# Give Your AI Agent a Searchable Directory of AI Tools (EveryAI MCP Setup)

> EveryAI runs a free remote MCP server at https://api.every-ai.com/mcp. Add it to Claude Code with one command (or paste the URL into any client that supports Streamable HTTP), and your agent can search 2,000+ reviewed AI tools by task, read a tool’s details, list categories, check whether a site is listed, and list a founder’s tool with submit_tool. No account or API key is needed.

- Source: https://every-ai.com/blog/connect-ai-agent-to-everyai-mcp
- Published by: EveryAI editorial team, 2026-11-18

## Key takeaways

- Server URL: https://api.every-ai.com/mcp (Streamable HTTP, no key).
- Claude Code: claude mcp add --transport http everyai https://api.every-ai.com/mcp
- Seven tools: six that only read (search_tools, get_tool, check_listing, list_categories, get_featured_offer, prepare_submission) and submit_tool, which lists a founder’s tool once they confirm by email.
- No MCP client? The same search is a plain HTTP API at api.every-ai.com/api/tools/search.

Agents are good at using tools and bad at knowing which tools exist. Ask a coding agent to “find an AI tool that transcribes interviews and exports SRT” and it will guess from training data that may be a year old. Connecting it to a live directory fixes that: the agent searches, reads the listings and cites them.

## What the EveryAI MCP server does

The server exposes the reviewed EveryAI index over the Model Context Protocol. Every tool but one only reads, so connecting it cannot change anything on your machine. The exception, `submit_tool`, lists a founder’s tool on EveryAI, and nothing is published until the founder confirms by email or pays (see [For AI agents](https://every-ai.com/agents)).

| Tool | What it returns |
| --- | --- |
| search_tools | The best-matching tools for a task (“logo maker”, “transcribe podcast episodes”), with EveryAI page, website, category and a short description. Optional category filter and limit. |
| get_tool | Full public details of one tool by its EveryAI URL, slug, website or exact name. |
| list_categories | Every category and use case, with hub pages and tool counts. |
| check_listing | Whether a website already has a live listing. |
| get_featured_offer | What a Featured listing costs in the founder’s country. |
| prepare_submission | A prefilled submit link for a founder. Nothing is submitted automatically. |

Results marked `featured` are paid placements, and the server says so in every response, so an agent can tell the difference.

## Connect it to Claude Code

Run this once in a terminal:

```
claude mcp add --transport http everyai https://api.every-ai.com/mcp
```

Then ask in plain language: “Use everyai to find three tools for turning meeting recordings into action items.” The agent calls `search_tools`, reads the matches and can open any of them with `get_tool`.

## Connect it to other MCP clients

Any client that supports remote (Streamable HTTP) servers takes the same URL. Clients that use an `mcpServers` JSON file, such as Cursor, accept an entry like this:

```
{
  "mcpServers": {
    "everyai": { "url": "https://api.every-ai.com/mcp" }
  }
}
```

Check your client’s documentation for where that file lives. The discovery card at [/.well-known/mcp.json](https://every-ai.com/.well-known/mcp.json) describes the server for clients and registries that read it.

## Use the HTTP API instead

Scripts and agents without MCP can call the same search over HTTPS:

```
curl "https://api.every-ai.com/api/tools/search?q=transcribe%20interviews&limit=5"
```

Results come back best match first as JSON. `/api/tools/check?url=https://example.com` tells you whether a site is listed, and the full contract is in the [OpenAPI document](https://api.every-ai.com/openapi.json). Please keep to about 120 requests a minute.

## Prompts that work well

- “Find AI tools for *[task]* and compare the top three on what they do and who they are for. Link each EveryAI page.”
- “List EveryAI’s categories and tell me which use cases have the most tools.”
- “Is *[website]* listed on EveryAI? If not, list it for me with my email.”

## Skills, too

EveryAI also catalogs agent skills. The open-source skills MCP gateway in the EveryAI repository searches that catalog and reads a skill’s `SKILL.md` as untrusted text without installing it. See the [MCP guide](https://every-ai.com/mcp) and the [skills library](https://every-ai.com/skills).

## FAQ

### Is the EveryAI MCP server free?

Yes. It needs no account or API key. Please keep to about 120 requests a minute per IP.

### What is the EveryAI MCP server URL?

https://api.every-ai.com/mcp, using the Streamable HTTP transport.

### Can the MCP server submit or change listings?

It can submit a new one: submit_tool lists a founder’s tool with their email, and nothing is published until they confirm by email or pay the $19 Featured checkout it returns. It never edits or removes existing listings.

### How does an agent know which results are paid?

Paid placements carry "listing": "featured" in every response, and the tool descriptions tell the agent so.

## On EveryAI

- [EveryAI MCP guide](https://every-ai.com/mcp): Setup for the tools server and the skills gateway.
- [Browse every category](https://every-ai.com/categories): The same taxonomy list_categories returns.
- [Glossary: Model Context Protocol](https://every-ai.com/glossary/model-context-protocol/): A one-paragraph definition.
- [EveryAI Labs](https://every-ai.com/labs): More remote MCP servers from the team, built on Cloudflare.

Source: EveryAI field notes (https://every-ai.com/blog/connect-ai-agent-to-everyai-mcp). Please cite and link the article when you use it.
