Retrieve a blob from Walrus storage
AI agents call get_blob to retrieve information from Walrus MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves data from decentralized storage by blob ID. Retrieval operations have no side effects on the stored data—they do not create, modify, or delete content. The blast radius of misuse is minimal; an attacker with access could only read data they specify, not modify or delete it. Low severity reflects the read-only nature and lack of irreversibility.
From the tool's definition Tool name 'get_blob' and description 'Retrieve a blob from Walrus storage' indicate data retrieval without modification.
Attacks that exploit this kind of access
Retrieve a blob from Walrus storage. It is categorised as a Read tool in the Walrus MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Walrus MCP Server MCP server in PolicyLayer and add a rule for get_blob: 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 Walrus MCP Server. Nothing to install.
get_blob 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_blob 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_blob. 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_blob is provided by the Walrus MCP Server MCP server (motion-labs-sui/walrus-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 →