Results for “MCP”

Why it matters

Binance has launched Agent OS, a platform connecting AI tools like Claude Code, Cursor, and Codex to crypto trading rails via Model Context Protocol (MCP). The architecture uses dedicated subaccounts and hard risk boundaries to isolate autonomous agent actions.

Why it matters

Toolport is a local Model Context Protocol (MCP) gateway that connects multiple AI clients to a shared set of MCP servers. By using lazy tool discovery, it reduces tool-definition token overhead by up to 96%.

Why it matters

October 2026 brought a run of critical flaws in Model Context Protocol components. Langflow allowed arbitrary OS command execution, the official fetch server shipped an SSRF bug, an x64dbg MCP server exposed debugger tools without authentication, and the Python SDK sent secrets to attacker-controlled token endpoints.

Why it matters

A new practical guide demonstrates running a containerized Kubernetes Model Context Protocol (MCP) server connected to Claude Desktop. The setup mounts local kubeconfig credentials as read-only, exposing kubectl, Helm, and ArgoCD tooling directly to natural-language agent prompts.

Why it matters

Anthropic introduced the Model Hardware Standard (MHS), an open research preview specification that enables AI agents to discover, configure, and control physical lab devices and hardware using Model Context Protocol (MCP) and CLI interfaces. Early implementations show setup times falling from weeks to hours and 99.3% success in automated quantum laser relocking.

Why it matters

A new architectural guide demonstrates how to secure Model Context Protocol (MCP) server endpoints using Open Policy Agent (OPA) with Quarkus, preventing unauthorized tool execution by LLMs.

Why it matters

Researchers uncovered protocol pivoting vulnerabilities in multi-agent systems using Model Context Protocol (MCP). Flaws in tools like Google's MCP database toolbox allow attackers to bypass guardrails and trigger server-side request forgery.

Why it matters

The dart_mcp package introduced bounded pagination helpers capped at 64 pages to prevent infinite loops from buggy or malicious Model Context Protocol servers. It also added automated weekly conformance test suites and streamable HTTP examples.

Why it matters

Pillar Security discovered an active supply-chain campaign named Deadbugz targeting Model Context Protocol (MCP) clients. The attack uses runtime-gated prompt poisoning that waits for three benign tool calls before swapping metadata to exfiltrate SSH keys and cloud credentials.

Why it matters

A definitive security guide outlines threat models and architectural controls for Agent-to-Agent (A2A) and Model Context Protocol (MCP) networks. It details how to implement robust identity verification, gate delegation, and setup structured audit trails.

Why it matters

Arkon is an open-source, self-hosted knowledge management platform that acts as an MCP server. It compiles documents into a structured wiki using an LLM-driven pipeline, allowing teams to securely expose organizational knowledge to Claude.

Why it matters

AWS published CVE-2026-87911 (CVSS 9.6) in its postgres-mcp-server where read-only mode can be bypassed using PostgreSQL COPY TO PROGRAM syntax. An untrusted prompt processed by an agent can execute shell commands on the host if the database role has elevated privileges.