Cyber Resilience

CVE-2026-27896

Lfprojects Mcp Go Sdk ≤ 1.3.1

Published
26 February 2026
Modified
15 July 2026
Patch / advisory
CVSS Score v4 7.0
Click a component to see what it means
Raw vectorCVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:N/VC:N/VI:N/VA:N/SC:H/SI:H/SA:N/E:X/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 Score 0.0026 17th percentile
Risk Priority 40 floored blend · peak EPSS

Summary

CVE-2026-27896 is a high-severity Improper Handling of Case Sensitivity (CWE-178) vulnerability in Lfprojects Mcp Go Sdk. Its CVSS base score is 7.0 (High).

Operationally, exploitation aligns with the MITRE ATT&CK technique Masquerading (T1036); ranked at the 17th percentile by exploit likelihood (below the median); it is not currently listed in the CISA KEV catalog.

This vulnerability is AI-related — categorised as AI Agent Protocols and Integrations; in the Protocol-Specific Risks risk domain.

The strongest mitigations our analysis identified map to SA-11 (Developer Testing and Evaluation) and SI-10 (Information Input Validation) — see the control section below for these in your framework.

Deeper analysis AI-assisted summary

Synthesised by an AI model from the NVD description and linked references — a reading aid, not an authoritative source.

CVE-2026-27896 is a vulnerability in the Go MCP SDK versions prior to 1.3.1, stemming from the use of Go's standard encoding/json.Unmarshal for parsing JSON-RPC and MCP protocol messages. This library performs case-insensitive matching of JSON keys to struct field tags, meaning a field tagged "json:\"method\"" would accept "Method", "METHOD", or similar variations. This violates the JSON-RPC 2.0 specification, which mandates exact field names, and is associated with CWE-178 (Improper Handling of Case Sensitivity) and CWE-436 (Interpretation Conflict).

A malicious MCP peer can exploit this over the network by sending protocol messages with non-standard field casing, which the SDK silently accepts. Attackers require no privileges or user interaction (CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:H/A:N, score 7.5), potentially bypassing intermediary inspection tools expecting strict JSON-RPC compliance and causing cross-implementation inconsistencies.

The vulnerability is fixed in SDK version 1.3.1 by replacing Go's standard JSON unmarshaling with a case-sensitive decoder, as detailed in commit 7b8d81c264074404abdf5aa16e2cf0c2d9c64cc0. Users should update to v1.3.1, with additional guidance in the GitHub security advisory at GHSA-wvj2-96wp-fq3f.

OWASP Top 10 for Web (2025)

EU & UK References

Vulnerability Data

The Go MCP SDK used Go's standard encoding/json.Unmarshal for JSON-RPC and MCP protocol message parsing in versions prior to 1.3.1. Go's standard library performs case-insensitive matching of JSON keys to struct field tags — a field tagged json:"method" would also…

more

match "Method", "METHOD", etc. This violated the JSON-RPC 2.0 specification, which defines exact field names. A malicious MCP peer may have been able to send protocol messages with non-standard field casing that the SDK would silently accept. This had the potential for bypassing intermediary inspection and coss-implementation inconsistency. Go's standard JSON unmarshaling was replaced with a case-sensitive decoder in commit 7b8d81c. Users are advised to update to v1.3.1 to resolve this issue.

CWE(s)

AI Security AnalysisAI

AI Category
AI Agent Protocols and Integrations
Risk Domain
Protocol-Specific Risks
OWASP Top 10 for LLMs 2025
None mapped
Classification Reason
Matched keywords: mcp

Related Threats

MITRE ATT&CK Enterprise Techniques

T1036 Masquerading Stealth
Adversaries may attempt to manipulate features of their artifacts to make them appear legitimate or benign to users and/or security tools.
T1190 Exploit Public-Facing Application Initial Access
Adversaries may attempt to exploit a weakness in an Internet-facing host or system to initially access a network.
T1557 Adversary-in-the-Middle Credential Access
Adversaries may attempt to position themselves between two or more networked devices using an adversary-in-the-middle (AiTM) technique to support follow-on behaviors such as [Network Sniffing](https://attack.
Derived from this CVE’s CWE(s) via the direct CWE→ATT&CK cross-walk.

CVEs Like This One

CVE-2026-33252Same product: Lfprojects Mcp Go Sdk
CVE-2026-34742Same product: Lfprojects Mcp Go Sdk
CVE-2026-52869Same vendor: Lfprojects
CVE-2026-44430Same vendor: Lfprojects
CVE-2026-44428Same vendor: Lfprojects
CVE-2025-68145Same vendor: Lfprojects
CVE-2026-27735Same vendor: Lfprojects
CVE-2025-68143Same vendor: Lfprojects
CVE-2026-35568Same vendor: Lfprojects
CVE-2026-34237Same vendor: Lfprojects

Affected Assets

lfprojects
mcp go sdk
≤ 1.3.1

Mitigating Controls

Mitigating Controls (NIST 800-53 r5) AI

Developer testing and evaluation can discover cases where two products interpret the same inputs or state transitions differently.

Strict, consistently applied input validation reduces the chance that one product will accept data the other product rejects or interprets differently.

Applying access control decisions to each request depends on accurate property determination that accounts for case differences.

Correct enforcement of authorizations for resource access structurally requires consistent case-sensitive handling of identifiers to avoid incorrect decisions.

Applying security engineering principles during design can require unambiguous protocol and data-format specifications that eliminate divergent interpretations between products.

Mitigating Controls (NIST CSF 2.0) AI

Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→CSF cross-walk (authority under review) — links open the control.

PR.PS-06 mostly match
prevents

Secure SDLC practices directly reduce the chance of introducing parser or state-machine inconsistencies.

DE.AE-03 partial match
prevents

Correlating logs from multiple products can surface discrepancies caused by interpretation conflicts.

DE.CM-09 partial match
prevents

Runtime monitoring of software behavior can detect adverse outcomes stemming from differing interpretations.

GV.SC-07 partial match
prevents

Supplier risk assessments can identify products whose differing interpretations create systemic exposure.

Mitigating Controls (ISO/IEC 27001:2022 Annex A) AI

Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→ISO cross-walk (authority under review) — links open the control.

finds

Security testing can detect and correct cases where one component misinterprets another’s state or messages.

prevents

Secure SDLC practices should include case-sensitivity requirements in design and coding standards.

prevents

Application security requirements must specify case handling for identifiers and paths.

prevents

Architecture principles should enforce canonical, case-aware resource naming.

prevents

Secure coding guidelines must mandate explicit case handling to prevent inconsistent lookups.

degrades

Access-control rules that ignore case can allow unintended resource access.

References