Reading the repo — stats and the shipped feed land in about ten seconds…
The week focused on fixing staleness and consistency issues throughout the UI and runtime. Web and macOS clients received multiple follow-ups addressing stale state in profiles and clients sheets, command palette behavior, and scope handling, while the server layer fixed session attribution across…
Get this in your inbox every Monday →A deterministic 0–100 hygiene score — README, license, CI, tests, docs, and freshness.
Who ships this repo — author concentration and the bus factor across the last 300 mainline commits.
How welcoming this repo is to contributors — issue throughput, close time, responsiveness, and good-first-issue count.
What this project is built on — dependency count by ecosystem, the license mix, and anything worth a legal look before you adopt it.
Whether this project's CI can be trusted — pass rate, run times, flaky runs, and which workflow is the weak link.
Grounded in mcpproxy-go's README, structure, and recent commits — answers won't invent code they haven't seen.
A Monday email with what shipped, in plain English — no account needed.
Showing raw commit titles for the newest commits. Sign in to generate AI summaries.
fix(oauth): discovery overrides, offline_access and discovery cache (Spec 113-b) (#1499)
fix(oauth): serialize token refresh per server and classify refresh errors (Spec 113-a) (#1498)
feat(server): private short-lived MCP cache hints on list/read results (Spec 113-f) (#1510)
feat(index): match underscore-delimited tool-name segments in search (#1535)
docs(specs): Spec 113 upstream resilience - OAuth refresh, discovery, call-error taxonomy, health (#1495)
feat(health): degrade on rolling tool-call failure rate (Spec 113-d) (#1504)
fix(upstream): re-initialize a terminated Streamable HTTP session and retry once (Spec 113-e) (#1501)
A floor, not a guess: counts only commits whose author, co-author trailer, or message explicitly credits an AI tool (Claude, Copilot, Cursor, aider, Codex…). Based on 30 mainline commits. Unattributed AI code isn't counted here — the full audit estimates that separately.
