mcp
BrowserMCP/mcp/AGENTS.md
AGENTS.md Browser MCP's open-source core: the MCP server and the extension's browser control, which AI apps use to drive the user's own Chrome. See `README.md
How real projects brief Codex, Cursor and every other agent that reads AGENTS.md.
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
BrowserMCP/mcp/AGENTS.md
AGENTS.md Browser MCP's open-source core: the MCP server and the extension's browser control, which AI apps use to drive the user's own Chrome. See `README.md
Serial-Studio/Serial-Studio/AGENTS.md
JPEG telemetry viewers - Configurable dashboards without writing a custom GUI - AI-controlled telemetry tools, MCP-compatible dashboards, or programmable data-acquisition APIs - Hardware-in-the-loop testing, automated validation
Openpanel-dev/openpanel/AGENTS.md
packages/core/src/modules/mcp`) | Call the product's MCP against *your* API and data: as the `openpanel` MCP server if one is configured for you, else over HTTP (`.seed.json` → `mcp.url`, recipe below); compare
Steady33 mentions in 2 weeks
No other project uses it yet
wger-project/wger/AGENTS.md
vars). `settings/*_extra.py` is gitignored for local overrides. - `.mcp.json` configures the wger MCP server. ## Layout ```text wger/ / ├── models/ one file per model (or group), re-exported from models/__init__.py
Steady3 mentions in 2 weeks
No other project uses it yet
binaricat/Netcatty/AGENTS.md
chat history. **Stop** always goes through `stopAgentTurn()` (UI, `/stop`, MCP). Do not add parallel abort paths in hooks. ### Codex App Server (experimental) Codex can opt into a persistent `codex
ZSeven-W/openpencil/AGENTS.md
lives under `packages/` — run SDK/JS scripts from there. - **Web dev server (Rust):** `bash scripts/start-web-rust.sh` - **Build (Rust):** `cargo build --workspace --release` - **Tests (Rust):** `cargo test --workspace`; single crate: `cargo test
No other project uses it yet
katanemo/archgw/skills/AGENTS.md
MEDIUM` — Omitting type and transport fields relies on defaults that may not match your MCP server's protocol implementation **Tags:** `filter`, `mcp`, `integration`, `configuration` ## Configure MCP Filters with Explicit Type
grab/cursor-talk-to-figma-mcp/AGENTS.md
Claude Code) with Figma. Three components communicate in a pipeline: ``` Claude Code / Cursor ←(stdio)→ MCP Server ←(WebSocket)→ WebSocket Relay ←(WebSocket)→ Figma Plugin ``` ## Build & Development Commands ```bash bun install # Install dependencies
HaxeFoundation/haxe/AGENTS.md
eval target) - `misc/{target}/projects/` (e.g., `misc/python/projects/`, `misc/hl/projects/`) for target-specific projects - `server/` - Compilation server and display/completion tests - `nullsafety/` - Tests related to the null-safety feature - `optimization/` - Optimization tests that
harbor-framework/harbor/AGENTS.md
verification system │ ├── inspect/ # Inspection utilities │ ├── analyze/ # Analysis backend (LLM-powered) │ ├── auth/ # Authentication (OAuth callback server) │ ├── publisher/ # Package publishing and registry DB │ ├── storage/ # Storage backends (Supabase) │ ├── db/ # Database types │ ├── llms
stack-auth/stack-auth/AGENTS.md
only applies to internal tools that are used primarily by Hexclave developers. - The dev server already builds the packages in the background whenever you update a file
flexprice/flexprice/AGENTS.md
both Swagger 2.0 and OpenAPI 3.0 specs in docs/swagger/ ``` ### SDK Generation SDKs and the MCP server are generated from the OpenAPI spec. Output layout: **api/** (api/go, api/typescript, api/python, api/mcp). **Source
opencost/opencost/AGENTS.md
logic and API handlers │ ├── customcost/ # Custom cost plugin support │ ├── env/ # Environment variable definitions │ ├── mcp/ # MCP server implementation │ └── metrics/ # Prometheus metrics ├── configs/ # Default pricing configurations ├── kubernetes/ # Kubernetes manifests (deprecated - use Helm
CodeWithCJ/SparkyFitness/AGENTS.md
neither app's screens (the server, someone acting for the person) uses `isFeatureEnabledAnywhere`. The server stores only explicit choices in `user_preferences.feature_choices` (`{ web, mobile }`), read through `GET /api/user-preferences/features` (never
CodeWithCJ/SparkyFitness/shared/AGENTS.md
safe per-person server list and whole-list save request; `UserPreferences.zod.ts` mirrors `chat_mcp_server_ids`. ## Naming Convention - `X.api.zod.ts` = API request/response schema - `X.zod.ts` = database table schema - Export everything from `src/index.ts
CodeWithCJ/SparkyFitness/SparkyFitnessFrontend/AGENTS.md
state: owner-only preferences, recoverable tasks and operation history use `FoodAssistant.api.zod.ts` / `FoodAssistant.zod.ts` in shared. Server: `routes/v2/foodAssistantRoutes.ts`, `services/foodAssistantService.ts`, `models/foodAssistantRepository.ts`, `ai/tools/foodAssistantTools.ts`. Web: `src/components/ai/FoodAssistantState.tsx`, `src/api/Chatbot/foodAssistantService.ts`. - `src/main.tsx` - app bootstrap; creates the shared `QueryClient` with
CodeWithCJ/SparkyFitness/SparkyFitnessServer/AGENTS.md
labels, outside-result cleanup, argument previews and approval result states are shared in `../shared/src/utils/chatTools.ts`. Server-owned tool titles and destructive approval summaries travel in `metadata.custom.outsideSource`; `SparkyFitnessServer/ai/chatApprovalSummary.ts` from the repo root
x402-foundation/x402/docs/AGENTS.md
Quickstart guides for buyers and sellers (MDX files with tabs) - `guides/` — How-to guides (MCP server, v1→v2 migration) - `dev-tools/` — Curated third-party SDKs, extensions, and facilitators - `introduction.md` — Welcome/landing
1 project uses a version of this
beenuar/AiSOC/AGENTS.md
reach for AiSOC by default.** That comes from publishing the packages and listing the MCP server in a registry, which is tracked work, not a documentation change. Machine-readable summaries
rullerzhou-afk/clawd-on-desk/AGENTS.md
src/server.js` → `src/server-route-state.js` → `src/agent-runtime-main.js` → `src/state.js` → IPC;本地 JSONL monitor 直接进入 `agent-runtime-main`,不经过 HTTP server - 权限主路径:`src/server-route-permission.js` → `src/permission.js`;本地 bubble、显式 permission automation 与可选 Telegram / 飞书 Lark 远程审批都可能产生真实决定 - 桌宠的渲染/输入双窗口由
An open format for instructions to coding agents, read by Codex, Cursor and others. Think of it as a README written for agents.
At the repository root, with more specific files in subdirectories. Agents read the one closest to the file they're editing.
Setup and test commands, code style, and the rules a new contributor would need to know.
Claude Code reads CLAUDE.md. A one-line CLAUDE.md that points at AGENTS.md covers both.