AI agents call get_architecture to retrieve information from Synapse without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves architectural information from an indexed codebase graph without modifying, executing, or deleting anything. It appears designed to answer 'what does this codebase look like' questions rather than perform any side effects. The empty description prevents full certainty, but the server's read-only query purpose and naming convention support Read classification.
From the tool's definition Tool name 'get_architecture' combined with server purpose of providing 'structural insights' and 'query code architecture' indicates data retrieval.
Attacks that exploit this kind of access
get_architecture. It is categorised as a Read tool in the Synapse MCP Server, which means it retrieves data without modifying state.
Register the Synapse MCP server in PolicyLayer and add a rule for get_architecture: 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 Synapse. Nothing to install.
get_architecture 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_architecture 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_architecture. 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_architecture is provided by the Synapse MCP server (synappscodecomprehension/synapps). 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 →