list_portcos
AI agents call list_portcos to retrieve information from northwood-carbon 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 or lists portfolio company data from a carbon emissions database. The 'list_' prefix is characteristic of read operations with no side effects. Even without an explicit description, the context of a portfolio carbon analytics platform indicates this enables queries rather than creates, modifies, or deletes data.
From the tool's definition Tool name 'list_portcos' indicates a listing/retrieval operation. Server description emphasizes querying portfolio carbon data, which is fundamentally a read-only operation.
Attacks that exploit this kind of access
list_portcos. It is categorised as a Read tool in the northwood-carbon MCP server MCP Server, which means it retrieves data without modifying state.
Register the northwood-carbon MCP server MCP server in PolicyLayer and add a rule for list_portcos: 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 northwood-carbon MCP server. Nothing to install.
list_portcos 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 list_portcos 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 list_portcos. 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.
list_portcos is provided by the northwood-carbon MCP server MCP server (trippborstel-hub/northwood-carbon-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 →