AI agents call get_symbol to retrieve information from Astllm without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves and queries source code by symbol ID without creating, modifying, deleting, executing, or initiating any financial transactions. It is purely a read operation. Severity is low because reading source code has minimal blast radius—the worst case is information disclosure of code that is typically already accessible via normal repository access.
From the tool's definition The tool description states it 'Get[s] the full source code of a specific symbol' and uses 'byte-offset seeking for O(1) retrieval.' This is a retrieval operation with no side effects.
Attacks that exploit this kind of access
Get the full source code of a specific symbol (function, class, method, etc.) by its ID. Uses byte-offset seeking for O(1) retrieval — much cheaper than reading the entire file. It is categorised as a Read tool in the Astllm MCP Server, which means it retrieves data without modifying state.
Register the Astllm MCP server in PolicyLayer and add a rule for get_symbol: 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 Astllm. Nothing to install.
get_symbol 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_symbol 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_symbol. 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_symbol is provided by the Astllm MCP server (tluyben/astllm-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 →