Skip to the content
AI and Cybersecurity Learning and Practice Center Test automation Open the Learning Center

Is my AI tool safe?Protocols and SDKsAnthropic and the MCP community

Is Model Context Protocol safe?

No tool is safe or unsafe on its own: it depends on what it can reach and how it is set up. The record for Model Context Protocol: 20 incidents in this center's library and 12 CVEs in its advisory feed (3 critical, 9 high), the newest published Oct 15, 2026. Below: what went wrong, what was fixed, and how to use it safely.

What to watch for

The plumbing of the agent ecosystem, and the busiest category in the library: malicious servers in registries, tool descriptions that change after review, STDIO configs that are command execution, and an SDK that handed OAuth secrets to any server that asked.

How to use it safely

Install servers only from vetted sources, pin each one to its tool list and re-approve on change, treat server config as code, and keep the SDKs on current versions.

What it can reach

  • Installs plugins, skills or tools from registries
  • Runs commands with your permissions
  • Holds API keys and tokens
  • Reads attacker-controlled content

What went wrong: incidents in the library

Known CVEs

  • CVE-2026-111768 High MCP TypeScript SDK runs out of memory validating one large tool request
    Oct 15, 2026 · no fixed release in the feed
  • CVE-2026-104850 High MCP TypeScript SDK sends OAuth credentials to an authorization server the MCP server chooses
    Oct 6, 2026 · fixed in 1.31.0
  • CVE-2026-111767 High MCP TypeScript SDK experimental tasks not tied to the session that created them
    Oct 2, 2026 · fixed in 1.32.0
  • CVE-2026-25536 High MCP TypeScript SDK cross-client data leak on shared server instances
    Feb 4, 2026 · fixed in 1.26.0
  • CVE-2026-23744 Critical MCPJam inspector unauthenticated RCE through an exposed HTTP endpoint
    Jan 16, 2026 · fixed in 1.4.3
  • CVE-2025-66414 High MCP TypeScript SDK lacks DNS rebinding protection by default
    Dec 2, 2025 · fixed in 1.24.0
  • CVE-2025-66416 High MCP Python SDK lacks DNS rebinding protection by default
    Dec 2, 2025 · fixed in 1.23.0
  • CVE-2025-53967 High Framelink Figma MCP server command injection in get_figma_data
    Sep 30, 2025 · fixed in 0.6.3
  • CVE-2025-6514 Critical mcp-remote OS command injection from an untrusted MCP server
    Jul 9, 2025 · fixed in 0.1.16
  • CVE-2025-53355 High mcp-server-kubernetes command injection in several tools
    Jul 8, 2025 · fixed in 2.5.0
  • CVE-2025-53109 High MCP filesystem server reads unintended files via symlinks
    Jul 2, 2025 · fixed in 2025.7.1
  • CVE-2025-49596 Critical MCP Inspector remote code execution through missing authentication
    Jun 13, 2025 · fixed in 0.14.1

How many people use it

  • 68.8M npm downloads of @modelcontextprotocol/sdk in a week (Sep 23 to 29, 2026) · npm download counts
  • 219M PyPI downloads of mcp in a month (to Oct 1, 2026) · PyPI Stats
  • 24k GitHub stars, Python SDK · GitHub

A high CVE count can mean heavy scrutiny as much as weak engineering, so read the incidents and advisories, not only the number. The counts are what this center has recorded, not every flaw ever found; usage figures are the vendors' and registries' own published numbers.

Sources

Compare it with the others on the Technology watch list