List all Fidelity accounts with their names, numbers, and optionally withdrawal balances.
AI agents call fidelity_get_accounts 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.
The tool itself performs a read-only operation (listing account information), which normally maps to the Read category with low severity. However, the context is critical: this is a financial account management system integrated with Fidelity Investments.
From the tool's definition Tool description states 'List all Fidelity accounts' — a retrieval operation with no modification. However, the sibling tools include financial operations like 'fidelity_place_order' and 'fidelity_batch_orders', indicating this server manages real brokerage…
Attacks that exploit this kind of access
List all Fidelity accounts with their names, numbers, and optionally withdrawal balances. 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_get_accounts: 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_get_accounts 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_get_accounts 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_get_accounts. 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_get_accounts 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 →