account_sign_data
AI agents invoke account_sign_data to trigger actions in NEAR 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.
Signing data with a blockchain account's private key is an Execute-level operation — it uses credentials to produce a cryptographic signature that can authorize transactions or messages. While not inherently destructive or financial on its own, misuse could enable unauthorized operations.
From the tool's definition Tool name 'account_sign_data' suggests cryptographic signing of arbitrary data using account credentials
Documented attack patterns abuse exactly the kind of access account_sign_data gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and NEAR MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for account_sign_data:
{
"version": "1",
"default": "deny",
"tools": {
"account_sign_data": {
"limits": [
{
"counter": "account_sign_data_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}account_sign_data 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.
account_sign_data. It is categorised as a Execute tool in the NEAR MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the NEAR MCP server in PolicyLayer and add a rule for account_sign_data: 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 NEAR MCP. Nothing to install.
account_sign_data 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 account_sign_data 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 account_sign_data. 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.
account_sign_data is provided by the NEAR MCP server (nearai/near-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from NEAR 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.
23 NEAR MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.