Registry
Browse stored services, provider pages, docs, and tooling that Query Here already knows about.
A powerful and flexible Kubernetes Model Context Protocol (MCP) server implementation with support for Kubernetes and OpenShift.
Nothing ever goes to stdout — stdout is the MCP protocol channel. npm install npm run verify # type-check + lint + format:check + test + build npm run test:watch # interactive tests
OverviewHow tool use worksTutorial: Build a tool-using agentDefine toolsHandle tool callsParallel tool useTool Runner (SDK)Strict tool useTool use with prompt cachingServer toolsTroubleshootingTool referenceWeb search toolWeb fetch toolCode execution toolMemory toolBash toolComputer use toolText editor tool ... Reduce hallucinationsIncrease output consistencyMitigate jailbreaksStreaming refusalsReduce prompt leak ... Admin API overviewData residencyWorkspacesUsage and Cost APIClaude Code Analytics APIAPI and data retention
Many teams use both: CLI for daily development, SDK for production. Workflows translate directly between them. Managed Agents is a hosted REST API: Anthropic runs the agent and the sandbox, and your application sends events and streams back results.
Complete API reference for the Python Agent SDK, including all functions, types, and classes.
Complete API reference for the TypeScript Agent SDK, including all functions, types, and interfaces.
Trust verification CLI for AI packages — check MCP servers, A2A agents, AI tools, and LLMs before you install
SDK for building AI agents with Claude Code's capabilities . Programmatically interact with Claude to build autonomous agents that can understand codebases, edit files, and execute workflows..
Agent Experience (AX) skill for agent-usable APIs, MCP tools, OpenAPI specs, llms.txt, manifests, payments, and machine-readable errors.
# Run directly with npx npx -y browser-devtools-cli --help npx -y node-devtools-cli --help # Or install globally npm install -g browser-devtools-mcp browser-devtools-cli --help node-devtools-cli --help
The OpenAI Agents SDK gives us a handy SandboxAgent class, a superset of Agent which comes preloaded with the tools to attach to a remotely running sandbox . It also offers a ShellTool class which adds extra guardrails to our commands.
Claude Code skill for static audit of OpenClaw config and agent proposals — llms.txt-first research, F1–F12 incident library, Notion-bridged Galatea audit workflow.
Promptfoo will skip its preflight API key validation, but the SDK still needs to be able to authenticate on its own. Apart from using the Anthropic API, you can also use AWS Bedrock and Google Vertex AI. ... Follow the Claude Code Bedrock documentation to make credentials available to Claude Agent ...
The agent can call external APIs defined by OpenAPI specifications. For a JavaScript version of this example, see the sample in the Azure SDK for JavaScript repository on GitHub. import { DefaultAzureCredential } from "@azure/identity"; import { AIProjectClient, OpenApiTool, OpenApiFunctionDefinition, OpenApiAnonymousAuthDetails, } from "@azure/ai-projects"; import * as fs from "fs"; import * as path from "path"; // Format: "https://resource_name.ai.azure.com/api/projects/project_name" const PROJECT_ENDPOINT = "your_project_endpoint"; const weatherSpecPath = path.resolve(__dirname, "../assets"
... Download the .dxt configuration ... clone https://github.com/contentful/contentful-mcp-server.git cd contentful-mcp-server npm install npm run build...
Control a Xiaomi Robot Vacuum X20+ via the xiao CLI. Agent-ready: AGENTS.md, llms.txt, SKILL.md, --json output, canonical exit codes.
At least one of these data sources, with data: A warehouse, a lakehouse, a Power BI semantic model, a KQL database, a mirrored database, or an ontology. You must have read access to the data source. Fabric data agents can also function as MCP servers. When used as an MCP server, a Fabric data agent exposes a single tool. This tool represents the data agent itself, so external AI systems can interact with it through the MCP protocol.
The dbt MCP server provides a standardized framework that lets you integrate AI applications with dbt‑managed data assets across different data platforms . This ensures consistent, governed access to models, metrics, lineage, and freshness ...
Install · Usage · Bridge two ... with an MCP client · Types · Peer Dependencies · License · npm install @decocms/mcp-utils @modelcontextprotocol/sdk ·...
Turn any personal website into an LLM-discoverable API. Daily scraper + static JSON endpoints + llms.txt, all hosted free on GitHub Pages.
When to use the official SDK: You need maximum control or have specific architectural requirements. In this case, we encourage referencing FastMCP's implementation to avoid common pitfalls. npm install fastmcp ·
Model Context Protocol (MCP) server that allows AI chatbots (Claude, ChatGPT, Gemini, etc.) to search, explore, and analyze datasets from data.gouv.fr, the French national Open Data platform, directly through conversation .
GMGN OpenAPI skills for AI Agent — query tokens, wallets, and market data, and execute on-chain trades across Solana, BSC, and Base. - GMGNAI/gmgn-skills
API documentation — Use docs/api.md for endpoint overview and usage notes, and docs/openapi.json for schema/tooling integration. Security policy — Review disclosure and policy details in SECURITY.md, and run pnpm run preflight:public before public releases. ... Apache 2.0 — Free for personal and commercial use. Built with pixels and passion. Claw-Empire — Where AI agents come to work.
It exposes every action, helper, and agent tool — so any MCP-compatible AI agent (Claude Code, Cursor, Windsurf, VS Code Copilot, etc.) can discover and use the full platform. ... { "mcpServers": { "mindstudio": { "command": "mindstudio", "args": ["mcp"], "env": { "MINDSTUDIO_API_KEY": "your-api-key" } } } } ... It contains a compact, complete reference of all methods with their required parameters and output keys — optimized for LLM context windows. The raw OpenAPI spec that this SDK is generated from is available at:
Get started with some examples or check out the docs to learn more. ... import os from openhands.sdk import LLM, Agent, Conversation, Tool from openhands.tools.file_editor import FileEditorTool from openhands.tools.task_tracker import TaskTrackerTool from openhands.tools.terminal import TerminalTool llm = LLM( model="anthropic/claude-sonnet-4-5-20250929", api_key=os.getenv("LLM_API_KEY"), ) agent = Agent( llm=llm, tools=[ Tool(name=TerminalTool.name), Tool(name=FileEditorTool.name), Tool(name=TaskTrackerTool.name), ], ) cwd = os.getcwd() conversation = Conversation(agent=agent, workspace=cwd) conversation.send_message("Write 3 facts about the current project into FACTS.txt.") conversation.run() print("All done!")
GMGN Agent API — a skill-based MCP architecture designed for AI agents and natural language workflows. GMGN OpenAPI — a traditional REST API documented on GitHub for developers who want raw endpoint access .
Streaming InputStream responses in real-timeConnect MCP serversDefine custom toolsTool searchHandling PermissionsUser approvals and inputControl execution with hooksFile checkpointingStructured outputs in the SDKHosting the Agent SDKSecurely deploying AI agentsModifying system promptsSubagents in the SDKSlash Commands in the SDKAgent Skills in the SDKTrack cost and usageTodo ListsPlugins in the SDK ... Reduce hallucinationsIncrease output consistencyMitigate jailbreaksStreaming refusalsReduce prompt leak ... Admin API overviewData residencyWorkspacesUsage and Cost APIClaude Code Analytics APIAPI and data retention
Step-by-step guide to making your site discoverable by AI agents. Add llms.txt, expose an OpenAPI spec, ship an MCP server, and unlock the 7 signals NHS scores against.
Imagine Peak Studios — product strategy, sonic direction, and AI-assisted systems development. Live at imaginepeakstudios.com. Vanilla HTML/CSS/JS, editorial briefs, AI-agent-aware (llms.txt + markdown companions), deployed on Cloudflare Pages.
Everything AI agents need to master the full Kaltura platform — The Agentic Digital Experience Platform. Live-tested API guides with curl examples and end-to-end test scripts. Agent Skill, llms.txt, and Context7 ready.
Agent-optimized personal site. llms.txt, agents.json, JSON-LD.
Turn Go structs into production CLIs with flags, env vars, config files, enums, validation, shell completion, and structured errors. Make any AI agent context aware of your CLIs through auto-generated JSON Schema, AGENTS.md, llms.txt, and MCP interfaces. Built on Cobra.
mcp-llms - This shows how to use an MCP server to iteratively explore the llms.txt file with your MCP client
An opinionated Astro Starlight template for AI-native documentation: Diátaxis-organized, schema-validated, with raw-markdown twins at /<slug>.md and an /llms.txt index any agent can read.
[!NOTE] MCP Proxy is what FastMCP uses to enable streamable HTTP and SSE. npm install mcp-proxy · MCP Proxy supports two invocation patterns: Simple usage (no mcp-proxy options): npx mcp-proxy npx -y @anthropic/mcp-server-filesystem /path · ...
import asyncio from langchain_openai ... print(result) asyncio.run(main()) → Full Python Agent Documentation · npm install mcp-use @langchain/openai ·...
MCP Apps SDK — Enable MCP servers to display interactive user interfaces in conversational clients.
The official Java SDK for Model Context Protocol server s and clients.
Build MCP clients that can connect to any MCP server · Use standard transports like stdio and Streamable HTTP · npm install @modelcontextprotocol/sdk zod · This SDK has a required peer dependency on zod for schema validation.
AI Readiness toolkit for Astro — generates llms.txt, agents.md, .well-known/mcp.json, named-bot rules in robots.txt, and ships JSON-LD helper components.
The 2026 focus has shifted significantly toward making OpenAPI work better with LLMs and AI agents . The SIG is investigating what additional metadata or structural information OpenAPI documents need to be more “agent-ready” — including ...
Full context of parallel.ai public content made agent-friendly
npx -y @phantom/mcp-server@latest · Install the package globally for faster startup: npm install -g @phantom/mcp-server@latest · Then run: phantom-mcp · Add the MCP server to your Claude Desktop configuration file: Location: macOS: ...
A CLI for interacting with llms.txt Markdown files.
Search and query KyberSwap docs via llms.txt and Documentation MCP · Two surfaces help agents discover and understand KyberSwap before taking action: a flat documentation index that works everywhere, and the MCP Server's typed tool manifest for agents that prefer structured, schema-driven discovery.
@spectre-ai/docs — offline documentation bundle for Spectre AI (llms.txt, recipes, agent prompts)
Turn any function into an agent tool with @tool. The docstring becomes the LLM's tool description.
Free agent-readiness scanner: score your site for robots.txt, llms.txt, sitemaps, MCP, OAuth & agent skills—plus free llms.txt & agent.json generators at llmsok.com
Automate GEO audits, llms.txt generation, and competitor tracking for any site with a CLI and WordPress plugin
For local runs from this repository, ... When the package is available on npm, install the CLI globally: npm install -g @transcend-io/mcp-server-dsr ·...
Search engine for AI agents — ranks sites by agentic readiness (llms.txt, OpenAPI, MCP, ai-plugin). MCP server, REST API, full-text search. 8,000+ indexed sites.
WaniWani SDK - MCP event tracking, widget framework, and tools
A Convex component that auto-generates, caches, and serves llms.txt, agents.md, and llms-full.txt from your Convex backend. Register it with app.use(agentReady), drop the widget into your React or Svelte frontend, and your app is discoverable by AI agents. No external hosting required.
MCP servers provide an alternative to the specialized development or complex integrations needed to utilize AI models. Other essential characteristics of MCP servers include: Integration enablement: MCP servers provide a standardized, unified protocol that allows AI agents to connect to various systems without the need for custom API patterns for each use case, removing the requirement for tailored integrations.