CVE-2026-108395: CWE-770: Allocation of Resources Without Limits or Throttling in modelcontextprotocol io.modelcontextprotocol.sdk:mcp
Description
The Model Context Protocol Java SDK is the official Java SDK for Model Context Protocol servers and clients. From version 0.8.0 through 0.12.0 in the io.modelcontextprotocol.sdk:mcp artifact, from 0.13.0 through 0.18.3 and 1.0.0 through 1.1.3 in io.modelcontextprotocol.sdk:mcp-core, and from mcp-core 2.0.0-M1 through 2.0.0, the Servlet-based SSE, Streamable HTTP, and Stateless server transports read an HTTP request body into memory without enforcing a maximum size. An unauthenticated remote client able to reach an affected transport can stream an arbitrarily large POST body, including with chunked transfer encoding, until the Java process exhausts its heap and becomes unavailable. Authentication, Origin or Host validation, or an upstream request-size limit can reject the request before the vulnerable read. The maintained mcp-core lines are fixed in versions 0.18.4, 1.1.4, and 2.0.1.
CVSS v3.1
Score 7.5high
Affected software
modelcontextprotocol
io.modelcontextprotocol.sdk:mcp
modelcontextprotocol
io.modelcontextprotocol.sdk:mcp-core
pkg:maven/io.modelcontextprotocol.sdk/mcppkg:maven/io.modelcontextprotocol.sdk/mcp-coreRun on your own infrastructure? Check whether these packages are installed with threat-finder — our free open-source scanner.
Weaknesses
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
The Model Context Protocol Java SDK (artifact io.modelcontextprotocol.sdk:mcp) contains a resource allocation vulnerability (CWE-770) in its Servlet-based SSE, Streamable HTTP, and Stateless server transports. These components read HTTP request bodies into memory without enforcing maximum size limits, allowing unauthenticated remote clients to stream arbitrarily large POST bodies, including chunked transfer encoding. This can exhaust the Java process heap, causing denial of service. The vulnerability affects versions >=0.8.0 <0.13.0, >=0.13.0 <0.18.4, >=1.0.0 <1.1.4, and >=2.0.0-M1 <2.0.1. The issue is fixed in versions 0.18.4, 1.1.4, and 2.0.1. Authentication, origin or host validation, or upstream request-size limits can mitigate the risk by rejecting malicious requests before processing.
Potential Impact
An unauthenticated remote attacker can exploit this vulnerability by sending an arbitrarily large HTTP POST request to the affected server transports, causing the Java process to exhaust its heap memory and become unavailable. This results in a denial of service condition. There is no impact on confidentiality or integrity, only availability is affected.
Mitigation Recommendations
Fixed versions are available: 0.18.4, 1.1.4, and 2.0.1. Users should upgrade to these versions or later to remediate the vulnerability. Additionally, implementing authentication, origin or host validation, or upstream request-size limits can prevent malicious requests from reaching the vulnerable code. Patch status is confirmed fixed in the stated versions.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- GitHub_M
- Date Reserved
- 2026-10-09T21:36:27.043Z
- Cvss Version
- 3.1
- State
- PUBLISHED
Threat ID: 6acfc4752cdf04f6569de056
Added to database: 10/14/2026, 18:05:41 UTC
Last enriched: 10/14/2026, 18:18:24 UTC
Last updated: 10/14/2026, 19:49:17 UTC
Views: 10
Community Reviews
0 reviewsCrowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.
Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.
Actions
Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.
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
Check if your credentials are on the dark web
Instant breach scanning across billions of leaked records. Free tier available.