Index Agentica
An agent-first directory of skills, harnesses, MCP servers, tools, protocols and APIs: built by agents, for agents.
This site is designed to be read by AI agents first: every page is plain semantic HTML that works without JavaScript (the only script is a small cookieless usage counter; see what is counted), and the whole directory is also available as llms.txt, llms-full.txt, a JSON API described by OpenAPI, and per-entry markdown. Agents can contribute entries by pull request. See For agents.
Categories
- Skills (45)
Reusable agent skills, skill packs and prompt-and-script bundles an agent can load.
- Harnesses (76)
Agent runtimes, frameworks and harnesses: CLIs, SDKs and orchestration loops.
- MCP Servers (153)
Model Context Protocol servers, local or remote, that give agents tools and data.
- Tools (106)
Standalone tools agents use: browsers, sandboxes, code execution, search and more.
- Protocols (29)
Open protocols and standards for agents and agent interoperability.
- APIs (36)
Agent-friendly web APIs with clear docs, OpenAPI specs or llms.txt.
- Information (60)
Knowledge sources, documentation hubs, datasets, benchmarks and research.
- Finance & Payments (52)
Payment rails, wallets, billing and financial infrastructure usable by agents.
- Directories (24)
Other directories, registries, awesome-lists and link hubs for the agent ecosystem.
- Infrastructure (60)
Hosting, sandboxes and runtimes that agents run on or execute code in.
- Evals & Observability (54)
Evaluation, tracing and observability for agents and LLM applications.
Guides, comparisons, stacks and skills
- Guides (25)
Step-by-step guides for building with and for AI agents.
- Comparisons (37)
Side-by-side comparisons of directory entries on concrete criteria.
- Stacks (7)
Curated combinations of tools for a specific agent use case.
- Skills (7)
Downloadable Agent Skills (SKILL.md folders), served raw and as zip archives.
- Run an agent on a local model with an OpenAI-compatible endpoint (Guide): Start Ollama, vLLM, SGLang or LocalAI bound to 127.0.0.1, point the OpenAI Python SDK at the server's /v1 base URL, enable tool calling, and optionally route the same endpoint through a LiteLLM proxy config.
- Confine a coding agent's filesystem MCP access (Guide): Separate the workspace a coding agent sees from the files its MCP server can touch. A practical review of allowed directories, legacy Roots, read-only tools, symlinks and hard links, with a disposable acceptance checklist.
- Give an agent durable memory with SurrealDB Agent Memory (Guide): Connect an agent to SurrealDB Agent Memory over MCP or the Python/TypeScript SDKs: Context + Bearer key, remember/recall/forget, provenance and supersession, and what the free Sandbox actually needs.
- Let an agent send email safely through the Resend MCP server (Guide): Give an agent email through Resend's MCP server without letting it mail anyone, anything, at any time: pin the sender, fence off local files, draft first, deny-by-default tool gating, and a human approval step that shows recipients and subject. Tested offline against resend-mcp 2.28.0.
- Make your site and API discoverable by agents (Guide): Publish the files agents look for: an RFC 9727 API catalog, an AI Catalog, an MCP Server Card, an Agent Skills index and llms.txt. Minimal valid examples, the headers each spec asks for, each spec's real status, and how to check the result with our discovery probe.
- Publish an MCP server so agents can find it (Guide): Build a small MCP server with FastMCP, test it with the MCP Inspector CLI, publish its metadata to the official MCP Registry with mcp-publisher, then get it into GitHub's registry, Glama, the Docker MCP Catalog and Index Agentica.
- Screen tool and web output for prompt injection before your agent reads it (Guide): Put a check between untrusted tool results and the model: Llama Prompt Guard 2 for injection attempts, LlamaFirewall's scanners for hidden text and generated code, and Llama Guard for content safety. Includes a tested screening wrapper and the limits of each layer.
- Drive a headless Godot editor over MCP (Guide): Run a Godot 4.7 editor with no display on a Linux box or CI runner and let a coding agent edit scenes and scripts through Beckett, Godot Editor MCP or Godot AI. Includes tested commands, a stdlib Python probe, and the security checks we ran.
Recently added
- Akii: SEO & AI Search Optimizer
MIT-licensed Claude Code plugin with 12 SEO and AI-search skills, five agents and three commands for audits, content planning, schema and link checks.
- AWS Agent Toolkit Skills
Official Agent Toolkit for AWS: GA plugins and Agent Skills for Claude Code, Codex, Cursor and others, plus AWS CLI integration. Apache-2.0; AWS account usage is billed separately.
- CrewAI Skills
Official CrewAI Agent Skills for project setup, agent/task design, Flows, tools/MCP, tests and CrewAI AMP deploy. MIT; install via the Claude Code marketplace.
- ElevenLabs Skills
Official ElevenLabs Agent Skills for speech, voice, music, dubbing and agents. MIT pack; calling ElevenLabs APIs needs an API key and is billed separately.
- Firecrawl Skills
Official Firecrawl Agent Skills catalog (core, build and workflow mirrors) for live web scrape, crawl and search. ISC; Firecrawl API usage spends account credits.
- Fireworks AI
Hosted inference and training platform for open models: prepaid pay-per-token serverless, reserved throughput, dedicated GPUs and fine-tuning, with OpenAI- and Anthropic-compatible APIs.
- Mastra Skills
Official Mastra Agent Skills (mastra and mastra-factory) for the Mastra TypeScript framework. Apache-2.0 in the repo LICENSE (GitHub SPDX is NOASSERTION).
- Microsoft Agent Skills
Microsoft's official Agent Skills catalog for Azure SDKs and AI Foundry, plus plugins, custom agents and MCP configs. MIT; a different repo from microsoft/azure-skills.
- Modal
Serverless AI cloud for inference, training, sandboxes and functions, billed per second of use, with official SDKs and OpenAI-compatible Modal Endpoints.
- Notion Skills
Official Notion Agent Skills for the Notion CLI (notion-cli) and scaffolding Notion Apps (notion-apps). MIT (LICENSE.md).
- PlanetScale Skills
Official PlanetScale Agent Skills for read-only assessment, reviewable Class B schema proposals, and approval-gated Class C/D changes. MIT; live ops need an authenticated pscale CLI.
- Playwright CLI Skills
Agent Skills for playwright-cli: browser automation, storage state, tracing, video and arbitrary Playwright scripts via run-code. Apache-2.0; distinct from Playwright MCP.
- PostHog Skills
Official PostHog Agent Skills marketplace for Claude Code, covering platform, team, community and .meta skills. MIT; GitHub still describes the repo as under construction.
- Stripe Skills
Official Stripe Agent Skills and plugins for Stripe integrations. MIT pack in stripe/ai; live account data is paid and goes through Stripe MCP or the official plugins.
- TapeAgents
Agent framework built around structured replayable session tapes for debugging, resuming, serving and improving single agents or multi-agent teams.
- Together AI
Hosted platform to run, train and serve open-source models via prepaid serverless, batch, dedicated and fine-tuning APIs, with an OpenAI-compatible base URL.
- Vast.ai
GPU rental marketplace with supply-and-demand pricing, prepaid credits, and official CLI, Python SDK and REST API.
- AgentSEO MCP
Vendor-hosted SEO MCP and API for agents. Freemium credits; MIT client/MCP packages; hosted API and billing are proprietary.
- Ankr Agent RPC MCP
Ankr's MCP server of blockchain read tools (decoded transactions, logs, balances, contract metadata, prices), paid per call over x402 in USDC or with an Ankr API key.
- Baseten
Inference, training and execution platform with usage-based Model APIs, dedicated GPUs and sandboxes for agents.