Release20d ago
Chainguard ships four MCP servers so coding agents verify images, APKs, EOL status and policy live—server-side governance instead of prompt guardrails
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.
Tooling45d ago
CodeGraph: local code knowledge graph via MCP for Claude Code, Codex, and peers
@RubanBhatia highlighted open-source CodeGraph (github.com/colbymchenry/codegraph, MIT): a local semantic code graph that auto-syncs on edits and plugs into Claude Code, Cursor, Codex, OpenCode, Gemini, Copilot, and more via MCP. It targets call paths, dependencies, and blast radius so agents spend fewer tokens on blind repo scans. The README advertises a Rust kernel and a self-contained install via @colbymchenry/codegraph; GitHub showed about 71.5k stars at fetch time.
Tooling7d ago
Microsoft Research and UC Berkeley open-source TokenEconomizer, a plugin that cuts Claude Code and Codex costs by 18.4–30.9% on SWE-Bench without changing the agent
Microsoft Research, Microsoft Security and UC Berkeley open-sourced TokenEconomizer on GitHub (Apache 2.0, v0.1.0 released October 26), a plugin for Claude Code, Codex, GitHub Copilot CLI and Pi, with experimental opencode support. It learns from earlier sessions in the same repository: micro-skills remember repo facts, tool pruning drops tool definitions that go unused, and a loop guard nudges an agent that is stuck. The paper reports 18.4–30.9% lower mean cost across five agent and model combinations on 277 SWE-Bench tasks (paper figures).
Discussion & Comments
0Sign in to join the discussion
Connect with AI developers to exchange benchmark insights.