Explore APIs, databases, and file servers, verify authentication, test endpoints, and examine response formats. Load the relevant protocol skill first. Only call ONE AT A TIME. Auth is always explicit — include headers for HTTP or embed credentials in the connection URL for databases/Redis/file s...
AI agents invoke call_system to trigger actions in Superglue 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.
This tool executes real calls against external APIs, databases, and file servers. It can trigger arbitrary external operations depending on arguments, including authenticated requests with embedded credentials. The blast radius is high because it can reach production systems, databases, and file servers with supplied credentials, potentially causing unintended side effects across integrated systems.
From the tool's definition Explore APIs, databases, and file servers, verify authentication, test endpoints, and examine response formats... Auth is always explicit — include headers for HTTP or embed credentials in the connection URL for databases/Redis/file servers
Documented attack patterns abuse exactly the kind of access call_system 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 call_system:
{
"version": "1",
"default": "deny",
"tools": {
"call_system": {
"limits": [
{
"counter": "call_system_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}call_system 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.
Explore APIs, databases, and file servers, verify authentication, test endpoints, and examine response formats. Load the relevant protocol skill first. Only call ONE AT A TIME. Auth is always explicit — include headers for HTTP or embed credentials in the connection URL for databases/Redis/file servers. Supports <<systemId_credKey>> placeholders. In bodies, use file::<key>.raw/.extracted/.base64. Multipart/form-data auto-builds FormData from JSON objects. It is categorised as a Execute tool in the Superglue MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Superglue MCP server in PolicyLayer and add a rule for call_system: 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.
call_system 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 call_system 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 call_system. 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.
call_system 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.