Fetch a chunk by id
AI agents call get_rule to retrieve information from Stackpress Context Provider without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves documentation or configuration chunks by identifier from the Stackpress framework context provider. It performs a simple lookup/retrieval with no side effects, data modification, code execution, or destructive actions. The low severity reflects that fetching framework documentation poses minimal risk even if accessed inappropriately by an AI agent.
From the tool's definition Tool name 'get_rule' with description 'Fetch a chunk by id' indicates retrieval of data without modification or side effects. The verb 'Fetch' and the query-like pattern of retrieving by identifier are characteristic of Read operations.
Attacks that exploit this kind of access
Fetch a chunk by id. It is categorised as a Read tool in the Stackpress Context Provider MCP Server, which means it retrieves data without modifying state.
Register the Stackpress Context Provider MCP server in PolicyLayer and add a rule for get_rule: 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 Stackpress Context Provider. Nothing to install.
get_rule 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_rule 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_rule. 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_rule is provided by the Stackpress Context Provider MCP server (stackpress/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 →