AI agents invoke custom_rpc to trigger actions in Substrate 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.
A custom RPC call can trigger arbitrary operations on a Substrate blockchain node, including state-changing transactions, administrative functions, or other side-effecting operations depending on the arguments provided. The open-ended nature of 'custom' RPC means it could span read to destructive operations, so Execute is the most appropriate base category given the potential for arbitrary execution.
From the tool's definition "Make a custom RPC call" - executes arbitrary RPC calls against the Substrate node
Documented attack patterns abuse exactly the kind of access custom_rpc gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Substrate MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for custom_rpc:
{
"version": "1",
"default": "deny",
"tools": {
"custom_rpc": {
"limits": [
{
"counter": "custom_rpc_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}custom_rpc 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.
Make a custom RPC call. It is categorised as a Execute tool in the Substrate MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Substrate MCP Server MCP server in PolicyLayer and add a rule for custom_rpc: 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 Substrate MCP Server. Nothing to install.
custom_rpc 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 custom_rpc 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 custom_rpc. 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.
custom_rpc is provided by the Substrate MCP Server MCP server (thomasmarches/substrate-mcp-rs). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Substrate 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.
13 Substrate MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.