liveBook · Manning

MCP server

As explained in AI Governance

An MCP server is a software component that exposes tools or data sources to AI agents through the Model Context Protocol.

An MCP server exposes tools or data sources through a uniform interface that compatible AI agents can discover and use without custom integrations. Reusing servers can simplify connections, but it also concentrates risk: a vulnerability can affect every connected agent. section 4.8.3

Assess the exposure created by an MCP server:

  • Check whether requested permissions exceed the tool’s actual needs; a GitHub integration may request full repository access to read issues. section 4.8.3
  • Treat tool descriptions as an attack surface: hidden instructions can manipulate an agent, including by requesting sensitive data. section 4.8.3
  • Consider connected systems together: malicious instructions in one source can reach data in others, and servers may advertise tools after connection. section 4.8.3

How AI Governance covers it

How deep it goes
Explains integration benefits and security risks, including permissions, tool descriptions, and dynamic discovery.
Examples
Uses database, document, and email integrations, plus a GitHub permission example and a malicious tool-description instruction.
What you can do after
Evaluate MCP integration risks by checking permission scope, tool descriptions, connected data sources, and changing tool availability.
How it connects
Connects MCP servers with AI agents, prompt injection, and external tools and data sources.

Also explained in

Compare how 18 books explain MCP server →

Related concepts

This explainer was generated by Manning's knowledge graph from the text of AI Governance. The section links point to the parts of the book it draws on.