AI agents invoke soroban_deploy to trigger actions in Stellar MCP. 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.
While deployment itself may not directly move funds, it executes code whose side effects cannot be fully predicted without reviewing the contract contents. This is an Execute action because it triggers external operations (blockchain contract deployment) whose effects depend on the contract arguments provided.
From the tool's definition The tool is named 'soroban_deploy' and described as 'Deploy a Soroban contract'. Deploying a smart contract constitutes executing code on a blockchain network that will have persistent effects and potentially interact with financial systems (as evidenced by…
Documented attack patterns abuse exactly the kind of access soroban_deploy gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Stellar MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for soroban_deploy:
{
"version": "1",
"default": "deny",
"tools": {
"soroban_deploy": {
"limits": [
{
"counter": "soroban_deploy_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}soroban_deploy 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.
Deploy a Soroban contract. It is categorised as a Execute tool in the Stellar MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Stellar MCP server in PolicyLayer and add a rule for soroban_deploy: 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 Stellar MCP. Nothing to install.
soroban_deploy 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 soroban_deploy 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 soroban_deploy. 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.
soroban_deploy is provided by the Stellar MCP server (syronlabs/stellar-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Stellar MCP, 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.
12 Stellar MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.