This record as markdown: /tools/io-github-dave-london-cargo/api.md
What api does on Cargo
AI agents invoke api to trigger actions in Cargo. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.
Why api is rated High
A tool that makes arbitrary GitHub API calls can span Read, Write, Destructive, and potentially other severe operations depending on the endpoint and method used. Since the tool is unrestricted ('arbitrary'), the most severe plausible category applies. GitHub API calls can modify repositories, delete branches, manage secrets, trigger workflows, etc.
From the tool's definition 'Makes arbitrary GitHub API calls via' — the description is truncated/incomplete, but 'arbitrary GitHub API calls' implies the tool can perform any GitHub API operation including writes, deletions, and administrative actions beyond simple reads.
Attacks that exploit this kind of access
The rule that runs api safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Cargo, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For api, this is the rule to start with:
api stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Cargo, apply this rule, and every api call is checked against it from then on.
Questions about api
Makes arbitrary GitHub API calls via. It is categorised as a Execute tool in the Cargo MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Cargo MCP server in PolicyLayer and add a rule for api: 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 Cargo. Nothing to install.
api is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the api 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 api. 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.
api is provided by the Cargo MCP server (Dave-London/Pare). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Cargo, and thousands of servers like it.
Across the catalogue