Notifications
Clear all
Topic starter
08/06/2026 4:22 pm
TL;DR: Cursor’s MCP Night 2.0 recap says one-click install and OAuth support coincided with a clear adoption inflection, while the most-used servers centered on documentation, database, browser, design, and GitHub context, according to WorkOS. The pattern shows that friction, context breadth, and real data are now the practical tests for MCP governance, not protocol novelty.
NHIMG editorial — based on content published by WorkOS: MCP Night 2.0 Demo Recap on how Cursor users are embracing the Model Context Protocol
Questions worth separating out
Q: How should security teams govern MCP servers in developer workflows?
A: Treat each MCP server as a governed non-human identity with explicit ownership, scoped permissions, and a lifecycle.
Q: Why do MCP connections change the identity risk surface for engineering teams?
A: MCP connections pull live data and tool access into one session, which expands the effective blast radius beyond a single application.
Q: What do security teams get wrong about OAuth-enabled developer tools?
A: They often assume OAuth automatically makes access safe to delegate.
Practitioner guidance
- Map every MCP connection to an identity owner Assign a named business and technical owner for each MCP server, including the OAuth client, underlying service account, and downstream systems it can reach.
- Review OAuth scopes before broad rollout Compare each MCP server’s granted scopes with the minimum data and action set required for its job.
- Track connected context as a governed asset Record which documentation, repository, database, and browser sources each MCP server can assemble into a live session.
What's in the full article
WorkOS's full recap covers the operational detail this post intentionally leaves for the source:
- Eric Zakariasson's full adoption timeline for Cursor's MCP implementation and the one-click install inflection point.
- The specific MCP servers that ranked highest in Cursor's ecosystem, including documentation, database, browser, design, and GitHub use cases.
- The live LinkedIn posting demo built on top of Playwright, including the dry-run behaviour shown on stage.
- Additional MCP Night 2.0 demo context and the broader event recap across participating builders.
👉 Read WorkOS's MCP Night 2.0 recap on developer adoption patterns →
Model Context Protocol adoption: what stable usage means for IAM teams?
Explore further
08/06/2026 5:57 pm
MCP adoption is becoming an NHI governance problem before it becomes an agentic AI problem. The article shows developers using MCP as a practical bridge to documents, databases, browser state, and project systems. That means the first-order risk is not autonomous behaviour, but non-human access that is easy to create and hard to inventory. Practitioners should read MCP as an identity expansion pattern, not just a tooling trend.
A few things that frame the scale:
- 53% of MCP servers expose credentials through hard-coded values in configuration files, according to The State of MCP Server Security 2025.
- 24,008 unique secrets were exposed in MCP configuration files in 2025 alone, according to the same research.
A question worth separating out:
Q: How can organisations tell whether an MCP integration is safe to keep in production?
A: A safe MCP integration has a named owner, documented scopes, observable activity, and a working offboarding path. If any of those are missing, the integration is still experimental from a governance perspective, even if developers already rely on it.
👉 Read our full editorial: MCP adoption is moving from novelty to durable developer usage
