This record as markdown: /tools/sqcows-forgejo-mcp/list-following.md
What list_following does on Forgejo
AI agents call list_following to retrieve information from Forgejo without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why list_following is rated Low
This is a pure read operation that queries and returns information about a user's following list. It does not create, modify, delete, or execute any actions. The blast radius of misuse is minimal—an AI agent could enumerate user follow relationships but cannot cause harm, financial loss, or irreversible changes. Low severity is appropriate for read-only social graph queries.
From the tool's definition Tool name is 'list_following' and description states it 'List who a user is following' — this retrieves/queries user follow relationship data with no side effects.
Attacks that exploit this kind of access
The rule that runs list_following safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Forgejo, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For list_following, this is the rule to start with:
list_following is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Forgejo, apply this rule, and every list_following call is checked against it from then on.
Questions about list_following
List who a user is following. It is categorised as a Read tool in the Forgejo MCP Server, which means it retrieves data without modifying state.
Register the Forgejo MCP server in PolicyLayer and add a rule for list_following: 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 Forgejo. Nothing to install.
list_following 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_following 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_following. 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_following is provided by the Forgejo MCP server (sqcows/forgejo-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Forgejo, and thousands of servers like it.
This server
Across the catalogue