get_attribution
AI agents call get_attribution to retrieve information from Northbeam MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Attribution data retrieval is a read-only query operation that retrieves historical marketing attribution metrics without modifying, executing, or deleting data. The empty description and naming convention are consistent with other read tools on this analytics server. Low severity due to no side effects or blast radius from misuse.
From the tool's definition Tool name 'get_attribution' follows the read pattern 'get_*'; server description indicates 'querying' and 'attribution data' access; sibling tools are all read operations (get_*, list_*) with no mutation capability.
Attacks that exploit this kind of access
get_attribution. It is categorised as a Read tool in the Northbeam MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Northbeam MCP Server MCP server in PolicyLayer and add a rule for get_attribution: 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 Northbeam MCP Server. Nothing to install.
get_attribution 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_attribution 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_attribution. 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_attribution is provided by the Northbeam MCP Server MCP server (mattcoatsworth/northbeam-mcp-server). 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 →