search_substreams
AI agents call search_substreams to retrieve information from Substreams Search MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Searching a package registry is a retrieval operation with no side effects. The tool queries data without creating, modifying, deleting, or executing operations. Confidence is not higher due to empty tool description, but server and sibling tool context strongly support Read classification.
From the tool's definition Tool name 'search_substreams' combined with server description stating it 'lets AI agents search the substreams.dev package registry' indicates a search/query operation.
Attacks that exploit this kind of access
search_substreams. It is categorised as a Read tool in the Substreams Search MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Substreams Search MCP Server MCP server in PolicyLayer and add a rule for search_substreams: 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 Substreams Search MCP Server. Nothing to install.
search_substreams 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 search_substreams 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 search_substreams. 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.
search_substreams is provided by the Substreams Search MCP Server MCP server (paulieb14/substreams-search-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 →