Enters or queries a Nix dev shell. When a command is provided, runs it inside the dev shell and returns the result.
AI agents invoke develop to trigger actions in Http. 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.
The tool explicitly runs user-provided commands inside a dev shell. This is code/command execution with broad potential impact depending on what commands are supplied. The blast radius is high since arbitrary commands can be executed in the shell environment, potentially affecting files, processes, and system state.
From the tool's definition 'runs it inside the dev shell and returns the result' — executes arbitrary commands within a Nix dev shell environment
Documented attack patterns abuse exactly the kind of access develop gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Http, and nothing reaches the server without passing your rules. This is the rule we recommend for develop:
{
"version": "1",
"default": "deny",
"tools": {
"develop": {
"limits": [
{
"counter": "develop_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}develop 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.
Free to start. No card required.
Enters or queries a Nix dev shell. When a command is provided, runs it inside the dev shell and returns the result. It is categorised as a Execute tool in the Http MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Http MCP server in PolicyLayer and add a rule for develop: 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 Http. Nothing to install.
develop 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 develop 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 develop. 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.
develop is provided by the Http MCP server (@paretools/http). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Http, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
202 Http tools catalogued and risk-classified — across an index of 43,000+ MCP servers.