Build a personalized crypto feed and continue it with a feed session cursor.
AI agents call get_personal_feed to retrieve information from Followin MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays personalized content from the Followin platform. The verbs 'build' and 'continue' refer to constructing a data view and paginating through results, which are read operations. There is no indication of data modification, deletion, code execution, financial transactions, or triggering external side effects.
From the tool's definition Tool description states 'Build a personalized crypto feed and continue it with a feed session cursor' - these are retrieval and pagination operations with no modification or execution of external operations.
Attacks that exploit this kind of access
Build a personalized crypto feed and continue it with a feed session cursor. It is categorised as a Read tool in the Followin MCP MCP Server, which means it retrieves data without modifying state.
Register the Followin MCP server in PolicyLayer and add a rule for get_personal_feed: 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 Followin MCP. Nothing to install.
get_personal_feed 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 get_personal_feed 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 get_personal_feed. 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.
get_personal_feed is provided by the Followin MCP server (qinshoudawang/crypto-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 →