// SCAN REPORT

Http Client

6 tools. 5 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated: 30 Jun 2026

5 can modify or destroy data

1 read-only

6 tools total

Community server · catalogue entry verified 30/06/2026

How to control Http Client ↓

TOOL MAP

What Http Client exposes to your agents

Read (1) Write / Execute (4) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Http Client tools

Destructive · High http_delete HTTP DELETE requests are designed to delete resources on remote servers. Execute · Critical http_request The tool description is empty, so the exact behavior is unknown. Write · High http_patch PATCH semantics indicate partial modification of a resource (Write category). Write · High http_post HTTP POST is fundamentally a Write operation—it sends data to a server to create or update resources.

5 of Http Client's 6 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Http Client

PolicyLayer is an MCP gateway — it sits between your AI agents and Http Client, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "http_delete": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "http_patch": {
    "limits": [
      {
        "counter": "http_patch_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "http_get": {
    "limits": [
      {
        "counter": "http_get_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Http Client — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON HTTP CLIENT →

Instant setup, no code required.

FULL CATALOGUE

All 6 Http Client tools

DESTRUCTIVE 1 tools

Destructive http_delete Make a DELETE request (convenience method).

EXECUTE 1 tools

Execute http_request http_request

WRITE 3 tools

Write http_patch http_patch Write http_post http_post Write http_put http_put

READ 1 tools

Read http_get Make a GET request (convenience method).

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Http Client

Can an AI agent delete data through the Http Client MCP server? +

Yes. The Http Client server exposes 1 destructive tools including http_delete. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Http Client? +

The Http Client server has 3 write tools including http_patch, http_post, http_put. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Http Client.

How many tools does the Http Client MCP server expose? +

6 tools across 3 categories: Destructive, Read, Write. 1 are read-only. 5 can modify, create, or delete data.

How do I enforce a policy on Http Client? +

Register the Http Client MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Http Client tool call.

Deterministic rules across all 6 Http Client tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON HTTP CLIENT →

Instant setup, no code required.

6 Http Client tools catalogued and risk-classified — across an index of 43,000+ MCP servers.