MCP in production: are tool servers keeping up with agent use?

TL;DR: More than 90,000 open-source MCP servers and 630,000 tools were rescanned, finding rapid ecosystem growth but persistent gaps in descriptions, input constraints, recovery guidance, and safety annotations, according to Arcade. The data suggests MCP adoption is outpacing the governance and authorisation discipline needed for production-grade agent workflows.

Editorial analysis by NHI Mgmt Group, based on content published by Arcade: “What Scanning 90,000 MCP Servers & 630,000 Tools Reveals About Agent-Ready Tools”.

By the numbers:

• Only 260 of the open-source servers we scored earn an A, and none earn an A+.
• Stateless handling appears on 5.8% of servers, and those servers average about eight points higher.

Key questions

Q: What breaks when an MCP server's tool descriptions do not match its actual actions?

A: The trust model breaks.

Q: Why do stateless MCP servers require tighter authorization than session-based designs?

A: Stateless handling removes reliance on a prior handshake or session ID, so each request has to stand on its own.

Q: What are the signs that an MCP deployment is being used unsafely by agents or downstream users?

A: Warning signs include unknown fields being accepted, risky write operations proceeding without approval, repeated retries creating duplicate actions, and tool calls reaching unexpected hosts or regions.

Practitioner guidance

• Define tool semantics as governance artefacts Document what each tool changes, what it returns, when it should be used, and when it should not.
• Annotate destructive and irreversible actions Mark reset, delete, and other state-changing tools with explicit safety annotations and require user confirmation before execution proceeds.
• Remove credentials from tool parameters Pass secrets through controlled identity channels instead of embedding them in prompts or inputs where they can be logged or replayed.

Bottom line: MCP server quality is now an identity and governance issue because agents act on tool metadata, not just on human review.

Explore further

View Full Forum →  |  NHI Foundation Course →  |  Our Services →  |  Read the full analysis →