VS Code MCP servers

MCP server for Adobe After Effects — comp/layer introspection, undo-grouped ops, frame rendering.

WH-347 certified payroll columns 5-9, fringe 6B reconciliation and PTO accrual balances.

Maths a model gets wrong: units with dimensional checking, equations, sheets. 5 tools, local.

AEO audit of any URL + French open data: website prices, public tenders, editorial calendar.

Lets your AI find open-source tools on GitHub and install them as sandboxed MCP tools.

Japan public intelligence for AI agents: earthquakes, weather, typhoons, EDINET filings. Keyless.

Stdio MCP server that inspects and (with confirmation) mutates one VPS over SSH.

Read and act on Safari — history, tabs and reading list, writes off by default

Scopus search, author and affiliation profiles, citation data, and PlumX metrics via Elsevier APIs.

Search, read and act on Apple Reminders — lists, due dates, writes off by default

Give AI agents Git history tools: commit search, file history, blame, contributors, ref diffs.

Auditable memory for AI agents: provable deletion, tamper-evident audit, time-travel recall.

Autonomous spec-to-product coding-agent CLI with an MCP server exposing 39 tools over stdio.

Deterministic inspect, safe repair, and JSON Schema validation for agent JSON. No LLM.

Audits any website for AI agent readiness and safety, scoring prompt injection risk and llms.txt.

Ask TypeSafe Jev yes/no, choice and score questions and receive structured model judgments.

Self-hosted, Tavily-compatible web search, extract, crawl and map tools for AI agents.

Local MCP analysis for CSV, TSV, Excel, JSON and Parquet: summaries, outliers and relationships.

Local, offline transcription, speakers, keyframes, on-screen text and review of any audio or video.

Free 0-100 score: can AI engines cite a site? Plus citation checks with your own API keys.

Hand browser work off to a server-side agent: read the page as a table, act, then verify.

AI agents use your Obsidian secrets by name — values never reach their context.