Analyze a Substreams package
AI agents call get_sink_config 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.
This tool retrieves and analyzes configuration data from Substreams packages without modifying, executing, or deleting anything. Analysis and inspection are non-destructive read operations. The low severity reflects that it only accesses metadata about packages in a public registry.
From the tool's definition Tool name 'get_sink_config' and description 'Analyze a Substreams package' indicate inspection/analysis of package configuration. The sibling tools (inspect_package, list_package_modules, search_substreams) are all read-only operations on a registry.
Attacks that exploit this kind of access
Analyze a Substreams package. 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 get_sink_config: 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.
get_sink_config 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_sink_config 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_sink_config. 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_sink_config 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 →