---
id: CVE-2026-54688
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 1.2.0,
  web_url_read passes a caller-supplied URL to the server-side fetch path while
  assertUrlAllow…
severity: medium
cvss: 6.5
cvssVector: 'CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:N/A:N'
cwe:
  - CWE-918
vendor: ihor-sokoliuk
product: mcp-searxng
affected:
  - mcp-searxng < 1.2.0
patched:
  - mcp-searxng 1.2.1
published: '2026-09-15'
updated: '2026-09-15'
sourceUpdated: '2026-09-15T19:17:20.583'
source: NVD
sourceUrl: 'https://nvd.nist.gov/vuln/detail/CVE-2026-54688'
references:
  - url: >-
      https://github.com/ihor-sokoliuk/mcp-searxng/commit/48e5ecdcb4166a60b94c252dbe74b0a318110ac4
    label: security-advisories@github.com
  - url: >-
      https://github.com/ihor-sokoliuk/mcp-searxng/issues/87#issuecomment-4645453694
    label: security-advisories@github.com
  - url: 'https://github.com/ihor-sokoliuk/mcp-searxng/releases/tag/v1.2.0'
    label: security-advisories@github.com
  - url: >-
      https://github.com/ihor-sokoliuk/mcp-searxng/security/advisories/GHSA-q87f-qc2r-2gw4
    label: security-advisories@github.com
  - url: >-
      https://github.com/ihor-sokoliuk/mcp-searxng/security/advisories/GHSA-q87f-qc2r-2gw4
    label: 134c704f-9b21-4f2e-91b3-4a467353bcc0
  - url: 'https://github.com/ihor-sokoliuk/mcp-searxng/releases/tag/v1.2.1'
  - url: 'https://github.com/advisories/GHSA-q87f-qc2r-2gw4'
tags:
  - nvd
  - cve.org
  - exploit-available
  - ghsa
  - npm
exploitAvailable: true
ssvc:
  exploitation: poc
  automatable: 'no'
  technicalImpact: partial
  timestamp: '2026-09-15T19:01:15.355649Z'
aliases:
  - GHSA-q87f-qc2r-2gw4
ecosystem: npm
ingestedAt: '2026-08-19T19:44:02.738Z'
epss: 0.00499
epssPercentile: 0.40208
---

## Overview

mcp-searxng is a Model Context Protocol server that gives AI assistants web search and URL-reading capabilities through SearXNG. Prior to 1.2.0, web_url_read passes a caller-supplied URL to the server-side fetch path while assertUrlAllowed() in src/url-reader.ts runs only when MCP_HTTP_HARDEN is enabled, even though MCP_HTTP_HARDEN is disabled by default in src/http-security.ts. In the default configuration, an attacker who influences the URL selected by a user or AI agent can make the server fetch loopback, private-network, or cloud metadata endpoint resources and return their contents into the model context. file:// URLs remain rejected, and the separate DNS-resolution and redirect-validation bypasses are outside this record. This issue is fixed in version 1.2.0.

## Remediation

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

## Package advisory (CVE-2026-54688)

Affected packages:

- `mcp-searxng < 1.2.1`

Patched in:

- `mcp-searxng 1.2.1`

Source: https://github.com/advisories/GHSA-q87f-qc2r-2gw4