JumpCloud ships Agentic IAM with MCP discovery: 8.5% of MCP deployments use OAuth
Enterprise IAM is waking up to agents. JumpCloud's Agentic IAM update auto-discovers MCP server configurations across an organization and routes them through a governed AI Gateway, treating each agent as a first-class identity that can be audited, restricted, or revoked — the same lifecycle humans get, applied to non-human actors.
The stats behind the push explain why IAM vendors smell budget: 30 CVEs filed against MCP infrastructure in 60 days (Jan-Feb 2026), 82% of MCP deployments vulnerable to path traversal, only 8.5% using OAuth at all, and 88% of organizations have had or suspect an agent-related security incident in the past year. Machine identities outnumber humans 109:1 in the average enterprise, and only 14.4% of agents reach production with full security approval.
Read the numbers together and the picture is blunt: agents got deployed at consumer-grade security, and the tooling that would govern them did not exist. When a vendor like JumpCloud builds MCP discovery into IAM, that is the market admitting agents are infrastructure — with inventories, permissions and audit trails — not experiments on a laptop. If you run agents inside a company, the near-term checklist is unglamorous: inventory what you actually connected, put auth in front of it, and assume the audit question arrives before the ROI question.
Governance in practice — Frameworks & Tools of the week
8. WSO2 ships an open-source control plane, formalizing agent governance as infrastructure — forkast.news (via GNews)
Link: https://news.google.com/search?q=WSO2+open-source+control+plane+agent+governance
Governance moved from slide decks to deployable infrastructure this week. Builders: if you sell anything agentic, “works with your governance plane” just became a checklist item.
9. GitHub trending — the safety-tooling wedge is real:
- cloudflare/security-audit-skill — security audits packaged as an agent skill; Cloudflare itself shipping the “auditor-agent” pattern.
- anthropics/knowledge-work-plugins + anthropics/claude-code — vendor tooling keeps consolidating around skills/plugins.
- Thurbeen/thurbox — tmux-based TUI/CLI for local agent orchestration (Show HN, 16 Sep).
- CTRLRun/ctrlrun — open-source safety layer for agent actions (Show HN, 15 Sep).
- gokulrajaram/ProductSpec — an open standard for software intent in the agent era: specs as the artifact humans author and agents implement.
- malaysherasia-ai/claude-never-again — agent memory so it stops repeating mistakes you already fixed.
Pattern to watch: three of the week's launches are “make agents checkable” tools. The governance/audit wedge is where small teams can still ship without a model budget.
Sources & further reading:
Coverage · Full Issue #001