MCP servers
Connectors that let any agent use a tool or data source through the Model Context Protocol, and how to adopt them safely.
What it is
The Model Context Protocol (MCP) is an open standard, introduced by Anthropic in November 2024, for connecting AI applications to tools and data. An MCP server wraps a system, such as a database, CRM, file store or browser, so any MCP-compatible agent can use it without a custom integration.
Why it matters to leaders
MCP turns integration from a bespoke project into configuration, which speeds up agent deployments. It also means every server you connect extends what an agent can do, so each one needs scoped credentials, a named owner and an audit trail.
What to watch
Official servers from software vendors, remote servers with proper authentication, registries for discovering trusted servers, and security issues such as tool poisoning and over-broad tokens.
Latest mcp servers radars
- MCP servers
MCP servers radar, 21 Nov 2026: bla leads 6 new projects
qybaihe/bla (6,334 stars) tops 6 new MCP servers. Plus 3 releases and 5 new papers.
- MCP servers
MCP servers radar, 20 Nov 2026: bla leads 6 new projects
qybaihe/bla (6,209 stars) tops 6 new MCP servers. Plus 3 releases and 5 new papers.
Questions and answers
What is an MCP server?
A small service that exposes a tool or data source, for example a database, a ticketing system or a browser, through the Model Context Protocol, so AI agents can use it in a standard way.
How do I evaluate an MCP server before connecting it?
Check who publishes and maintains it, what permissions and credentials it needs, whether it runs locally or remotely, how it authenticates, how recently it was updated and its licence. Start with read-only access.
What are the security risks of MCP?
Over-broad tokens, untrusted servers that change their tool descriptions, prompt injection through returned content and data leaving your environment. Scoped credentials, an allow-list of approved servers and logging reduce the risk.
Other beats in the village
- Quantum computingQubits, error correction, post-quantum security and the open-source SDKs where quantum developers are spending their time.
- Agentic AIAI that plans, uses tools and acts across several steps: the projects, research and governance questions behind it.
- AI solutionsThe applications built on top of models: retrieval, copilots, document AI and the open-source building blocks behind them.
- AI harnessesThe software around a model that turns it into a working agent: coding agents, terminals, sandboxes and the loop that runs them.
- Agent skillsPackaged know-how that teaches an agent to do a job well: SKILL.md folders, skill libraries and how teams share them.
- Agentic GitHubThe most-starred agent projects on GitHub and the releases they ship each week: a health check for the frameworks everyone builds on.