Test an MCP tool call directly. Evaluates JSONata expressions in args if context is provided.
AI agents invoke testMcpTool 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 directly invokes MCP tool calls, which constitutes executing external operations. The ability to call arbitrary MCP tools with evaluated expressions means the blast radius depends on what tools are accessible — potentially spanning read, write, destructive, or financial actions depending on which tool is invoked. This makes it an Execute-category tool with high severity.
From the tool's definition 'Test an MCP tool call directly. Evaluates JSONata expressions in args if context is provided.'
Documented attack patterns abuse exactly the kind of access testMcpTool 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 testMcpTool:
{
"version": "1",
"default": "deny",
"tools": {
"testMcpTool": {
"limits": [
{
"counter": "testmcptool_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}testMcpTool 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.
Test an MCP tool call directly. Evaluates JSONata expressions in args if context is provided. 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 testMcpTool: 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.
testMcpTool 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 testMcpTool 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 testMcpTool. 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.
testMcpTool 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.