.
get_course_logs is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_course_logs 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 get_course_logs. 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.
get_course_logs 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