All tracked jobs (running and finished). raw is stripped from
AI agents call list_jobs to retrieve information from Claude Bridge without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and lists existing job state. It has no side effects, does not execute code, and does not modify data. The read-only nature and informational purpose classify it as a Read-category tool with low severity since an agent listing jobs cannot cause harm through this operation alone.
From the tool's definition Tool name 'list_jobs' and description indicating it retrieves 'All tracked jobs (running and finished)' - a pure retrieval/query operation with no modification or execution.
Attacks that exploit this kind of access
All tracked jobs (running and finished). raw is stripped from. It is categorised as a Read tool in the Claude Bridge MCP Server, which means it retrieves data without modifying state.
Register the Claude Bridge MCP server in PolicyLayer and add a rule for list_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 Claude Bridge. Nothing to install.
list_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 list_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 list_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.
list_jobs is provided by the Claude Bridge MCP server (josiahsiegel/claude-bridge). 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 →