Look up a well-known Solana program by its address
AI agents call identify_program to retrieve information from Solana 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 information about a Solana program from a lookup table or registry based on an address parameter. It is a read-only operation that queries data without modifying state, executing code, or causing financial impact. The blast radius of misuse is minimal—returning incorrect or stale program identification data would inform an agent but not cause direct harm.
From the tool's definition Tool name 'identify_program' and description 'Look up a well-known Solana program by its address' indicate a query/lookup operation with no side effects.
Attacks that exploit this kind of access
Look up a well-known Solana program by its address. It is categorised as a Read tool in the Solana MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Solana MCP Server MCP server in PolicyLayer and add a rule for identify_program: 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 Solana MCP Server. Nothing to install.
identify_program 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 identify_program 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 identify_program. 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.
identify_program is provided by the Solana MCP Server MCP server (visioneth/solana-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 →