TL;DR: The usual client and server labels invert the runtime roles in MCP, Archestra reports, so engineers cannot infer trust, responsibility, or control placement from the names alone. Role-based controls need to follow the actual tool boundary, or governance can land on the wrong component.
Editorial analysis by NHI Mgmt Group, based on content published by Archestra: “'MCP server' and 'MCP client' are confusing names”.
Key questions
Q: Why does clean core matter for identity and access governance?
A: Clean core matters because it changes where controls can live.
Q: What should teams do when a protocol uses familiar words in unfamiliar ways?
A: They should freeze the vocabulary, write down the actual runtime roles, and require reviewers to use those roles in design discussions.
A: Security teams should treat each MCP boundary as a separate trust decision.
Practitioner guidance
- Audit role assignments by execution behaviour Document which component initiates tool calls, which component exposes tools, and which component stores credentials so the team does not inherit the wrong mental model from the protocol name.
- Treat local tool servers as governed NHIs Apply inventory, ownership, and secret-handling controls to small MCP server processes even when they run on a developer laptop or in a short-lived shell session.
- Define the security boundary around delegation Mark the point where a client request becomes an authenticated tool invocation and require that boundary to carry policy, logging, and approval logic.
Bottom line: MCP reverses the usual web naming pattern, so teams cannot rely on the words client and server to infer trust, responsibility, or control placement.
Glossary terms: Mcp Client, MCP Server, Role-label inversion
Explore further
View Full Forum → | NHI Foundation Course → | Our Services → | Read the full analysis →
Naming confusion is itself a control failure in MCP onboarding. When the same term means the opposite of what most engineers expect, access, credential, and trust decisions start from the wrong mental model. That does not create an exploit by itself, but it creates the conditions for mis-scoped controls and misplaced responsibility. Practitioners should treat terminology drift as a governance issue, not a documentation annoyance.
A few things that frame the scale:
- 24,008 unique secrets were exposed in MCP configuration files in 2025 alone, the protocol's first year of widespread adoption, according to the State of Secrets Sprawl 2026.
- AI-related credential leaks surged 81.5% year-over-year in 2025, with the surrounding AI infrastructure leaking 5x faster than core LLM providers, according to the State of Secrets Sprawl 2026.
A question worth separating out:
Q: What is the difference between an MCP host, client, and server?
A: The host is the AI application the user interacts with and where the session is managed. The client handles one connection to a specific server, including discovery and request formatting. The server exposes the actual tools, resources, and prompts. Security responsibility is split across all three, so each boundary needs separate controls.
👉 Read our full editorial: MCP client and server names invert the usual security model