CVE-2026-50027 (GCVE-0-2026-50027)
Vulnerability from cvelistv5 – Published: 2026-08-14 18:52 – Updated: 2026-08-17 16:08
VLAI
EPSS
VEX
Title
mcp-memory-service: Missing Authentication on Document API Endpoints Allows Unauthenticated Memory Read/Write/Delete
Summary
mcp-memory-service is a semantic memory layer for AI applications. Prior to 10.67.1, all HTTP routes under /api/documents/* in mcp-memory-service are served without any authentication dependency, even when the server is configured with an API key (MCP_API_KEY) or OAuth. An unauthenticated remote attacker can upload arbitrary content into the memory store (write), retrieve stored document content (read), and permanently delete memories belonging to authenticated users (delete) — all without supplying any credentials. The /api/memories counterpart correctly enforces authentication, making this an inconsistent and exploitable authentication boundary. This vulnerability is fixed in 10.67.1.
Severity
9.8 (Critical)
SSVC
Exploitation: none
Automatable: yes
Technical Impact: total
CISA Coordinator · CISA-ADP (v2.0.3)
Decision recorded 2026-08-17 15:24 UTC
CWE
- CWE-306 - Missing Authentication for Critical Function
Assigner
References
3 references
| URL | Tags |
|---|---|
| https://web.archive.org/web/20260508112116/https:… | x_refsource_CONFIRM |
| https://github.com/advisories/GHSA-84hp-mqvj-3p8h | x_refsource_MISC |
| https://pypi.org/project/mcp-memory-service | x_refsource_MISC |
Impacted products
1 product
| Vendor | Product | Version | CPE status | |
|---|---|---|---|---|
| doobidoo | mcp-memory-service |
Affected:
< 10.67.1
|
guessed |
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-50027",
"options": [
{
"Exploitation": "none"
},
{
"Automatable": "yes"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-08-17T15:24:28.617436Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-08-17T16:08:00.980Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "mcp-memory-service",
"vendor": "doobidoo",
"versions": [
{
"status": "affected",
"version": "\u003c 10.67.1"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "mcp-memory-service is a semantic memory layer for AI applications. Prior to 10.67.1, all HTTP routes under /api/documents/* in mcp-memory-service are served without any authentication dependency, even when the server is configured with an API key (MCP_API_KEY) or OAuth. An unauthenticated remote attacker can upload arbitrary content into the memory store (write), retrieve stored document content (read), and permanently delete memories belonging to authenticated users (delete) \u2014 all without supplying any credentials. The /api/memories counterpart correctly enforces authentication, making this an inconsistent and exploitable authentication boundary. This vulnerability is fixed in 10.67.1."
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "HIGH",
"baseScore": 9.8,
"baseSeverity": "CRITICAL",
"confidentialityImpact": "HIGH",
"integrityImpact": "HIGH",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H",
"version": "3.1"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-306",
"description": "CWE-306: Missing Authentication for Critical Function",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-08-14T18:52:47.309Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://web.archive.org/web/20260508112116/https://github.com/doobidoo/mcp-memory-service",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://web.archive.org/web/20260508112116/https://github.com/doobidoo/mcp-memory-service"
},
{
"name": "https://github.com/advisories/GHSA-84hp-mqvj-3p8h",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/advisories/GHSA-84hp-mqvj-3p8h"
},
{
"name": "https://pypi.org/project/mcp-memory-service",
"tags": [
"x_refsource_MISC"
],
"url": "https://pypi.org/project/mcp-memory-service"
}
],
"source": {
"advisory": "GHSA-84hp-mqvj-3p8h",
"discovery": "UNKNOWN"
},
"title": "mcp-memory-service: Missing Authentication on Document API Endpoints Allows Unauthenticated Memory Read/Write/Delete"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-50027",
"datePublished": "2026-08-14T18:52:47.309Z",
"dateReserved": "2026-06-02T22:46:02.580Z",
"dateUpdated": "2026-08-17T16:08:00.980Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2",
"vulnerability-lookup:meta": {
"epss": {
"cve": "CVE-2026-50027",
"date": "2026-08-18",
"epss": "0.00503",
"percentile": "0.40716"
},
"nvd": "{\"cve\":{\"id\":\"CVE-2026-50027\",\"sourceIdentifier\":\"security-advisories@github.com\",\"published\":\"2026-08-14T19:17:18.843\",\"lastModified\":\"2026-08-17T16:16:57.720\",\"vulnStatus\":\"Received\",\"cveTags\":[],\"descriptions\":[{\"lang\":\"en\",\"value\":\"mcp-memory-service is a semantic memory layer for AI applications. Prior to 10.67.1, all HTTP routes under /api/documents/* in mcp-memory-service are served without any authentication dependency, even when the server is configured with an API key (MCP_API_KEY) or OAuth. An unauthenticated remote attacker can upload arbitrary content into the memory store (write), retrieve stored document content (read), and permanently delete memories belonging to authenticated users (delete) \u2014 all without supplying any credentials. The /api/memories counterpart correctly enforces authentication, making this an inconsistent and exploitable authentication boundary. This vulnerability is fixed in 10.67.1.\"}],\"affected\":[{\"source\":\"security-advisories@github.com\",\"affectedData\":[{\"vendor\":\"doobidoo\",\"product\":\"mcp-memory-service\",\"versions\":[{\"version\":\"\u003c 10.67.1\",\"status\":\"affected\"}]}]}],\"metrics\":{\"cvssMetricV31\":[{\"source\":\"security-advisories@github.com\",\"type\":\"Secondary\",\"cvssData\":{\"version\":\"3.1\",\"vectorString\":\"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H\",\"baseScore\":9.8,\"baseSeverity\":\"CRITICAL\",\"attackVector\":\"NETWORK\",\"attackComplexity\":\"LOW\",\"privilegesRequired\":\"NONE\",\"userInteraction\":\"NONE\",\"scope\":\"UNCHANGED\",\"confidentialityImpact\":\"HIGH\",\"integrityImpact\":\"HIGH\",\"availabilityImpact\":\"HIGH\"},\"exploitabilityScore\":3.9,\"impactScore\":5.9}],\"ssvcV203\":[{\"source\":\"134c704f-9b21-4f2e-91b3-4a467353bcc0\",\"ssvcData\":{\"timestamp\":\"2026-08-17T15:24:28.617436Z\",\"id\":\"CVE-2026-50027\",\"options\":[{\"exploitation\":\"none\"},{\"automatable\":\"yes\"},{\"technicalImpact\":\"total\"}],\"role\":\"CISA Coordinator\",\"version\":\"2.0.3\"}}]},\"weaknesses\":[{\"source\":\"security-advisories@github.com\",\"type\":\"Secondary\",\"description\":[{\"lang\":\"en\",\"value\":\"CWE-306\"}]}],\"references\":[{\"url\":\"https://github.com/advisories/GHSA-84hp-mqvj-3p8h\",\"source\":\"security-advisories@github.com\"},{\"url\":\"https://pypi.org/project/mcp-memory-service\",\"source\":\"security-advisories@github.com\"},{\"url\":\"https://web.archive.org/web/20260508112116/https://github.com/doobidoo/mcp-memory-service\",\"source\":\"security-advisories@github.com\"}]}}"
}
}
Loading…
Loading…
Experimental. This forecast is provided for visualization only and may change without notice. Do not use it for operational decisions.
Forecast uses a logistic model when the trend is rising, or an exponential decay model when the trend is falling. Fitted via linearized least squares.
Sightings
| Author | Source | Type | Date | Other |
|---|
Nomenclature
- Seen: The vulnerability was mentioned, discussed, or observed by the user.
- Confirmed: The vulnerability has been validated from an analyst's perspective.
- Published Proof of Concept: A public proof of concept is available for this vulnerability.
- Exploited: The vulnerability was observed as exploited by the user who reported the sighting.
- Patched: The vulnerability was observed as successfully patched by the user who reported the sighting.
- Not exploited: The vulnerability was not observed as exploited by the user who reported the sighting.
- Not confirmed: The user expressed doubt about the validity of the vulnerability.
- Not patched: The vulnerability was not observed as successfully patched by the user who reported the sighting.
Loading…
The MITRE ATT&CK techniques below are AI-generated suggestions, inferred from the description of the
vulnerability by the CIRCL/vulnerability-attack-technique-classification-roberta-base
model, served locally by ML-Gateway.
They have not been verified by an analyst and are provided for guidance only.
The approach is described in our paper Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion.
The approach is described in our paper Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion.
Loading…
Loading…