Posts a visible suggestion to human collaborators watching the document WITHOUT making any changes to the diagram. Use this when you observe something worth flagging — a potential mistake, an improvement, or a question — but want the human to decide. The suggestion appears as a bold "SUGGESTION:"...
Risk signalsHandles credentials or secrets (token)
Part of the Trident server.
Free to start. No card required.
AI agents call make_suggestion to retrieve information from Trident without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though make_suggestion only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
{
"version": "1",
"default": "deny",
"tools": {
"make_suggestion": {}
}
}See the full Trident policy for all 22 tools.
These attack patterns abuse exactly the kind of access make_suggestion gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
Posts a visible suggestion to human collaborators watching the document WITHOUT making any changes to the diagram. Use this when you observe something worth flagging — a potential mistake, an improvement, or a question — but want the human to decide. The suggestion appears as a bold "SUGGESTION:" callout in the UI with a radar pulse animation on your presence dot for 10 seconds. Does NOT mutate the diagram. Requires a valid viewer or editor access token.. It is categorised as a Read tool in the Trident MCP Server, which means it retrieves data without modifying state.
Register the Trident MCP server in PolicyLayer and add a rule for make_suggestion: 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 Trident. Nothing to install.
make_suggestion 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 make_suggestion 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 make_suggestion. 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.
make_suggestion is provided by the Trident MCP server (trident-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 22 Trident tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.