AI agents use add_clue to create or update resources in DMCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your DMCP environment.
This tool creates or modifies game narrative data within an RPG context by appending a clue to a secret. This is a reversible write operation with no destructive capability, code execution, or financial impact. The blast radius is limited to the game state of a single RPG session, making it low severity.
From the tool's definition Tool name 'add_clue' with description 'Add a clue to a secret' indicates creation/modification of game state data (adding content to an existing game element).
Documented attack patterns abuse exactly the kind of access add_clue gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and DMCP, and nothing reaches the server without passing your rules. This is the rule we recommend for add_clue:
{
"version": "1",
"default": "deny",
"tools": {
"add_clue": {
"limits": [
{
"counter": "add_clue_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}add_clue 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.
Free to start. No card required.
Add a clue to a secret. It is categorised as a Write tool in the DMCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the D MCP server in PolicyLayer and add a rule for add_clue: 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 DMCP. Nothing to install.
add_clue 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 add_clue 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 add_clue. 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.
add_clue is provided by the D MCP server (shawnrushefsky/dmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from DMCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
204 DMCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.