AI agents call socheli_jobs 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 queries and returns information about fleet jobs and their statuses. It performs no mutations, deletions, or side effects—purely a status/history inspection function. Classified as Read with low severity since it only surfaces non-sensitive operational metadata about job execution state.
From the tool's definition Tool name 'socheli_jobs' and description 'List recent fleet jobs and their status (dispatched/running/done/error) and which device ran them' indicates a read-only operation that retrieves job status and execution history without modifying, deleting, or…
Attacks that exploit this kind of access
List recent fleet jobs and their status (dispatched/running/done/error) and which device ran them. 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_jobs: 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_jobs 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_jobs 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_jobs. 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_jobs 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 →