AI agents call jsr_search_packages to retrieve information from JSR MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs a search query that retrieves package information from a public registry without modifying, deleting, or executing any code. This is a read-only operation with minimal blast radius if misused by an AI agent.
From the tool's definition Tool name 'jsr_search_packages' and description states it 'Search for packages in the JSR registry. Returns a list of packages matching the query.' This is a retrieval operation with no side effects.
Attacks that exploit this kind of access
Search for packages in the JSR registry. Returns a list of packages matching the query. It is categorised as a Read tool in the JSR MCP MCP Server, which means it retrieves data without modifying state.
Register the JSR MCP server in PolicyLayer and add a rule for jsr_search_packages: 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 JSR MCP. Nothing to install.
jsr_search_packages 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 jsr_search_packages 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 jsr_search_packages. 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.
jsr_search_packages is provided by the JSR MCP server (wyattjoh/jsr-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 →