list_completions
AI agents call list_completions 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.
The tool name pattern 'list_*' typically indicates a read operation that queries and returns a list of items without side effects. While the description is empty, reducing confidence slightly, the semantic meaning of 'list_completions' strongly suggests data retrieval rather than modification, execution, or deletion.
From the tool's definition Tool name 'list_completions' suggests retrieval/enumeration of completion data with no modification. The 'list_' prefix is a strong indicator of read-only retrieval.
Attacks that exploit this kind of access
list_completions. 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_completions: 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_completions 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_completions 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_completions. 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_completions 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 →