ap_http

Test an HTTP GET from an AP's perspective (async, polls ~60s). timeout: 1-10s.

SERVERAPI-Central SOURCEsecure-ssid/centralmcp

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/secure-ssid-centralmcp/ap-http.md

WHAT IT DOES

What ap_http does on API-Central

AI agents invoke ap_http to trigger actions in API-Central. 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 ap_http is rated High

This tool triggers an active network operation — an HTTP GET request originating from an access point — which constitutes executing an external network action. It is not merely reading existing data; it initiates a real network transaction. The async polling behavior and timeout parameter further confirm active execution.

From the tool's definition 'Test an HTTP GET from an AP's perspective (async, polls ~60s)'

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs ap_http safely

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

ap_http Rate-limited

ap_http 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": {
    "ap_http": {
      "limits": [
        {
          "counter": "ap_http_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 API-Central, apply this rule, and every ap_http call is checked against it from then on.

FAQ

Questions about ap_http

What does the ap_http tool do? +

Test an HTTP GET from an AP's perspective (async, polls ~60s). timeout: 1-10s. It is categorised as a Execute tool in the API-Central MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on ap_http? +

Register the API-Central MCP server in PolicyLayer and add a rule for ap_http: 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 API-Central. Nothing to install.

What risk level is ap_http? +

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

Can I rate-limit ap_http? +

Yes. Add a rate_limit block to the ap_http 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 ap_http completely? +

Set action: deny in the PolicyLayer policy for ap_http. 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 ap_http? +

ap_http is provided by the API-Central MCP server (secure-ssid/centralmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on API-Central, and thousands of servers like it.

This server

All 590 API-Central 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 →