Execute a read-only contract call
AI agents call stbl_read to retrieve information from Stability MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Read-only contract calls retrieve data from the blockchain without creating, modifying, or deleting state. This falls squarely in the Read category. The term 'read-only' is unambiguous. Severity is low because querying blockchain state has minimal blast radius—no funds at risk, no data altered, no external operations triggered. High confidence because the description is explicit and clear.
From the tool's definition Tool name 'stbl_read' and description 'Execute a read-only contract call' explicitly indicate read-only semantics with no state modification.
Attacks that exploit this kind of access
Execute a read-only contract call. It is categorised as a Read tool in the Stability MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Stability MCP Server MCP server in PolicyLayer and add a rule for stbl_read: 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 Stability MCP Server. Nothing to install.
stbl_read 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 stbl_read 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 stbl_read. 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.
stbl_read is provided by the Stability MCP Server MCP server (nuljui/stbl-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 →