Run an exported tool from the mcpGraph. Can specify existing tool name or run a tool definition supplied in payload.
AI agents invoke runGraphTool to trigger actions in mcpGraph. 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.
This tool runs tool definitions whose behavior is determined by external input (payload). The ability to execute 'a tool definition supplied in payload' means an AI agent could be induced to execute malicious tool definitions.
From the tool's definition 'Run an exported tool from the mcpGraph' with ability to 'specify existing tool name or run a tool definition supplied in payload' — this executes arbitrary tool definitions with externally-supplied payloads, triggering operations whose effects depend on the…
Documented attack patterns abuse exactly the kind of access runGraphTool gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and mcpGraph, and nothing reaches the server without passing your rules. This is the rule we recommend for runGraphTool:
{
"version": "1",
"default": "deny",
"tools": {
"runGraphTool": {
"limits": [
{
"counter": "rungraphtool_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}runGraphTool 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 exported tool from the mcpGraph. Can specify existing tool name or run a tool definition supplied in payload. It is categorised as a Execute tool in the mcpGraph MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the mcpGraph MCP server in PolicyLayer and add a rule for runGraphTool: 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 mcpGraph. Nothing to install.
runGraphTool 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 runGraphTool 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 runGraphTool. 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.
runGraphTool is provided by the mcpGraph MCP server (teamsparkai/mcpgraph). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from mcpGraph, 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 mcpGraph tools catalogued and risk-classified — across an index of 43,000+ MCP servers.