AI agents invoke start_dsp to trigger actions in Pure Data MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Starting DSP processing executes active signal processing operations within Pure Data that produce real-time audio/signal effects. This is an Execute operation because it triggers external computational processes whose actual effects depend on the current patch configuration.
From the tool's definition Tool enables 'DSP processing' (digital signal processing) which involves executing audio/signal processing operations within Pure Data. DSP processing triggers computational operations with audio effects.
Documented attack patterns abuse exactly the kind of access start_dsp gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Pure Data MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for start_dsp:
{
"version": "1",
"default": "deny",
"tools": {
"start_dsp": {
"limits": [
{
"counter": "start_dsp_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}start_dsp stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Enable DSP processing in Pure Data. It is categorised as a Execute tool in the Pure Data MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Pure Data MCP Server MCP server in PolicyLayer and add a rule for start_dsp: 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 Pure Data MCP Server. Nothing to install.
start_dsp is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the start_dsp 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 start_dsp. 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.
start_dsp is provided by the Pure Data MCP Server MCP server (nikmaniatis/pd-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Pure Data MCP Server, 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.
11 Pure Data MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.