{"id":"CVE-2026-67431","aliases":["GHSA-5p9g-j988-pcwv"],"title":"MCP Ruby SDK: Ruby SSE Session Poisoning","summary":"MCP Ruby SDK: Ruby SSE Session Poisoning","severity":"high","cwe":["CWE-284"],"vendor":"mcp","product":"mcp","ecosystem":"rubygems","affected":["mcp <= 0.22.0"],"patched":["mcp 0.23.0"],"published":"2026-07-30","updated":"2026-07-30","source":"GHSA","sourceUrl":"https://github.com/advisories/GHSA-5p9g-j988-pcwv","references":[{"url":"https://github.com/modelcontextprotocol/ruby-sdk/security/advisories/GHSA-5p9g-j988-pcwv"},{"url":"https://nvd.nist.gov/vuln/detail/CVE-2026-67431"},{"url":"https://github.com/modelcontextprotocol/ruby-sdk/commit/35466605319a34e4c7808712ae9bb1ca1afb2356"},{"url":"https://github.com/modelcontextprotocol/ruby-sdk/releases/tag/v0.23.0"},{"url":"https://github.com/advisories/GHSA-5p9g-j988-pcwv"}],"tags":["ghsa","rubygems"],"epss":0.00292,"epssPercentile":0.22024,"ingestedAt":"2026-07-30T14:54:20.303Z","slug":"CVE-2026-67431","body":"## Overview\n\n### Summary\n**Vulnerability**: Missing Session Ownership Validation in the Ruby MCP SDK's Streamable and SSE HTTP transport implementation. Any attacker with a stolen session ID can execute tools with the victim's session. This is a silent attack - the victim's session is compromised and being used for unauthorized actions, but it is hard to know for the victim\n\n### Details\nhttps://github.com/modelcontextprotocol/ruby-sdk/blob/main/lib/mcp/server/transports/streamable_http_transport.rb#L260-L278\n\n**Victim** starts a legitimate MCP session and receives session ID abc-123\n**Attacker** obtains the session ID (various means - network sniffing, logs, etc. out of scope for this analysis)\n**Attacker** sends POST to /messages/abc-123 with a tool call\n**Server** accepts the request (no ownership validation!)\n**Server** executes the tool and sends response to victim's SSE stream\n**Victim** receives attacker's response, thinking it's legitimate\n\n### PoC\n[attacker_client.py](https://github.com/user-attachments/files/26044817/attacker_client.py)\n[legitimate_client.py](https://github.com/user-attachments/files/26044818/legitimate_client.py)\n\n**Prerequisites**\n\n1. Python 3.8+\n2. Install dependencies: `requests`\n\n**Running the Demo**\n\n1. **Terminal 1:** Start the Ruby MCP Server\n\n`ruby streamable_http_server.rb`\n\nMakes use of https://github.com/modelcontextprotocol/ruby-sdk/blob/main/examples/streamable_http_server.rb\nThis server has a tool call notification_tool which the clients call\n\n2. **Terminal 2:**  Start Victim Client\n\n`python3 legitimate_client.py`\n\n3.  **Terminal 3** - Attacker Client:\n\nCopy the session ID from Terminal 1 and run:\n\n```bash\npython3 attacker_client.py abc-123-def-456\n```\n4. **Back to Terminal 2** - Victim sees the injected response:\n\n### Impact\n\n- **Integrity:** HIGH - Attacker can execute unauthorized tools and modify state\n- **Availability:** LOW - Attacker can disrupt victim's session with injected responses\n\n### Additional Details\nSession Hijacking Protection in MCP Implementations\n\nThe MCP specification recommends - \"[MCP servers SHOULD bind session IDs to user-specific information](https://modelcontextprotocol.io/docs/tutorials/security/security_best_practices#mitigation-4)\".\n\n#### User Binding - Comparison other SDKs\n**csharp-sdk**\n\n- https://github.com/modelcontextprotocol/csharp-sdk/blob/main/src/ModelContextProtocol.AspNetCore/SseHandler.cs#L36\n- https://github.com/modelcontextprotocol/csharp-sdk/blob/main/src/ModelContextProtocol.AspNetCore/SseHandler.cs#L95-L98\n\n**Go-sdk**\n\n- https://github.com/modelcontextprotocol/go-sdk/blob/main/mcp/streamable.go#L66\n- https://github.com/modelcontextprotocol/go-sdk/blob/main/mcp/streamable.go#L316-L320\n\n#### Comparison with the Stream Replacement vulnerability \n\n**Stream Replacement**\nhttps://github.com/modelcontextprotocol/ruby-sdk/security/advisories/GHSA-qvqr-5cv7-wh35\n\n- **Target**: SSE stream connection\n- **Attack Vector**: GET /mcp\n- **What happens to Victim**: The connection is disconnected and doesn't receive reponses \n\n**Session Poisoning**\n\n- **Target**: Tool execution\n- **Attack Vector**: POST /mcp\n- **What happens to Victim**: The connection stays connected and receives responses of tool calls by attacker\n\n## Affected packages\n\n- `mcp <= 0.22.0`\n\n## Remediation\n\nUpgrade to a patched release:\n\n- `mcp 0.23.0`","depth":"twilight","depthScore":41,"depthScoreParts":{"impact":41.3,"likelihood":0.1,"exploitation":0,"ransomware":0},"changes":[]}