Open the OS file manager with the target file selected so user can drag/drop it into chat.
AI agents invoke reveal_file to trigger actions in ContextCore. 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 triggers an external OS-level operation (launching the file manager application and selecting a file), which constitutes executing an action with effects beyond the MCP server itself. It is not merely reading data — it actively opens a GUI application on the user's system. Misuse could involve revealing sensitive file paths or opening unexpected OS dialogs, hence medium severity.
From the tool's definition Open the OS file manager with the target file selected
Documented attack patterns abuse exactly the kind of access reveal_file gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and ContextCore, and nothing reaches the server without passing your rules. This is the rule we recommend for reveal_file:
{
"version": "1",
"default": "deny",
"tools": {
"reveal_file": {
"limits": [
{
"counter": "reveal_file_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}reveal_file 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.
Open the OS file manager with the target file selected so user can drag/drop it into chat. It is categorised as a Execute tool in the ContextCore MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the ContextCore MCP server in PolicyLayer and add a rule for reveal_file: 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 ContextCore. Nothing to install.
reveal_file 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 reveal_file 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 reveal_file. 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.
reveal_file is provided by the ContextCore MCP server (lucifer-ux/contextcore). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from ContextCore, 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.
16 ContextCore tools catalogued and risk-classified — across an index of 43,000+ MCP servers.