AGENTS.md examples from real projects

darktable-orgAGENTS.md

darktable

darktable-org/darktable/AGENTS.md

when GTK3 has the Wayland backend gui/gtk.c calls into libwayland-client directly to detect server-side decoration support, but gtk+-3.0.pc does not list wayland-client. The symbols were

debeziumAGENTS.md

debezium

debezium/debezium/AGENTS.md

analyze the codebase, DO NOT set up build environments, DO NOT run scripts, or MCP, or skills, DO NOT look things up online, DO NOT make code changes, UNTIL

No other project uses it yet

openreplayAGENTS.md

openreplay / mcp_app

openreplay/openreplay/mcp_app/AGENTS.md

OpenReplay MCP App — Agent Guide Reference: https://modelcontextprotocol.github.io/ext-apps/api/documents/Patterns.html --- ## Project Structure ``` server.ts MCP server entry point (stdio transport) lib/ tools.ts All tool registrations (UI + internal) api.ts OpenReplay REST API client

VercelAGENTS.md

portless

vercel-labs/portless/AGENTS.md

change to a CLI command, flag, output, or environment variable must update the MCP tools in `packages/portless/src/mcp.ts` in the same change. `mcp.test.ts` reads `portless --help` and each tool command

No other project uses it yet

nearaiAGENTS.md

ironclaw / tests

nearai/ironclaw/tests/AGENTS.md

before durable storage without retaining inline media/blob base64 | `mcp.rs` | | User-registered and bundled hosted MCP servers register, authenticate, project active, restore, and invoke | `hosted_mcp_registration.rs` | | Web search/fetch runs the real

ChainlitAGENTS.md

chainlit

Chainlit/chainlit/AGENTS.md

over keeping legacy code in place. ## MCP-First Approach (CRITICAL) When available, **ALWAYS** prefer MCP servers over manual alternatives. Use **Context7** for docs/API references, **Serena** for code navigation/refactoring/memory, and **GitHub

tw93AGENTS.md

Kami

tw93/Kami/AGENTS.md

WeasyPrint-safe. Pure Python, no Node, ships in the package. - `scripts/mcp_server.py` - zero-dependency MCP stdio server exposing `kami_templates` / `kami_doctor` / `kami_render` / `kami_check` / `kami_deliver` / `kami_screenshot

No other project uses it yet

viarotel-orgAGENTS.md

escrcpy

viarotel-org/escrcpy/AGENTS.md

string | string[]` contract; business code stays untouched across internal changes. - [packages/madb/](../packages/madb/) is an MCP server for AI agent Android device control via ADB and yadb (32 tools

aureuserpAGENTS.md

aureuserp

aureuserp/aureuserp/AGENTS.md

important rather than explaining obvious details. === boost rules === # Laravel Boost - Laravel Boost is an MCP server that comes with powerful tools designed specifically for this application. Use them. ## Artisan

cocoindex-ioAGENTS.md

cocoindex

cocoindex-io/cocoindex/AGENTS.md

status` to confirm the root is this repo. We register no MCP server on purpose — an `ccc mcp` mode exists, but the CLI costs no context until invoked and behaves

No other project uses it yet

TencentCloudAGENTS.md

Octop

TencentCloud/Octop/AGENTS.md

agents/`, `api/routers/workspace*.py` | | `infra/connectors/` | Connector catalog, OAuth, MCP gateway, credential crypto | `api/routers/connectors.py`, `internal_mcp.py`, `agents/manager.py` (MCP assembly) | | `infra/control/` | Host control surfaces: `browser/`, `desktop/`, `mobile/` | `api/routers/browser/`, `desktop/`, `mobile/` | | `infra/cron/` | Cron jobs, triggers

rerun-ioAGENTS.md

rerun

rerun-io/rerun/AGENTS.md

output once the notification arrives. ### Driving a running egui UI (for agents) Two MCP servers let an agent see and click a running UI instead of guessing from code: - `rerun

CloudflareAGENTS.md

cloudflare-os / mcp-shared

cloudflare/cloudflare-os/packages/mcp-shared/AGENTS.md

portal` (one admin-configured portal). Not a Worker; a library both import, holding the MCP client, the OAuth chain, the account DO base, the resource-URL scope grammar

MoonshotAIAGENTS.md

kimi-cli

MoonshotAI/kimi-cli/AGENTS.md

software engineering workflows. It supports an interactive shell UI, ACP server mode for IDE integrations, and MCP tool loading. ## Tech stack - Python 3.12+ (tooling configured for 3.14) - CLI framework: Typer

MoonshotAIAGENTS.md

kimi-cli / tests_e2e

MoonshotAI/kimi-cli/tests_e2e/AGENTS.md

runs the flow until `END`. - W-36 MCP: use a Python fastmcp test server, load via `--mcp-config-file`, verify tool works. **Resilience and Errors** - W-37 Invalid JSON: malformed

apereoAGENTS.md

cas

apereo/cas/AGENTS.md

local branch | | [`cas-interrupt-notifications`](.claude/skills/cas-interrupt-notifications/SKILL.md) | `support/cas-server-support-interrupt*` | | [`cas-ldap`](.claude/skills/cas-ldap/SKILL.md) | LDAP modules | | [`cas-mcp-server`](.claude/skills/cas-mcp-server/SKILL.md) | `support/cas-server-support-mcp` | | [`cas-oauth-oidc-authentication`](.claude/skills/cas-oauth-oidc-authentication/SKILL.md) | OAuth/OIDC/UMA client authentication, access-token-protected endpoints, `OAuth20UserProfile

tambo-aiAGENTS.md

tambo

tambo-ai/tambo/docs/AGENTS.md

authentication/** (8 pages including index) - Auth.js, Auth0, Clerk, Supabase, Neon, WorkOS, Better Auth - connect-mcp-servers - Single page (not in subfolder) - **self-hosting/** (9 pages including index) - quickstart, environment-variables

No other project uses it yet

tambo-aiAGENTS.md

tambo / react-sdk

tambo-ai/tambo/react-sdk/AGENTS.md

return rich content including images, audio, or mixed media. This is particularly useful for MCP tools that already return content in the proper format. ### Key Hook System - **`useTambo()`** - Primary hook

No other project uses it yet

LangChainAGENTS.md

open-swe

langchain-ai/open-swe/AGENTS.md

composing generic capabilities such as plugins, automations, skills, or external MCP servers. First check whether existing capabilities, with small generic additions if needed, can deliver the feature. - Before changing

No other project uses it yet

MicrosoftAGENTS.md

fluentui-system-icons

microsoft/fluentui-system-icons/AGENTS.md

affected`) instead of using the underlying tooling directly - You have access to the Nx MCP server and its tools, use them to help the user - When answering questions about