configure
Set this server's configuration for this session: the Moodle site (url; a new one is added to the server's sites and kept, a known one becomes active, see use_site), whether the browser runs without a window (headless), how student tools view and do things (trail) and the browser profile folder (...
This record as markdown: /tools/falkenslab-moodle-mcp/configure.md
What configure does on Moodle
AI agents use configure 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 |
|---|---|---|---|
url | string | — | The Moodle site's URL, or any page of it (a course URL works: the site is read from it) |
role | string | — | Keep only one role's tools for this session (teacher or student), from all; never back to all |
trail | string | — | How student tools view and do things: realistic (real pages, human pace; Moodle logs views and completion) or fast |
access | string | — | read: keep only the tools that change nothing in Moodle for this session; never back to write |
scopes | string | — | Narrow the kinds of tools for this session: a profile (teacher, student, content) or scopes (content, student-data, grading, communication, as-student, browser) |
headless | boolean | — | Run the browser without a window (logging in always shows one) |
profileDir | string | — | Absolute folder for the browser profile that keeps the Moodle session; outside the server's folder |
studentData | string | — | Tighten how others' data reaches you for this session (block is strictest). Only stricter than now, never looser |
Parameters from the server's own tool schema.
Why configure is rated Medium
An AI agent can call configure 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 URL/endpoint input (url)
Attacks that exploit this kind of access
The rule that runs configure 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 configure, this is the rule to start with:
configure 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 configure call is checked against it from then on.
Questions about configure
Set this server's configuration for this session: the Moodle site (url; a new one is added to the server's sites and kept, a known one becomes active, see use_site), whether the browser runs without a window (headless), how student tools view and do things (trail) and the browser profile folder (profileDir). It can also narrow the kinds of tools (scopes), the role (role) or access to read only (access) and tighten how others' data reaches you (studentData), never the other way: widening is the person's, in the client's configuration. Each is optional; only those given change. The URL is checked to be a Moodle site. Kept in memory only, but for a new site, which stays among the server's sites. Returns the effective configuration, as server_info. 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.
configure accepts 8 parameters: url, role, trail, access, scopes, headless, profileDir, studentData. 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 configure: 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.
configure 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 configure 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 configure. 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.
configure 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