AI agents invoke run_report to trigger actions in ERPNext 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.
While the tool name 'run_report' might superficially suggest a read operation, ERPNext reports are executable procedures that can trigger calculations, generate data, invoke custom scripts, or execute database queries with effects dependent on parameters. An AI agent misusing this tool could trigger unintended business operations, data transformations, or resource-intensive processes.
From the tool's definition Tool named 'run_report' that 'Run[s] an ERPNext report' — reports in ERPNext can execute arbitrary queries, scripts, or business logic with side effects determined by report configuration and arguments, making this an execution action rather than a simple…
Documented attack patterns abuse exactly the kind of access run_report gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and ERPNext MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for run_report:
{
"version": "1",
"default": "deny",
"tools": {
"run_report": {
"limits": [
{
"counter": "run_report_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
} run_report 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.
Run an ERPNext report. It is categorised as a Execute tool in the ERPNext MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the ERPNext MCP Server MCP server in PolicyLayer and add a rule for run_report: 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 ERPNext MCP Server. Nothing to install.
run_report 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 run_report 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 run_report. 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.
run_report is provided by the ERPNext MCP Server MCP server (rakeshgangwar/erpnext-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 11 ERPNext MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
11 ERPNext MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.