http_repeater

Send a crafted request (Burp Repeater equivalent). request_spec keys: url, method, headers, cookies, data.

SERVERPengstrike SOURCEwangqiongpeng/pengstrike-mcp

High RISK CLASS

Category Execute

Parameters 00 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/pengstrike-mcp/http-repeater.md

WHAT IT DOES

What http_repeater does on Pengstrike

AI agents invoke http_repeater to trigger actions in Pengstrike. 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.

RISK

Why http_repeater is rated High

This tool sends arbitrary HTTP requests to external targets with full control over URL, method, headers, cookies, and body data — equivalent to Burp Suite's Repeater. It triggers real external operations whose effects depend entirely on the arguments provided (e.g., could POST data, trigger state changes, probe authenticated endpoints).

From the tool's definition Send a crafted request (Burp Repeater equivalent). request_spec keys: url, method, headers, cookies, data.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs http_repeater safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Pengstrike, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For http_repeater, this is the rule to start with:

http_repeater Rate-limited

http_repeater 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "http_repeater": {
      "limits": [
        {
          "counter": "http_repeater_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Pengstrike, apply this rule, and every http_repeater call is checked against it from then on.

FAQ

Questions about http_repeater

What does the http_repeater tool do? +

Send a crafted request (Burp Repeater equivalent). request_spec keys: url, method, headers, cookies, data. It is categorised as a Execute tool in the Pengstrike MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on http_repeater? +

Register the Pengstrike MCP server in PolicyLayer and add a rule for http_repeater: 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 Pengstrike. Nothing to install.

What risk level is http_repeater? +

http_repeater is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit http_repeater? +

Yes. Add a rate_limit block to the http_repeater 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.

How do I block http_repeater completely? +

Set action: deny in the PolicyLayer policy for http_repeater. 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.

What MCP server provides http_repeater? +

http_repeater is provided by the Pengstrike MCP server (wangqiongpeng/pengstrike-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Pengstrike, and thousands of servers like it.

This server

All 163 Pengstrike tools → High-risk tools on this server →

Across the catalogue

http_request on 0sec → All high-risk MCP tools → The MCP Attack Database →

Guides

Govern code and CI agents →Agent sandbox →Least privilege for MCP →