# mcp.so vs Models.dev

mcp.so records 286,704 monthly visits with -3% month-over-month growth and Free pricing. Models.dev records 200,451 monthly visits with -3.9% growth and Free pricing.

| Metric | [mcp.so](https://openaitools.app/tool/mcp-server) | [Models.dev](https://openaitools.app/tool/models-dev) |
| :--- | :--- | :--- |
| Website URL | https://mcp.so | https://models.dev |
| Categories | AI Tools Directory, Large Language Models (LLMs), AI Developer Tools | AI Models, AI API, Open Source AI Models, AI Tools Directory |
| Pricing Model | Free | Free |
| Monthly Visits | 286,704 | 200,451 |
| MoM Growth Rate | -3% | -3.9% |
| Primary Market | United States | China |
| Direct Visits | 107,648 | 136,316 |
| Review Score | 4.2 | 4.4 |
| Saved Count | 0 | 0 |
| Supported Platforms | Website | Website |

## mcp.so

mcp.so organises the fast-growing Model Context Protocol ecosystem in one searchable place. You can browse servers by category (developer tools, AI and agents, cloud infrastructure, memory and knowledge, media and design), inspect remote endpoints, and read setup details before wiring a server into Claude, Cursor or another MCP-compatible client. Featured and trending sections surface popular or newly added servers, and rankings help you gauge what the community is adopting.

Beyond raw server listings, the site collects MCP clients (apps, IDEs and frameworks that speak the protocol), official CLI tools such as Bun, Cloudflare Wrangler, DuckDB and FFmpeg, reusable agent loops and skills, and curated collections. A feed tracks new arrivals, and submit/claim flows let maintainers add or take ownership of their own listings.

For anyone building with AI agents, mcp.so works as a discovery and reference layer: pick a capability, check how the server connects and authenticates, follow the setup guide, and keep an eye on what the community is installing each week. It is a directory, so it does not itself host or run the servers it lists.

**Pricing & Plans:** Free to browse and use the directory. Advertising, featured placement and claiming listings are handled through the site; no subscription is required for normal browsing.

- **Searchable MCP server directory:** Find servers by name, category, tag, runtime or integration, with featured, trending and newest sections that track community activity.
- **Remote endpoints and setup guides:** Review hosted MCP endpoints, authentication requirements and per-client setup instructions before you connect anything.
- **Clients, CLI tools and skills:** Discover MCP-compatible clients, official command-line tools, agent loops and reusable Claude/Codex skills in dedicated sections.
- **Submit and claim listings:** Maintainers can publish new servers and claim existing listings so entries stay accurate and attributable.
- **Categories, rankings and feed:** Browse top categories, compare curated selections and follow a live feed of newly added servers, tools and skills.

**Strengths:** Broad, regularly updated coverage of MCP servers and clients; Setup and authentication details gathered together in one place; Free to use with no account needed for browsing; Includes CLI tools, agent skills and curated collections beyond raw listings

**Limitations:** Listings are community-submitted, so quality and freshness can vary; It is a directory only, not a place to run or host MCP servers; Ad and featured placements can push less relevant results higher

[Profile (Markdown)](https://openaitools.app/tool/mcp-server.md)

## Models.dev

Models.dev exists to answer a very practical developer question: which model should I use, and what will it cost? The site organises every entry under a canonical identifier in the form provider/model, so the same model served by several providers can be compared directly rather than guessed at. Columns cover context window, maximum output, whether input and output are supported, reasoning, tool calling, structured output, temperature control, open versus closed weights, price per million tokens, and release and update dates.

Because model releases move fast, the catalogue is built to stay current, with sortable and searchable tables that let you scan by lab or provider and filter down to what matters. Entries include both closed flagship models and open-weight alternatives, making it useful for cost planning as well as capability research.

The project is open source and free to use, and it is intended to be consumed programmatically. Developers can pull the catalogue into their own tooling through a JSON API or a type-safe SDK, which makes it a practical backend for dashboards, routing logic, or internal cost calculators rather than just a reference page to browse.

**Pricing & Plans:** Models.dev is free and open source. It is a reference database, so the prices it lists are the per-million-token rates charged by the model providers themselves, not a fee for using the site.

- **Canonical model identifiers:** Every model uses a consistent provider/model format so the same model across providers can be compared directly.
- **Specification comparison:** Side-by-side context window, output limit, reasoning, tool calling, structured output, and temperature support.
- **Pricing transparency:** Input and output prices per million tokens listed alongside release and update dates.
- **Open and closed models:** Covers closed flagship APIs and open-weight models from many labs in one sortable catalogue.
- **Developer access:** Consume the catalogue through a JSON API or a type-safe SDK for your own tools and dashboards.

**Strengths:** Free and open source with no account required; Consistent canonical identifiers make cross-provider comparison reliable; Covers pricing, limits, and capabilities in one sortable table; Available as a JSON API and type-safe SDK for programmatic use

**Limitations:** It is a reference catalogue, not an inference or hosting service; Data quality depends on community and maintainer updates keeping pace with releases; Interface is aimed at developers and offers little guidance for non-technical users

[Profile (Markdown)](https://openaitools.app/tool/models-dev.md)

## Frequently Asked Questions

### How do mcp.so and Models.dev compare in monthly traffic?

mcp.so has 286,704 monthly visits, while Models.dev has 200,451. Traffic estimates describe audience size, not product quality.

### How do their growth rates compare?

mcp.so has a month-over-month growth rate of -3%; Models.dev has -3.9%.

### How does pricing compare?

mcp.so: Free. Free to browse and use the directory. Advertising, featured placement and claiming listings are handled through the site; no subscription is required for normal browsing. Models.dev: Free. Models.dev is free and open source. It is a reference database, so the prices it lists are the per-million-token rates charged by the model providers themselves, not a fee for using the site.

## Alternatives

| # | Tool Name | Monthly Visits | MoM Growth Rate | Pricing Model | Summary | Profile (Markdown) |
| :--- | :--- | :--- | :--- | :--- | :--- | :--- |
| 1 | [Dang.ai](https://openaitools.app/tool/dang-ai) | 552,907 | +17.5% | Free | Curated directory and search engine cataloging thousands of general AI products rather than MCP developer integrations. | [.md](https://openaitools.app/tool/dang-ai.md) |
| 2 | [Futurepedia](https://openaitools.app/tool/futurepedia-find-the-best-ai-tools-software) | 527,719 | +22.5% | Free | Massive general AI tools directory, offering broader software discovery but less focus on specific MCP servers. | [.md](https://openaitools.app/tool/futurepedia-find-the-best-ai-tools-software.md) |
| 3 | [SkillsMP — Agent Skills Marketplace](https://openaitools.app/tool/agent-skills-marketplace) | 470,744 | -3.7% | Free | Independent public directory indexing open-source agent skill files and MCP integrations for AI developers. | [.md](https://openaitools.app/tool/agent-skills-marketplace.md) |
| 4 | [Stork](https://openaitools.app/tool/stork) | 201,544 | +2.3% | Free | Includes model pricing trackers and developer news alongside tools directories, but less focused on raw API specs. | [.md](https://openaitools.app/tool/stork.md) |
| 5 | [AI Agent Store](https://openaitools.app/tool/ai-agent-store) | 169,388 | -5.4% | Freemium, Free Trial, Paid | Marketplace connecting users with ready-made AI agents and starter kits, but with fewer raw developer MCP tools. | [.md](https://openaitools.app/tool/ai-agent-store.md) |
| 6 | [Cursor Directory](https://openaitools.app/tool/cursor-directory) | 125,466 | +5.3% | Free | Community hub focused specifically on discovering and installing MCP servers and plugins for the Cursor IDE. | [.md](https://openaitools.app/tool/cursor-directory.md) |
| 7 | [Easy With AI](https://openaitools.app/tool/easywithai-com) | 119,734 | -2.7% | Freemium, Free Trial, Free | A hand-curated directory for discovering AI tools and resources | [.md](https://openaitools.app/tool/easywithai-com.md) |
| 8 | [ToolCenter](https://openaitools.app/tool/toolcenter) | 66,647 | +3.2% | Free | Curated online directory cataloging productivity and AI software, lacking specialized categorization for MCP protocol servers. | [.md](https://openaitools.app/tool/toolcenter.md) |
| 9 | [InfraBase.ai](https://openaitools.app/tool/infrabase-ai) | 39,072 | -13.6% | Free | Catalogues and compares AI infrastructure tools and services across categories, but lacks deep per-token pricing tables. | [.md](https://openaitools.app/tool/infrabase-ai.md) |
| 10 | [Agent Skills Hub](https://openaitools.app/tool/agent-skils-hub) | 28,753 | +34.3% | Freemium, Paid, Free | Open-source directory that indexes, secures, and grades AI agent skills and Model Context Protocol servers. | [.md](https://openaitools.app/tool/agent-skils-hub.md) |

---
Source: https://openaitools.app/compare/mcp-server-vs-models-dev

More Markdown: [Categories](https://openaitools.app/categories.md) · [Traffic rankings](https://openaitools.app/rankings.md) · [llms.txt](https://openaitools.app/llms.txt)