Skip to main content
Press slash or control plus K to focus the search. Use the arrow keys to navigate results and press enter to open a threat.
Reconnecting to live updates…
EPSS 0.5%top 61%

CVE-2026-49291: CWE-862: Missing Authorization in doobidoo mcp-memory-service

0
High
VulnerabilityCVE-2026-49291cvecve-2026-49291cwe-862
Published: 06/19/2026 (06/19/2026, 17:59:48 UTC)
Source: CVE Database V5
Vendor/Project: doobidoo
Product: mcp-memory-service

Description

mcp-memory-service is a semantic memory layer for AI applications. Prior to version 10.65.3, the HTTP MCP JSON-RPC endpoint at `/mcp` requires only OAuth `read` scope for all requests, then dispatches `tools/call` directly to handlers that include mutating tools. A read-only OAuth client can call `store_memory` and `delete_memory` through MCP even though the corresponding REST endpoints require `write` scope. Version 10.65.3 patches the issue.

CVSS v3.1

Score 8.1high

Attack Vector
Network
Attack Complexity
Low
Privileges Required
Low
User Interaction
None
Scope
Unchanged
Confidentiality
None
Integrity
High
Availability
High
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:H/A:H

Affected software

mcp-memory-service
pkg:pypi/mcp-memory-service
Affected versions
<10.65.3

Run on your own infrastructure? Check whether these packages are installed with threat-finder — our free open-source scanner.

AI-Powered Analysis

Machine-generated threat intelligence

AILast updated: 06/26/2026, 19:20:09 UTC

Technical Analysis

CVE-2026-49291 is a missing authorization vulnerability (CWE-862) in doobidoo's mcp-memory-service. Before version 10.65.3, the /mcp JSON-RPC endpoint requires only OAuth read scope for all requests but dispatches calls to mutating handlers like store_memory and delete_memory. These operations should require OAuth write scope, but the insufficient authorization allows read-only clients to perform write operations. The vulnerability is fixed in version 10.65.3.

Potential Impact

An attacker with OAuth read scope can perform unauthorized write operations such as storing or deleting memory via the MCP JSON-RPC endpoint. This leads to integrity and availability impacts on the semantic memory layer, potentially disrupting AI application behavior. Confidentiality is not impacted.

Mitigation Recommendations

Upgrade to version 10.65.3 or later, where the authorization checks are corrected to require write scope for mutating operations. No other mitigation is indicated. Patch status is not explicitly confirmed but the description states version 10.65.3 patches the issue.

Pro Console: star threats, build custom feeds, automate alerts via Slack, email & webhooks.Upgrade to Pro

Technical Details

Data Version
5.2
Assigner Short Name
GitHub_M
Date Reserved
2026-05-28T20:07:58.862Z
Cvss Version
3.1
State
PUBLISHED
Remediation Level
null

Threat ID: 6a358c5cf198dc38c1f2fbb0

Added to database: 06/19/2026, 18:37:16 UTC

Last enriched: 06/26/2026, 19:20:09 UTC

Last updated: 08/03/2026, 19:18:00 UTC

Views: 125

Community Reviews

0 reviews

Crowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.

Sort by
Loading community insights…

Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.

Actions

PRO

Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.

Please log in to the Console to use AI analysis features.

Need more coverage?

Upgrade to Pro Console for AI refresh and higher limits.

For incident response and remediation, OffSeq services can help resolve threats faster.

Latest Threats

Breach by OffSeqOFFSEQFRIENDS — 25% OFF

Check if your credentials are on the dark web

Instant breach scanning across billions of leaked records. Free tier available.

Scan now
OffSeq TrainingCredly Certified

Lead Pen Test Professional

Technical5-day eLearningPECB Accredited
View courses