message_participants

SERVERMoodle SOURCE@falkenslab/moodle-mcp

Medium RISK CLASS

Category Write

Parameters 72 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/falkenslab-moodle-mcp/message-participants.md

WHAT IT DOES

What message_participants does on Moodle

AI agents use message_participants 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
`role`	integer	—	Or: everyone with this role
`text`	string	Yes
`group`	integer	—	Or: everyone in this group
`users`	array	—	The participants' aliases, as the reading tools give them when the server pseudonymizes
`userIds`	array	—	The participants' user ids, when the server shows names
`courseId`	integer	Yes
`inactiveSince`	string	—	Or: everyone who hasn't accessed the course since this date (ISO 8601)

Parameters from the server's own tool schema.

RISK

Why message_participants is rated Medium

An AI agent can call message_participants 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

RECOMMENDED RULE

The rule that runs message_participants 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 message_participants, this is the rule to start with:

message_participants Rate-limited

message_participants 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "message_participants": {
      "limits": [
        {
          "counter": "message_participants_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Moodle, apply this rule, and every message_participants call is checked against it from then on.

FAQ

Questions about message_participants

What does the message_participants tool do? +

Send one private message to several participants of a course, as the participants page's "Send a message" does: to users (aliases) or userIds, or to everyone chosen by role, group or inactiveSince (everyone when none is given), the person left out. Returns who got it and who Moodle didn't write to, and why. The text is plain, with no aliases in it. Sent as the person, visibly: confirm the text and the recipients 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.

What parameters does message_participants accept? +

message_participants accepts 7 parameters: role, text, group, users, userIds, courseId, inactiveSince. Required: text, courseId. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on message_participants? +

Register the Moodle MCP server in PolicyLayer and add a rule for message_participants: 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.

What risk level is message_participants? +

message_participants is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit message_participants? +

Yes. Add a rate_limit block to the message_participants 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.

How do I block message_participants completely? +

Set action: deny in the PolicyLayer policy for message_participants. 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.

What MCP server provides message_participants? +

message_participants 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.

KEEP EXPLORING

More on Moodle, and thousands of servers like it.

This server

All 233 Moodle tools →

Across the catalogue

The MCP Attack Database →

Guides

Govern customer-ops agents →Argument validation →Scoped token →