---
id: CVE-2026-58483
title: >-
  mcp-searxng is a Model Context Protocol server that gives AI assistants web
  search and URL-reading capabilities through SearXNG
summary: >-
  mcp-searxng is a Model Context Protocol server that gives AI assistants web
  search and URL-reading capabilities through SearXNG. Prior to 1.7.1,
  web_url_read in src/index.ts passes a caller-supplied URL to readUrlContent()
  in src/url-rea…
severity: high
cvss: 7.5
cvssVector: 'CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H'
cwe:
  - CWE-400
vendor: ihor-sokoliuk
product: mcp-searxng
affected:
  - mcp-searxng < 1.7.1
published: '2026-09-15'
updated: '2026-09-15'
sourceUpdated: '2026-09-15T19:17:31.290'
source: NVD
sourceUrl: 'https://nvd.nist.gov/vuln/detail/CVE-2026-58483'
references:
  - url: >-
      https://github.com/ihor-sokoliuk/mcp-searxng/commit/f5a947ed1650daed10fbdcd53c0db5a86489ffe4
    label: security-advisories@github.com
  - url: 'https://github.com/ihor-sokoliuk/mcp-searxng/pull/121'
    label: security-advisories@github.com
  - url: 'https://github.com/ihor-sokoliuk/mcp-searxng/releases/tag/v1.7.1'
    label: security-advisories@github.com
  - url: >-
      https://github.com/ihor-sokoliuk/mcp-searxng/security/advisories/GHSA-xcqx-9jf5-w339
    label: security-advisories@github.com
  - url: >-
      https://github.com/ihor-sokoliuk/mcp-searxng/security/advisories/GHSA-xcqx-9jf5-w339
    label: 134c704f-9b21-4f2e-91b3-4a467353bcc0
tags:
  - nvd
  - cve.org
  - exploit-available
exploitAvailable: true
ssvc:
  exploitation: poc
  automatable: 'yes'
  technicalImpact: partial
  timestamp: '2026-09-15T18:22:16.482545Z'
ingestedAt: '2026-09-15T18:41:59.143Z'
epss: 0.0067
epssPercentile: 0.4997
---

## Overview

mcp-searxng is a Model Context Protocol server that gives AI assistants web search and URL-reading capabilities through SearXNG. Prior to 1.7.1, web_url_read in src/index.ts passes a caller-supplied URL to readUrlContent() in src/url-reader.ts, where checkContentLength() treats a missing Content-Length header as an inconclusive preflight and the normal and error paths then consume the complete body with response.text(). A server that omits Content-Length can therefore bypass URL_READ_MAX_CONTENT_LENGTH_BYTES and force unbounded memory use. The resulting string is also processed by NodeHtmlMarkdown.translate(), increasing CPU consumption and allowing an unauthenticated HTTP client to cause denial of service. This issue is fixed in version 1.7.1.

## Remediation

Refer to the linked advisories for vendor-supplied fixes and affected version ranges.