CVE-2026-27896: MCP Go SDK Vulnerable to Improper Handling of Case Sensitivity
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 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.
Security readout for executives and security teams
Plain-English summary
Applications using the MCP Go SDK before 1.3.1 may accept protocol messages with incorrectly capitalized JSON-RPC field names. That can let a malicious MCP peer slip messages past tools that enforce the exact standard, creating inspection gaps and inconsistent behavior between components.
Executive priority
Prioritize remediation for internet-facing, multi-tenant, or partner-connected MCP deployments. The issue is not documented as actively exploited, but it affects trust boundaries and protocol inspection, making timely dependency updates appropriate.
Technical view
The SDK used Go encoding/json.Unmarshal for JSON-RPC and MCP parsing. Go matches JSON keys to struct tags case-insensitively, so fields like method could be accepted with alternate casing. JSON-RPC requires exact field names. Commit 7b8d81c replaced this with case-sensitive decoding; users should update to v1.3.1.
Likely exposure
Exposure is limited to systems that include modelcontextprotocol/go-sdk versions before 1.3.1, especially MCP clients, servers, or intermediaries that parse peer-supplied protocol messages. The bundle does not identify specific downstream products or Red Hat package impact.
Exploitation context
The source bundle does not show active exploitation, and KEV is false. The documented risk is a malicious MCP peer sending non-standard field casing that affected SDK versions silently accept, potentially bypassing intermediary inspection or causing cross-implementation inconsistency.
Researcher notes
Do not assume code execution or data theft from the cited sources. Focus validation on parser behavior, dependency reachability, and whether intermediary controls normalize or inspect JSON-RPC keys differently than the affected SDK.
Mitigation direction
Update modelcontextprotocol/go-sdk to v1.3.1 or later.
Regenerate SBOMs and dependency lock files after upgrading.
Check vendor advisories for downstream package status.
Ensure MCP intermediaries enforce exact JSON-RPC field names.
Validation and detection
Search dependency manifests for modelcontextprotocol/go-sdk versions before 1.3.1.
Confirm deployed artifacts include go-sdk v1.3.1 or later.
Review parser tests for exact JSON-RPC field-name handling.
Check vulnerability scanners for CVE-2026-27896 findings.
Generated from the cited source records. This long-tail analysis has not been individually reviewed by a named human.
Potential ATT&CK relevance
Conservative CVE-to-ATT&CK context
These mappings and lookup hints may be relevant to the vulnerability behavior, CWE, affected product, or exposure path. Glexia-inferred context is not an official MITRE, ATT&CK, CWE, or CVE Program mapping.
ATT&CK lookup starting points
Use these exact CWE pages and searches to review the Glexia ATT&CK library from this CVE's weakness and description context.
cwe · low confidence lookup
CWE-178: Exact CWE lookup
Use the exact CWE identifier as the starting point before reviewing related ATT&CK behavior. Open the exact CWE lookup page first, then review the ATT&CK searches from that MITRE weakness context. This is a Glexia lookup hint, not an official ATT&CK mapping.
Use the exact CWE identifier as the starting point before reviewing related ATT&CK behavior. Open the exact CWE lookup page first, then review the ATT&CK searches from that MITRE weakness context. This is a Glexia lookup hint, not an official ATT&CK mapping.
These fields come from the CVE record and ADP containers, not from Glexia's Take. They preserve time-varying source decisions such as CISA SSVC, KEV status, CVSS metrics, and provider references.
We collect every scored CVSS vector available in the official CNA and ADP containers. When more than one version is present, the table keeps the source vectors side by side instead of collapsing them into the highest score.
CWE links open Glexia weakness intelligence pages with official CWE context, developer remediation guidance, and related CVE mappings.
CWE-178 · source CWE mapping
Improper Handling of Case Sensitivity
Improper Handling of Case Sensitivity represents a recurring weakness pattern that can create exploitable paths when design, validation, or implementation controls are missing.
Interpretation Conflict represents a recurring weakness pattern that can create exploitable paths when design, validation, or implementation controls are missing.