Retrieve atlases available through the API (from OntologiesApi).
AI agents call get_atlases to retrieve information from Allen Brain API 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 returns a list of available atlases from the Allen Institute API. It performs a GET-like operation that retrieves metadata without creating, modifying, deleting, or executing any operations. The blast radius of misuse is minimal—an agent could at worst retrieve all available atlases repeatedly, causing minor API load.
From the tool's definition Tool name 'get_atlases' and description 'Retrieve atlases available through the API' indicate a data retrieval operation with no modification or execution of code.
Attacks that exploit this kind of access
Retrieve atlases available through the API (from OntologiesApi). It is categorised as a Read tool in the Allen Brain API MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Allen Brain API MCP Server MCP server in PolicyLayer and add a rule for get_atlases: 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 Allen Brain API MCP Server. Nothing to install.
get_atlases 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_atlases 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_atlases. 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_atlases is provided by the Allen Brain API MCP Server MCP server (maflot/allenbrain-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 →