Inspect specific parts of the current playground tool configuration and execution results in detail. Request all needed sections and steps in a single call — both accept multiple items. Unlike find_tool (which looks up saved tools by ID/query), this inspects the current draft in the playground.
AI agents call inspect_tool to retrieve information from Superglue MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and examines existing playground configuration and execution results. It has no side effects—it does not modify, create, delete, or trigger external operations. The explicit distinction from find_tool (lookup) combined with the focus on inspection of current state confirms this is a read-only diagnostic/inspection tool with minimal blast radius if misused.
From the tool's definition Tool description states it 'Inspect specific parts of the current playground tool configuration and execution results in detail' and explicitly contrasts with find_tool by noting it 'inspects the current draft in the playground.' The verbs 'inspect' and…
Documented attack patterns abuse exactly the kind of access inspect_tool gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Superglue MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for inspect_tool:
{
"version": "1",
"default": "deny",
"tools": {
"inspect_tool": {}
}
}inspect_tool is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Inspect specific parts of the current playground tool configuration and execution results in detail. Request all needed sections and steps in a single call — both accept multiple items. Unlike find_tool (which looks up saved tools by ID/query), this inspects the current draft in the playground. It is categorised as a Read tool in the Superglue MCP MCP Server, which means it retrieves data without modifying state.
Register the Superglue MCP server in PolicyLayer and add a rule for inspect_tool: 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 Superglue MCP. Nothing to install.
inspect_tool is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the inspect_tool 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 inspect_tool. 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.
inspect_tool is provided by the Superglue MCP server (superglue-ai/superglue). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 21 Superglue MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
21 Superglue MCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.