bridge_help
AI agents call bridge_help 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.
Without a description, confidence is moderate. However, 'help' tools universally retrieve documentation or usage information, which is a read operation with no side effects. No evidence suggests this modifies, executes, deletes, or moves data. The tool appears informational and safe.
From the tool's definition Tool named 'bridge_help' with an empty description suggests a help/documentation retrieval function. The naming pattern 'help' typically indicates informational access with no side effects.
Attacks that exploit this kind of access
bridge_help. 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 bridge_help: 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.
bridge_help 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 bridge_help 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 bridge_help. 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.
bridge_help 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 →