---
title: "Blog: security | mcp.tc"
description: "Articles tagged “security” on the mcp.tc blog: guides and data about MCP servers."
url: "https://mcp.tc/blog/tag/security"
markdown: "https://mcp.tc/blog/tag/security.md"
lang: "en"
---

# Posts about security

5 posts

Follow new posts in any feed reader with the [Atom feed](https://mcp.tc/blog/feed.xml).

- [MCP Tool Poisoning: Reading Schemas, Enums and Defaults](https://mcp.tc/blog/mcp-tool-poisoning-schemas) · MCP tool poisoning goes beyond the description field: parameter descriptions, enums, defaults and invisible characters. How to dump a tool list and read it. · 5 Nov 2026 14 min read
- [MCP Tool Annotations: What readOnlyHint and destructiveHint Mean](https://mcp.tc/blog/mcp-tool-annotations) · MCP tool annotations explained: readOnlyHint, destructiveHint, idempotentHint, openWorldHint, their defaults, SDK syntax and why clients treat them as hints. · 22 Oct 2026 11 min read
- [MCP Authorization in Practice: Metadata, Client IDs and Sign-In](https://mcp.tc/blog/mcp-authorization-in-practice) · How MCP authorization works on the wire: the 401 challenge, protected resource metadata, Client ID Metadata Documents, PKCE, scopes and the client side. · 19 Oct 2026 14 min read
- [Is This MCP Server Safe? How to Check Before You Connect](https://mcp.tc/blog/is-this-mcp-server-safe) · A practical MCP server security check: tool poisoning, prompt injection, scopes, read-only hints, vendor verification, npm supply chain, and a checklist. · 4 Oct 2026 10 min read
- [Remote vs Local MCP Servers: OAuth, API Keys and stdio](https://mcp.tc/blog/remote-vs-local-mcp-servers) · When to run an MCP server locally over stdio and when to use a remote one with OAuth or an API key: security, privacy, performance and enterprise tradeoffs. · 4 Oct 2026 10 min read

---
Source: https://mcp.tc/blog/tag/security. Markdown version for AI agents (ask for `text/markdown` or add `.md` to the address). Site overview: https://mcp.tc/llms.txt
