Is there a public PoC exploit available for CVE-2026-14748?

Yes, a public proof-of-concept exploit is available for CVE-2026-14748. Prioritise patching immediately. EPSS: 0.2%.

Awesome-MCP-Server CVE-2026-14748

Q: What is the CVSS score of CVE-2026-14748?

CVE-2026-14748 has a CVSS 4.0 base score of 2.1 (Low). CVSS vector: CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N/E:P/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X. EPSS exploitation probability: 0.2%.

EUVD-2026-41754 LOW

Server-Side Request Forgery (SSRF) (CWE-918)

2026-07-05 VulDB

GHSA-qq5h-499r-fxfj

SSRF Awesome Mcp Server

2.1

CVSS 4.0 · Vendor: VulDB

Severity by source

Vendor (VulDB) PRIMARY

2.1 MEDIUM

CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N/E:P/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X

vuln.today AI

6.3 MEDIUM

Network-reachable SSRF requiring low-privilege auth (PR:L per CVSS 4.0 vector); low C/I/A impact as SSRF enables partial internal access without full system compromise and no scope change.

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

4.0 AV:N/AC:L/AT:N/PR:L/UI:N/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N

Primary rating from Vendor (VulDB).

CVSS VectorVendor: VulDB

Attack Vector

Network

Attack Complexity

Low

Privileges Required

Low

User Interaction

None

Scope

Lifecycle Timeline

Severity Changed

Jul 05, 2026 - 13:22 NVD

MEDIUM LOW

CVSS changed

Jul 05, 2026 - 13:22 NVD

5.3 (MEDIUM) 2.1 (LOW)

Analysis Generated

Jul 05, 2026 - 13:03 vuln.today

DescriptionCVE.org

A flaw has been found in AIAnytime Awesome-MCP-Server up to a884bb51bcd99e08e14fd712c749d55d9d9a13ab. Affected by this issue is some unknown functionality of the file mcp-wiki/src/mcp_wiki/server.py of the component mcp-wiki/wiki-summary. This manipulation of the argument url causes server-side request forgery. The attack may be initiated remotely. The exploit has been published and may be used. This product uses a rolling release model to deliver continuous updates. As a result, specific version information for affected or updated releases is not available. The project was informed of the problem early through an issue report but has not responded yet.

AnalysisAI

Server-side request forgery in the mcp-wiki/wiki-summary component of AIAnytime Awesome-MCP-Server (up to commit a884bb51) allows a remote, low-privileged attacker to manipulate the url argument in mcp-wiki/src/mcp_wiki/server.py, causing the server to issue arbitrary HTTP requests to internal or external resources on the attacker's behalf. Successful exploitation can expose internal services, cloud metadata endpoints, or other backend infrastructure inaccessible from the public internet. A publicly available exploit exists (POC confirmed via GitHub issue #35); this CVE is not currently listed in CISA KEV. The CVSS 4.0 score of 5.3 reflects a moderate severity with low-privilege authentication required and partial confidentiality, integrity, and availability impact.

Technical ContextAI

AIAnytime Awesome-MCP-Server is an implementation of the Model Context Protocol (MCP), an open standard for connecting AI models to tools and data sources. The vulnerable component is the mcp-wiki module, specifically its wiki-summary feature, implemented in mcp-wiki/src/mcp_wiki/server.py. The CWE-918 root cause - Server-Side Request Forgery - arises when the application accepts a user-supplied url argument and passes it to an internal HTTP client without adequate validation or allowlisting. This enables the server to act as a proxy, forwarding requests to arbitrary destinations including RFC-1918 private addresses, loopback interfaces, or cloud-provider metadata services (e.g., AWS IMDSv1 at 169.254.169.254). Affected CPE: cpe:2.3:a:aianytime:awesome-mcp-server:*:*:*:*:*:*:*:*. Because the project uses a rolling release model, all commits up to a884bb51bcd99e08e14fd712c749d55d9d9a13ab are considered affected.

RemediationAI

No vendor-released patch identified at time of analysis - the project was notified via GitHub issue #34 but has not responded. Monitor https://github.com/AIAnytime/Awesome-MCP-Server/ for upstream commits addressing this issue. As an immediate compensating control, implement strict URL allowlisting in mcp-wiki/src/mcp_wiki/server.py to permit only known-safe external domains (e.g., wikipedia.org), rejecting all RFC-1918 addresses, loopback addresses, and cloud metadata IP ranges (169.254.169.254, fd00:ec2::254); this is the most targeted mitigation with minimal functional trade-off. If the wiki-summary feature is non-essential, disable or remove the mcp-wiki component entirely to eliminate the attack surface. Deploy the MCP server behind a network egress filter that blocks outbound requests to internal IP ranges, limiting the SSRF blast radius even if the application-layer fix is not yet applied - note this does not prevent SSRF against external targets. Restrict API access to authenticated, trusted principals to reduce exposure, consistent with the PR:L prerequisite already implied by the CVSS vector.