Permit launches MCP gateway for secure agents

// 70d agoPRODUCT LAUNCH

Permit launches MCP gateway for secure agents

Permit MCP Gateway is a drop-in trust layer for MCP that sits in front of existing servers and adds the security and governance MCP itself lacks. It authenticates users through existing IdP infrastructure, enforces Zanzibar-style fine-grained authorization, presents consent screens, and records full decision logs without requiring SDK changes or server rewrites.

// ANALYSIS

Hot take: this is the kind of product that can turn MCP from a clever developer protocol into something security teams will actually approve.

–Strong wedge: it solves the exact enterprise objections around MCP, especially auth, delegation, and auditability.
–The "swap one URL" story is compelling because it lowers adoption friction more than another SDK ever could.
–If Permit really hides the complexity behind policy generation and consent UX, it could become the default control plane for agent-to-tool access.
–The risk is platform gravity: teams already using API gateways, IAM, or zero-trust proxies may see overlap unless Permit is clearly better at MCP-specific governance.
–This is most valuable where agents touch sensitive systems like CRM, docs, code, and support tooling.

// TAGS

mcpsecurityauthorizationidentityoauthzero-trustagentgovernance

DISCOVERED

70d ago

2026-03-18

PUBLISHED

71d ago

2026-03-18

RELEVANCE

9/ 10

AUTHOR

[REDACTED]

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

OPEN SOURCE52m ago

Plannotator 0.19.24 adds Amp support and configurable storage

Plannotator 0.19.24 is a substantial release that expands the tool beyond Claude Code with native Amp support, adds a `PLANNOTATOR_DATA_DIR` override so users can move the default `~/.plannotator` data directory, introduces Auto Mode in the permission selector for newer Claude Code versions, and fixes a Pi approval crash after plan acceptance. The update folds multiple stacked PRs into one release and pushes the project further toward a multi-agent review layer rather than a single-agent hook utility.

UPDATE1h ago

Grok Build widens access, adds subagents

xAI’s Grok Build is an early-beta terminal coding agent with plan-review-approve flows, parallel subagents, worktree isolation, and support for plugins, hooks, skills, and MCP. The latest improvements make it feel less like a demo and more like xAI’s bid to compete seriously in the AI coding CLI race.

MODEL1h ago

Krea 2 lands on Replicate

Krea 2 is now available on Replicate, giving developers access to Krea's style-first image model outside the Krea app. It emphasizes aesthetic diversity, style control, and reference-driven creative workflows.