Pulse
2026-09-18-v3.0
Dataset
2026-10-27-catalog-ai-v2
Ruleset
b2e8889c66f7
Scanned
2026-10-27
Window
February–September 15, 2026
Catalog tracking observation. This repository is measured with the same fixed window and ruleset, but it is not part of the published benchmark or its aggregate claims.

Visual testing tool for MCP servers

01Result

modelcontextprotocol/inspector ↗

modelcontextprotocol/inspector AI coding statistics: 72.7%

of 1,420 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
72.7% agent · top contributor 79.4%12 contributors
team

A small group is using agents. Adoption has spread beyond one person but is not project-wide.

1,033
agent commits
387
other considered commits
12
agent contributors
79.4%
largest contributor

02Drivers

What shapes this result

Mode, timing, and detected signatures show whether the result reflects broad adoption or one concentrated workflow.

Assisted or autonomous

1028assisted
5autonomous

Assisted — a developer’s identity authored the commit and the agent added itself as co-author. Autonomous — a bot identity authored the commit without a human identity attached.

Agent share by month

Agent-attributed commit share by month
MonthAgent shareConsidered commits
2026-0255.6%27
2026-0365.9%44
2026-0485.3%102
2026-05100%41
2026-0689.4%66
2026-0785.5%220
2026-0851.5%616
2026-0997.7%304

Peak month: 100%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic102772.3%
GitHub CopilotGitHub60.4%
Cursor AgentAnysphere30.2%

03Evidence

Inspect the matches

Public commit samples let you inspect the signatures behind the aggregate result.

Matched commit samples

  • f3e0edd2 on GitHubdocs: describe DirectoryReadResultSchema as the shape both eras share (#23Claude Code
  • e53f6a1b on GitHubtest: await each strict refusal before starting the next (#2374)Claude Code
  • 22438497 on GitHubdocs: bring comments and docs in line with -32021 and the Skills registry Claude Code
  • 5d91d4ac on GitHubfix(core): mirror SEP-2243 x-mcp-header args to Mcp-Param-* on tools/call GitHub Copilot
  • 0ba1b8d1 on GitHubchore: bump version to 0.22.0 (#1428)GitHub Copilot
  • db0827b2 on GitHubchore: bump version to 0.21.1 (#1116)GitHub Copilot
  • 33e88eac on GitHubCLI: catalog listing, auth flags, and OAuth browser UX (#1782)Cursor Agent
  • 52023ff1 on GitHubfix(auth): clear OAuth callback timer and reorder EMA scope persistCursor Agent
  • 13dafe45 on GitHubGuided-auth removal, OAuth smoke testing, and TUI/CLI support (#1531)Cursor Agent

04Method

What entered the denominator

The result begins with commit history, removes merges and routine automation, and reports literal agent signatures as a lower bound.

Exclusion ledger

Commits in window1,904
Merge commits removed−467
CI / dependency bots removed−17
Considered1,420

Bots are excluded from the denominator entirely. Agent attribution requires a literal supported signature; no code-style inference is used.

Continue exploring

Claude Code commitsBrowse repositories with detected Claude Code signatures →GitHub Copilot commitsBrowse repositories with detected GitHub Copilot signatures →Cursor Agent commitsBrowse repositories with detected Cursor Agent signatures →TypeScript AI coding statisticsCompare evidence across TypeScript repositories →GitHub AI commit analyzerInspect another repository with the same evidence model →
Reproduce this observation

Run the same detector locally.

Deterministic signature matching; no code-style inference. Squash merges can remove trailers, so this result remains a measured floor.

npx qmmit-cli modelcontextprotocol/inspector

Scan another repository

Try