Take a screenshot of the current Fidelity browser page. Useful for debugging when tools return unexpected results.
AI agents call fidelity_screenshot to retrieve information from Claude Fidelity without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
While this tool operates in a financial context (Fidelity brokerage), it performs only a read operation—capturing the current visual state of a web page. It has no ability to modify accounts, execute trades, or move money. The blast radius is minimal: screenshots reveal account information but cannot directly harm financial positions.
From the tool's definition The tool 'takes a screenshot of the current Fidelity browser page' for 'debugging when tools return unexpected results.' Screenshots capture visual state without modifying data or executing transactions.
Attacks that exploit this kind of access
Take a screenshot of the current Fidelity browser page. Useful for debugging when tools return unexpected results. It is categorised as a Read tool in the Claude Fidelity MCP Server, which means it retrieves data without modifying state.
Register the Claude Fidelity MCP server in PolicyLayer and add a rule for fidelity_screenshot: 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 Fidelity. Nothing to install.
fidelity_screenshot 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 fidelity_screenshot 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 fidelity_screenshot. 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.
fidelity_screenshot is provided by the Claude Fidelity MCP server (tylerflar/claude-fidelity-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 →