UTC
High

mcp-memory-service: OAuth read-only clients can write and delete memories through MCP tools/call

CVE-2026-49291 · GHSA-2r68-g678-7qr3 · published 2026-06-26

Severity
High
CVSS score
8.1
Chance of exploitation (EPSS)
0.49%
Fixed in
10.65.3
  • Exploitation No known exploitation
  • Automatable No
  • Technical impact Total
  • CISA SSVC
What it is

A client intended to be read-only can inject or delete memories through the MCP API. This can corrupt the memory database, influence future agent context, and destroy stored user memories without the OAuth write scope required by the REST API.

What to do

Upgrade mcp-memory-service to 10.65.3 or later. If you start it from an MCP config with npx or uvx, pin that version so an old cached copy is not used.

Enforce authorization per MCP tool at tools/call time. Require write for store_memory and delete_memory, keep read only for read-only tools, and add regression tests proving direct tools/call to mutating tools is rejected before the handler reaches storage when the caller has only read scope.

Affected
PackageRegistryAffectedFixed in
mcp-memory-servicePyPI<= 10.65.110.65.3

The impact, patch and workaround text comes from the advisory, shortened (GitHub Advisory Database, CC BY 4.0). Proof-of-concept and reproduction sections and code are left out; the original advisory has them.

Sources: GitHub Advisory Database, reviewed and malware advisories (CC BY 4.0, https://github.com/advisories); advisories published by Cursor (https://github.com/cursor/cursor/security/advisories); advisories published by OpenClaw (https://github.com/openclaw/openclaw/security/advisories); advisories published by vLLM (https://github.com/vllm-project/vllm/security/advisories); advisories published by Open WebUI (https://github.com/open-webui/open-webui/security/advisories); advisories published by n8n (https://github.com/n8n-io/n8n/security/advisories); advisories published by Flowise (https://github.com/FlowiseAI/Flowise/security/advisories); advisories published by Langflow (https://github.com/langflow-ai/langflow/security/advisories); advisories published by the MCP Python SDK project (https://github.com/modelcontextprotocol/python-sdk/security/advisories); advisories published by MLflow (https://github.com/mlflow/mlflow/security/advisories); CISA Known Exploited Vulnerabilities catalog (CC0). Data as of 2026-11-22. ShieldMap describes how each problem works and how to fix it; it does not publish exploit code. Report a correction to [email protected].