On 2026-10-14 Chainguard announced four MCP servers for agent supply-chain checks, generally available to enterprise customers: cg-oci (image manifests/SBOMs/provenance), cg-apk (Wolfi package equivalents), cg-versions (upstream releases and EOL), and cg-api (org policy and attestations). Any MCP client (Claude Code, Cursor, and others) connects via OAuth; pagination and response caps are enforced server-side so agents stop hallucinating tags or recommending EOL packages. Complements the same-day Harness/Checks/Workspaces launch by wiring dependency choices to live product data.

Key Takeaways

  • ✓Four endpoints: https://cgr.dev/mcp, apk.cgr.dev/mcp, versions.cgr.dev/mcp, console-api.enforce.dev/mcp over Streamable HTTP + OAuth 2.0
  • ✓Live data: image SBOM/provenance, Debian→Wolfi package mapping, upstream EOL history, org policy/advisories—not model memory
  • ✓Governance: server-side pagination (~25–50 default, 200 max) and response caps; cg-api hides tools your token cannot use
  • ✓Headless: chainctl auth login --audience=<mcp-url> plus a headersHelper Bearer injector avoids Claude Code's ~1h OAuth re-login loop
  • ✓Extras: docs MCP at mcp.edu.chainguard.dev (no sign-in); Skills MCP at skills.cgr.dev/mcp for on-demand hardening skills
Chainguard ships four MCP servers so coding agents verify images, APKs, EOL status and policy live—server-side governance instead of prompt guardrails
🖼️Official Media
Click to view high-res
⚡

Key Decision Metrics at a Glance

TL;DR Verdict
🏆 Benchmark RankRank
See how it ranks on the leaderboard
Full Leaderboard→
💰 Cost & PlansCompare
API & Subscription
Compare Plans↗
🛠️ Ecosystem & IDERules
Chainguard · MCP · SBOM
Setup IDE Rules↗
🧭

Heavy Claude Code use: compare subscription limits and API bills

Compare 40 dev plans & simulate token costs vs $20/mo subscriptions

⚔️ Compare Model→💰 Compare plans & limits↗
🔗

Project Links & Resources

Direct Access
Direct access to official project resources and documentation
📝
Introducing Chainguard MCP (official blog)
www.chainguard.dev/unchained/introducing-chainguard-mcp-for-secure-agentic-development
↗
📖
Chainguard MCP servers overview (Academy)
edu.chainguard.dev/platform/mcp-servers/overview/
↗
📖
cg-apk MCP server docs
edu.chainguard.dev/platform/mcp-servers/cg-apk/
↗
📖
Claude Code MCP quickstart
code.claude.com/docs/en/mcp-quickstart
↗
🔬

In-Depth Technical Analysis

Chainguard announced four MCP servers for secure agentic development on 2026-10-14, generally available to enterprise customers. Coding agents write code faster than reviewers can vet dependencies; models invent image tags and suggest EOL packages. The servers expose live product data over Streamable HTTP with OAuth: cg-oci (https://cgr.dev/mcp) for manifests, SBOMs, apko configs and provenance; cg-apk for Wolfi package lookup and melange configs; cg-versions for upstream release/EOL history; cg-api for org IAM, registry metadata and advisories. Tool results are scoped to the caller's token, and cg-api hides tools the token cannot use. Pagination defaults (~25–50, max 200) plus response caps enforce governance server-side instead of relying on prompt guardrails. Headless setups use chainctl auth login --audience=<full-mcp-url> and a Claude Code headersHelper that injects Bearer tokens (avoiding ~1h OAuth without refresh). Docs MCP (mcp.edu.chainguard.dev) needs no sign-in; Skills MCP serves hardening skills on demand. Complements Chainguard's same-day Harness/Checks/Workspaces line: MCP grounds dependency facts, while those products cover vulnerability hunting and sandboxed agent runs. Setup: see Chainguard Academy MCP overview.

Action HubReady to adopt this in production?

Benchmark side-by-side against alternatives, or calculate monthly token cost vs subscription break-even.

⚔️ Launch VS Compare→💳 View Plans↗
Up NextChainguard ships three agent-security products: Harness runs Claude Mythos 5.1 vulnerability hunts for you, Checks turns CI into an agent-callable pre-commit check, Workspaces adds microVM sandboxes
Read Now→