https://miscreants.github.io/blog.trailofbits.com/categories/mcp/Recent content in mcp on The Trail of Bits BlogHugoen-usSat, 15 Nov 2025 00:00:00 -0500https://miscreants.github.io/blog.trailofbits.com/2025/11/15/level-up-your-solidity-llm-tooling-with-slither-mcp/Sat, 15 Nov 2025 07:00:00 -0500https://miscreants.github.io/blog.trailofbits.com/2025/11/15/level-up-your-solidity-llm-tooling-with-slither-mcp/We’re releasing Slither-MCP, a new tool that augments LLMs with Slither’s unmatched static analysis engine.https://miscreants.github.io/blog.trailofbits.com/2025/07/28/we-built-the-security-layer-mcp-always-needed/Mon, 28 Jul 2025 07:00:00 -0400https://miscreants.github.io/blog.trailofbits.com/2025/07/28/we-built-the-security-layer-mcp-always-needed/Today we’re announcing the beta release of mcp-context-protector, a security wrapper for LLM apps using the Model Context Protocol (MCP). It defends against the line jumping attacks documented earlier in this blog series, such as prompt injection via tool descriptions and ANSI terminal escape codes.https://miscreants.github.io/blog.trailofbits.com/2025/04/30/insecure-credential-storage-plagues-mcp/Wed, 30 Apr 2025 03:00:00 -0400https://miscreants.github.io/blog.trailofbits.com/2025/04/30/insecure-credential-storage-plagues-mcp/This post describes how many examples of MCP software store long-term API keys for third-party services in plaintext on the local filesystem, often with insecure, world-readable permissions.https://miscreants.github.io/blog.trailofbits.com/2025/04/29/deceiving-users-with-ansi-terminal-codes-in-mcp/Tue, 29 Apr 2025 09:00:00 -0400https://miscreants.github.io/blog.trailofbits.com/2025/04/29/deceiving-users-with-ansi-terminal-codes-in-mcp/This post describes attacks using ANSI terminal code escape sequences to hide malicious instructions to the LLM, leveraging the line jumping vulnerability we discovered in MCP.https://miscreants.github.io/blog.trailofbits.com/2025/04/23/how-mcp-servers-can-steal-your-conversation-history/Wed, 23 Apr 2025 10:30:00 -0400https://miscreants.github.io/blog.trailofbits.com/2025/04/23/how-mcp-servers-can-steal-your-conversation-history/Malicious MCP servers can inject trigger phrases into tool descriptions to exfiltrate entire conversation histories and steal sensitive credentials and IP.https://miscreants.github.io/blog.trailofbits.com/2025/04/21/jumping-the-line-how-mcp-servers-can-attack-you-before-you-ever-use-them/Mon, 21 Apr 2025 10:30:00 -0400https://miscreants.github.io/blog.trailofbits.com/2025/04/21/jumping-the-line-how-mcp-servers-can-attack-you-before-you-ever-use-them/MCP’s ’line jumping’ vulnerability lets malicious servers inject prompts through tool descriptions to manipulate AI behavior before tools are ever invoked.