AI agents call socheli_get_item to retrieve information from Socheli without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries existing content metadata without creating, modifying, deleting, or executing operations. It has no side effects and fits the Read category definition of retrieving data. Severity is low because information disclosure about content items poses minimal risk in a content management context.
From the tool's definition Tool description explicitly states 'Get the full detail of one content item by id' with retrieval of read-only fields (idea, script, storyboard, package, video URL, publish state).
Attacks that exploit this kind of access
Get the full detail of one content item by id (idea, script, storyboard, package, video URL, publish state). It is categorised as a Read tool in the Socheli MCP Server, which means it retrieves data without modifying state.
Register the Socheli MCP server in PolicyLayer and add a rule for socheli_get_item: 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 Socheli. Nothing to install.
socheli_get_item 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 socheli_get_item 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 socheli_get_item. 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.
socheli_get_item is provided by the Socheli MCP server (socheli/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →