superset
superset-sh/superset/AGENTS.md
reach its tools through `/mcp/plugins/ / ` on the API, which proxies to the vendor's MCP server or, for the plugins named in the `SUPERSET_HOSTED_PLUGINS` constant, serves them from
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.
superset-sh/superset/AGENTS.md
reach its tools through `/mcp/plugins/ / ` on the API, which proxies to the vendor's MCP server or, for the plugins named in the `SUPERSET_HOSTED_PLUGINS` constant, serves them from
open-metadata/OpenMetadata/AGENTS.md
operator/` — Kubernetes operator - `openmetadata-integration-tests/` — backend API integration tests (`*IT.java`) - `openmetadata-mcp/` — MCP server - `openmetadata-ui-core-components/` — canonical React component library - `openmetadata-ui/src/main/resources/ui/` — React frontend application - `openmetadata
storytold/lightcraft/AGENTS.md
crates/engine`): id, label, menu path, shortcut, params, enabled(), run(). UI, CLI, control channel and MCP all dispatch by id. Every slider is a `develop` control spec. - **Resolution independence:** settings
prowler-cloud/prowler/AGENTS.md
conventions | [SKILL.md](skills/prowler-ui/SKILL.md) | | `prowler-sdk-check` | Create new security checks | [SKILL.md](skills/prowler-sdk-check/SKILL.md) | | `prowler-mcp` | MCP server tools and models | [SKILL.md](skills/prowler-mcp/SKILL.md) | | `prowler-test-sdk` | SDK testing (pytest + moto) | [SKILL.md](skills/prowler-test-sdk/SKILL.md
prowler-cloud/prowler/docs/AGENTS.md
group is subscription-gated. One sanctioned exception: the Prowler MCP group is marked because the hosted server at `mcp.prowler.com` includes tools for Prowler Cloud-specific features, and its overview page
prowler-cloud/prowler/mcp_server/AGENTS.md
Prowler MCP Server - AI Agent Ruleset > **Skills Reference**: See [`prowler-mcp`](../skills/prowler-mcp/SKILL.md) ## Auto-invoke Skills When performing these actions, ALWAYS invoke the corresponding skill FIRST: | Action | Skill | |--------|-------| | Add changelog entry
Steady21 mentions in 2 weeks
No other project uses it yet
grokability/snipe-it/AGENTS.md
rather than explaining obvious details. === boost rules === # Laravel Boost ## Tools - Laravel Boost is an MCP server with tools designed specifically for this application. Prefer Boost tools over manual alternatives like
Steady15 mentions in 2 weeks
No other project uses it yet
yusufkaraaslan/Skill_Seekers/AGENTS.md
OpenRouter, Together AI, Fireworks AI, Markdown, LangChain, LlamaIndex, Haystack, Weaviate, ChromaDB, FAISS, Qdrant, Pinecone - **MCP Server:** FastMCP-based Model Context Protocol server for AI assistant integration ## Setup ```bash # REQUIRED before
livekit/agents/AGENTS.md
when working with this project. LiveKit offers both a CLI (`lk docs`) and an MCP server for browsing and searching its documentation. ### LiveKit CLI Install or update the CLI: - **macOS
No other project uses it yet
akitaonrails/ai-memory/AGENTS.md
workspace.package.version` in `Cargo.toml`. - **Async runtime:** `tokio` (full features). - **MCP/HTTP:** `rmcp` 2.2 (server SDK) + `axum` 0.8 for MCP HTTP, hooks, admin, `/api/v1`, and the built-in `/web` UI; `tower` / `tower-http
palmier-io/palmier-pro/AGENTS.md
internal Swift methods. Use connected MCP tools directly when available, or run the MCP server and use a temporary script or client to exercise it. - MCP tests must verify
bytebase/bytebase/AGENTS.md
List`. - Annotating an RPC `mcp_method_class = READ` or `WRITE` also changes what the MCP Access policy page promises, and nothing enforces that. Before changing one, read [mcp-capability-ladder.md](docs/design/mcp-capability-ladder.md#keeping
carla-simulator/carla/AGENTS.md
wrong one fails slowly. Ask the user, then record the answer. ### Optional: MCP server [`Util/AgenticTools/`](Util/AgenticTools/) serves the same skills over MCP (`list_skills`, `read_skill`, `check_prerequisites`, `get_config
microsoft/agent-framework/python/packages/ag-ui/AGENTS.md
history()`** - Converts persisted Agent Framework messages to bounded AG-UI Host history while retaining MCP widget payloads and model replay metadata - **`AGUIEventConverter`** - Converts between Agent Framework and AG-UI events
microsoft/agent-framework/python/packages/core/AGENTS.md
configured MCP tools' async contexts, then release them along with lazily connected MCP tools. `async with agent` delegates to these methods; a partially failed `open()` closes resources already entered. - Providers
microsoft/agent-framework/python/packages/declarative/AGENTS.md
sessions intentionally add connection overhead and lose server session continuity between invocations; shared session ownership requires an explicitly scoped custom `MCPToolHandler`. ## MCP Approval Context `InvokeMcpToolActionExecutor` binds evaluated headers to each
Steady16 mentions in 2 weeks
No other project uses it yet
microsoft/agent-framework/python/packages/gemini/AGENTS.md
mapping - **`get_file_search_tool()`** - Retrieval from Gemini file search stores - **`get_mcp_tool()`** - Model Context Protocol server integration ## Usage ```python from agent_framework import Content, Message from agent_framework.gemini import
Steady16 mentions in 2 weeks
No other project uses it yet
microsoft/agent-framework/python/packages/hosting-mcp/AGENTS.md
result)` converts an Agent Framework response or message to MCP `ContentBlock` values. ## Boundary This package does not provide a server, routes, transport lifecycle, authentication, authorization, session-key policy, concurrency policy
Steady16 mentions in 2 weeks
No other project uses it yet
microsoft/agent-framework/python/packages/openai/AGENTS.md
process and must not be serialized as MCP items. An approval is hosted when its function call carries a `server_label` in `function_call.additional_properties`; approvals without that metadata are local
google/ax/AGENTS.md
Control API internal/workspace git clone / inline files / skills dir (MCP is spec-only; agents read it via the metadata server) internal/{tunnel,guest,metadata} k8s port-forward, in-sandbox guest
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.