---
title: "Firecrawl MCP: Scrape, Crawl and Search the Web"
url: "https://mcpshelf.co/servers/firecrawl"
description: "Firecrawl MCP turns pages and whole sites into clean Markdown for an AI assistant, with search and structured extraction. Config and the API key."
updated: "2026-10-27"
site: "MCP Shelf"
---

# Firecrawl

> Scrape pages, crawl sites and search, returned as clean Markdown.

Source: https://mcpshelf.co/servers/firecrawl  
Markdown: https://mcpshelf.co/servers/firecrawl.md  
Generated: 2026-11-22T19:04:39.446Z

## Facts

- **Name:** Firecrawl
- **Tagline:** Scrape pages, crawl sites and search, returned as clean Markdown.
- **Description:** Firecrawl MCP is the official MCP server for Firecrawl, letting AI assistants search the web and scrape, crawl, map and extract websites into clean, model-ready content.
- **Repository:** https://github.com/mendableai/firecrawl-mcp-server
- **Package:** firecrawl-mcp 3.35.0 (npm)
- **Install:** `claude mcp add firecrawl -e FIRECRAWL_API_KEY=fc-your-key -- npx -y firecrawl-mcp`
- **Transport:** stdio (local)
- **Auth:** Needs `FIRECRAWL_API_KEY`
- **Tools exposed:** 28: `firecrawl_scrape`, `firecrawl_map`, `firecrawl_search`, `firecrawl_find_tools`, `firecrawl_search_feedback`, `firecrawl_feedback`, `firecrawl_crawl`, `firecrawl_check_crawl_status`, `firecrawl_agent`, `firecrawl_agent_status`, `firecrawl_interact`, `firecrawl_interact_stop`, `firecrawl_parse`, `firecrawl_monitor_create`, `firecrawl_monitor_list`, `firecrawl_monitor_get`, `firecrawl_monitor_update`, `firecrawl_monitor_delete`, `firecrawl_monitor_run`, `firecrawl_monitor_checks`, `firecrawl_monitor_check`, `firecrawl_research_search_papers`, `firecrawl_research_inspect_paper`, `firecrawl_research_related_papers`, `firecrawl_research_read_paper`, `firecrawl_developer_search`, `firecrawl_gov_search`, `firecrawl_credit_usage`
- **Category:** Browser and web data (https://mcpshelf.co/categories/browser-and-web)
- **Stats:** 7.7K GitHub stars, 128.6K downloads a week, last commit 27 Oct 2026, 0 upvotes on MCP Shelf
- **Install check:** Started in our test
- **Listed:** 2026-10-26
- **Page updated:** 2026-10-27

## Full description

### What is Firecrawl?

**Firecrawl MCP is the official MCP server for Firecrawl, letting AI assistants search the web and scrape, crawl, map and extract websites into clean, model-ready content.**

Firecrawl's server sends requests to the Firecrawl API, which renders pages, strips navigation and ads, and returns Markdown or structured JSON. It can also map a site's URLs, crawl them, and run a web search and scrape the results in one go.

Because the work happens on Firecrawl’s side, it copes with JavaScript-heavy pages without a browser on your machine.

|  |  |
| --- | --- |
| Made by | Firecrawl (Mendable) |
| GitHub | https://github.com/mendableai/firecrawl-mcp-server |
| Licence | MIT |
| npm package | [firecrawl-mcp](https://www.npmjs.com/package/firecrawl-mcp) 3.35.0 (26 Oct 2026) |
| GitHub stars | 7.7K |
| Downloads | 128.6K a week |
| Last commit | 27 Oct 2026 |
| Tools | 28 |
| Runs on | Your computer or hosted |
| Install check | Started in our test |
| Category | [Browser and web data](https://mcpshelf.co/categories/browser-and-web) |
| Works with | Claude Code, Cursor, Claude Desktop, VS Code, Codex, Windsurf, ChatGPT |
| Setup checked | 27 Oct 2026 |
| Page updated | 27 Oct 2026 |

**Our check:** We ran this exact config on 26 Oct 2026: it started and answered with 28 tools. firecrawl-mcp on npm is published from firecrawl/firecrawl-mcp-server.

#### Try asking Firecrawl

- "Scrape the pricing page at stripe.com/pricing and turn it into a Markdown table."
- "Map every URL on docs.example.com and list the ones about authentication."
- "Search the web for this week’s posts about MCP security and summarise the top five."

#### MCP Shelf take

> We started Firecrawl on our own test machine on 26 Oct 2026 and it answered with 28 tools. 17 of the 28 only read; the other 11 can change things. Every tool comes with a useful description, all of them say whether they change things, and the tool list costs about 5,500 tokens of context before you ask a thing. It sits 3rd of 13 in its category on our shelf by GitHub stars (7.7K, with 128.6K downloads a week).

— MCP Shelf tests (numbers from our own runs), tested on 26 Oct 2026

### What tools does Firecrawl have?

We listed 28 tools on 26 Oct 2026. 17 only read; the rest can change things or run commands.

| Tool | Kind | What it is for |
| --- | --- | --- |
| `firecrawl_scrape` | changes | Fetches one URL and returns it as Markdown, HTML, a screenshot or JSON that fits a schema you give. |
| `firecrawl_map` | reads | Lists the URLs on a site without downloading their content. |
| `firecrawl_search` | reads | Searches the web and returns ranked results with excerpts, optionally scraping each result too. |
| `firecrawl_find_tools` | reads | Browses Firecrawl's catalogue of ready-made data providers. |
| `firecrawl_search_feedback` | changes | Rates a past search so Firecrawl can improve it, sometimes refunding a credit. |
| `firecrawl_feedback` | changes | Sends a rating on any Firecrawl result back to the service. |
| `firecrawl_crawl` | changes | Walks a whole site or section and fetches every page it finds, within limits you set. |
| `firecrawl_check_crawl_status` | reads | Reports progress on a crawl and returns the pages gathered so far. |
| `firecrawl_agent` | changes | Hands a research goal to Firecrawl's own agent, which browses on its own and returns structured findings. |
| `firecrawl_agent_status` | reads | Checks whether an agent job has finished and collects its results. |
| `firecrawl_interact` | changes | Clicks, types or navigates on a live page, for content that only appears after an action. |
| `firecrawl_interact_stop` | changes | Closes a browser session opened by firecrawl_interact. |
| `firecrawl_parse` | reads | Turns an uploaded document, such as a PDF, into clean text. |
| `firecrawl_monitor_create` | changes | Sets up a page to be re-checked on a schedule with change alerts. |
| `firecrawl_monitor_list` | reads | Lists your monitors. |
| `firecrawl_monitor_get` | reads | Shows one monitor's settings. |
| `firecrawl_monitor_update` | changes | Changes a monitor's schedule or target. |
| `firecrawl_monitor_delete` | changes | Removes a monitor. |
| `firecrawl_monitor_run` | runs | Runs a monitor's check right away. |
| `firecrawl_monitor_checks` | reads | Lists past checks for a monitor. |
| `firecrawl_monitor_check` | reads | Shows the result of one scheduled check, including what changed. |
| `firecrawl_research_search_papers` | reads | Searches biomedical and arXiv research papers. |
| `firecrawl_research_inspect_paper` | reads | Gives a quick look at one paper's details and sections. |
| `firecrawl_research_related_papers` | reads | Follows citations to papers linked to one you already have. |
| `firecrawl_research_read_paper` | reads | Reads passages from a paper's full text. |
| `firecrawl_developer_search` | reads | Searches public code, GitHub issues, pull requests and library docs for programming answers. |
| `firecrawl_gov_search` | reads | Searches US federal, state and local laws, regulations and court opinions. |
| `firecrawl_credit_usage` | reads | Shows how many credits you have left and what used them, by day or month. |

#### How clearly it describes its tools

28 of 28 tools have a description and 28 of 28 say whether they change things. The tool list takes at least ~5,500 tokens of context. Every tool says whether it only reads or can change things, so a client can ask before the risky ones. The tool list is large: switch off the tools you do not use if your client allows it.

### How do I install Firecrawl?

#### Install steps from the Firecrawl README

Copied from the project's [README on GitHub](https://github.com/mendableai/firecrawl-mcp-server#readme) on 20 Nov 2026 under its MIT licence.

##### Hosted MCP (keyless free tier)

Connect to the remote hosted server with no setup:

```
https://mcp.firecrawl.dev/v2/mcp
```

On the keyless free tier, `scrape`, `search`, and `parse` work without an API key (rate-limited). Other tools such as `crawl`, `map`, and `agent` still need a key.

Prefer OAuth or an API key whenever the human can sign up. It unlocks the full tool set and higher limits.

For an interactive account connection, configure your MCP client to use this server URL. This is an MCP endpoint, **not a browser page**; use the client's account-connection flow and do not add a second Firecrawl server entry when reconnecting:

```
https://mcp.firecrawl.dev/v2/mcp-oauth
```

For an API-key connection (for example, an unattended integration), keep the server URL as:

```
https://mcp.firecrawl.dev/v2/mcp
```

Then configure the client's secure header or secret setting with:

```
Authorization: Bearer <FIRECRAWL_API_KEY>
```

Never put an API key in the server URL. Never put an API key in an agent chat. Configure it directly in the client or secret manager. See the [hosted MCP setup guide](https://docs.firecrawl.dev/mcp-server) and the [agent onboarding guide](https://www.firecrawl.dev/agent-onboarding/SKILL.md) for client-specific instructions.

##### Naming your integration

An integration that connects over HTTP can name itself with an `X-Firecrawl-Origin` header, for example `X-Firecrawl-Origin: my-agent`. The server reports it to Firecrawl as the request origin `mcp-my-agent@`, in place of the client name or User-Agent it would otherwise report. Use letters, digits and dashes: each run of other characters becomes one dash, leading and trailing dashes are dropped, and the name is cut at 48 characters. Tool results are unaffected; only the origin sent to the Firecrawl API (and passed to an embedder's `beforeKeylessRequest`) changes.

##### Search-only endpoint

A fixed-scope search surface is also hosted at:

```
https://mcp.firecrawl.dev/v2/mcp-search
```

It exposes a fixed set of twelve tools: `firecrawl_search`, `firecrawl_developer_search`, `firecrawl_gov_search`, the four `firecrawl_research_*` paper tools, the two Alexandria tools `firecrawl_find_tools` and `firecrawl_scrape`, and the enrich tools `people_company_search` and `people_company_enrich`, and the jobs tool `jobs_search`. Its `firecrawl_search` fetches no page content.

##### Running with npx

```
env FIRECRAWL_API_KEY=fc-YOUR_API_KEY npx -y firecrawl-mcp
```

##### Manual Installation

```
npm install -g firecrawl-mcp
```

##### Running on Cursor

Configuring Cursor 🖥️
Note: Requires Cursor version 0.45.6+
For the most up-to-date configuration instructions, please refer to the official Cursor documentation on configuring MCP servers:
[Cursor MCP Server Configuration Guide](https://docs.cursor.com/context/model-context-protocol#configuring-mcp-servers)

To configure Firecrawl MCP in Cursor **v0.48.6**

1. Open Cursor Settings
2. Go to Features > MCP Servers
3. Click "+ Add new global MCP server"
4. Enter the following code:`{  "mcpServers": {  "firecrawl-mcp": {  "command": "npx",  "args": ["-y", "firecrawl-mcp"],  "env": {  "FIRECRAWL_API_KEY": "YOUR-API-KEY"  }  }  } }`

To configure Firecrawl MCP in Cursor **v0.45.6**

1. Open Cursor Settings
2. Go to Features > MCP Servers
3. Click "+ Add New MCP Server"
4. Enter the following:
  - Name: "firecrawl-mcp" (or your preferred name)
  - Type: "command"
  - Command: `env FIRECRAWL_API_KEY=your-api-key npx -y firecrawl-mcp`

> If you are using Windows and are running into issues, try `cmd /c "set FIRECRAWL_API_KEY=your-api-key && npx -y firecrawl-mcp"`

Replace `your-api-key` with your Firecrawl API key. If you don't have one yet, you can create an account and get it from [https://www.firecrawl.dev/app/api-keys](https://www.firecrawl.dev/app/api-keys)

After adding, refresh the MCP server list to see the new tools. The Composer Agent will automatically use Firecrawl MCP when appropriate, but you can explicitly request it by describing what you need from the web. Access the Composer via Command+L (Mac), select "Agent" next to the submit button, and enter your query.

##### Running on Windsurf

Add this to your `./codeium/windsurf/model_config.json`:

```
{
  "mcpServers": {
    "mcp-server-firecrawl": {
      "command": "npx",
      "args": ["-y", "firecrawl-mcp"],
      "env": {
        "FIRECRAWL_API_KEY": "YOUR_API_KEY"
      }
    }
  }
}
```

##### Running on VS Code

For one-click installation, click one of the install buttons below...

For manual installation, add the following JSON block to your User Settings (JSON) file in VS Code. You can do this by pressing `Ctrl + Shift + P` and typing `Preferences: Open User Settings (JSON)`.

```
{
  "mcp": {
    "inputs": [
      {
        "type": "promptString",
        "id": "apiKey",
        "description": "Firecrawl API Key",
        "password": true
      }
    ],
    "servers": {
      "firecrawl": {
        "command": "npx",
        "args": ["-y", "firecrawl-mcp"],
        "env": {
          "FIRECRAWL_API_KEY": "${input:apiKey}"
        }
      }
    }
  }
}
```

Optionally, you can add it to a file called `.vscode/mcp.json` in your workspace. This will allow you to share the configuration with others:

```
{
  "inputs": [
    {
      "type": "promptString",
      "id": "apiKey",
      "description": "Firecrawl API Key",
      "password": true
    }
  ],
  "servers": {
    "firecrawl": {
      "command": "npx",
      "args": ["-y", "firecrawl-mcp"],
      "env": {
        "FIRECRAWL_API_KEY": "${input:apiKey}"
      }
    }
  }
}
```

##### Usage with Claude Desktop

Add this to your `claude_desktop_config.json`:

```
{
  "mcpServers": {
    "mcp-server-firecrawl": {
      "command": "npx",
      "args": ["-y", "firecrawl-mcp"],
      "env": {
        "FIRECRAWL_API_KEY": "YOUR_API_KEY_HERE"
      }
    }
  }
}
```

##### Required for Cloud API

- `FIRECRAWL_API_KEY`: Your Firecrawl API key
  - Required when using cloud API (default)
  - Optional when using self-hosted instance with `FIRECRAWL_API_URL`
- `FIRECRAWL_API_URL` (Optional): Custom API endpoint for self-hosted instances
  - Example: `https://firecrawl.your-domain.com`
  - If not provided, the cloud API will be used (requires API key)
  - Over stdio, Alexandria tools are sent to this endpoint even when no API key is set here, and it answers for the account. [Firecrawl Local](https://github.com/firecrawl/firecrawl/tree/main/apps/local) signs them with the login it holds
- `FIRECRAWL_INTEGRATION` (Optional): Integration tag for apps that launch this server, such as an editor extension
  - Sent as the `integration` field of scrape, batch scrape, crawl, map, search, extract, agent, parse, interact and feedback requests
  - Use a value that starts with `_`, for example `_zed`
- `FIRECRAWL_MCP_LIBRARY_SKILLS` (Optional): Set to `false` to serve the Alexandria library without skills
  - Every `firecrawl/library` call carries `skills: false` (through `alexandria_library_search`, `alexandria_library_read` or a `firecrawl_scrape` alexandria body), the library description and the server instructions leave out the skills folder, no skills are listed under its results, and `firecrawl_save_skill` is not registered

#### What you need first

- A Firecrawl account and API key (there is a free tier)
- Node.js 18 or newer

#### Claude Code

Where: Your terminal, in the project folder

```bash
claude mcp add firecrawl -e FIRECRAWL_API_KEY=fc-your-key -- npx -y firecrawl-mcp
```

#### Cursor

Where: ~/.cursor/mcp.json, or .cursor/mcp.json in a project

```json
{
  "mcpServers": {
    "firecrawl": {
      "command": "npx",
      "args": [
        "-y",
        "firecrawl-mcp"
      ],
      "env": {
        "FIRECRAWL_API_KEY": "fc-your-key"
      }
    }
  }
}
```

Get a key at firecrawl.dev/app/api-keys. On Windows, if npx will not start, the project suggests cmd /c "set FIRECRAWL_API_KEY=your-api-key && npx -y firecrawl-mcp" as the command.

#### Claude Desktop

Where: claude_desktop_config.json (Settings → Developer → Edit Config)

```json
{
  "mcpServers": {
    "firecrawl": {
      "command": "npx",
      "args": [
        "-y",
        "firecrawl-mcp"
      ],
      "env": {
        "FIRECRAWL_API_KEY": "fc-your-key"
      }
    }
  }
}
```

No Node.js? Add https://mcp.firecrawl.dev/v2/mcp-oauth under Settings → Connectors → Add custom connector and sign in to Firecrawl instead.

#### VS Code

Where: .vscode/mcp.json in your project

```json
{
  "servers": {
    "firecrawl": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "firecrawl-mcp"
      ],
      "env": {
        "FIRECRAWL_API_KEY": "fc-your-key"
      }
    }
  }
}
```

#### Codex

Where: ~/.codex/config.toml, shared by the Codex CLI, IDE extension and ChatGPT desktop app

```
[mcp_servers.firecrawl]
command = "npx"
args = ["-y", "firecrawl-mcp"]

[mcp_servers.firecrawl.env]
FIRECRAWL_API_KEY = "fc-your-key"
```

Or run: `codex mcp add firecrawl --env FIRECRAWL_API_KEY=fc-your-key -- npx -y firecrawl-mcp`

#### Windsurf

Where: ~/.codeium/windsurf/mcp_config.json

```json
{
  "mcpServers": {
    "firecrawl": {
      "command": "npx",
      "args": [
        "-y",
        "firecrawl-mcp"
      ],
      "env": {
        "FIRECRAWL_API_KEY": "fc-your-key"
      }
    }
  }
}
```

#### ChatGPT

Where: chatgpt.com/plugins → + → Add custom MCP server

```
https://mcp.firecrawl.dev/v2/mcp-oauth
```

Use Firecrawl's hosted server with OAuth sign-in. Without signing in, https://mcp.firecrawl.dev/v2/mcp still offers scrape, search and parse on a rate-limited free tier.

Checked against the project's own install docs on 27 Oct 2026: https://github.com/mendableai/firecrawl-mcp-server#readme, https://docs.firecrawl.dev/mcp-server

### How do I configure Firecrawl?

| Setting | Kind | Required | What it does |
| --- | --- | --- | --- |
| `FIRECRAWL_API_KEY` | env | yes | Your key from firecrawl.dev. Needed for the cloud service unless you use the hosted keyless tier or OAuth. Example: `fc-xxxxxxxx` |
| `FIRECRAWL_API_URL` | env | no | Address of your own self-hosted Firecrawl. The key becomes optional if your instance has no auth. Example: `https://firecrawl.your-domain.com` |
| `https://mcp.firecrawl.dev/v2/mcp` | config | no | Hosted address. Scrape, search and parse work without a key on the free tier; send a Bearer key header for everything else. |
| `https://mcp.firecrawl.dev/v2/mcp-oauth` | config | no | Hosted address that signs in to your Firecrawl account through your client, no key to copy. |
| `FIRECRAWL_OAUTH_TOKEN` | env | no | A fixed OAuth access token (starting fco_) for the local stdio mode instead of an API key. |
| `FIRECRAWL_NO_SEARCH_FEEDBACK` | env | no | Set to 1 to hide the feedback tools and keep the tool list shorter. Example: `1` |

### What can Firecrawl read and change?

**It can read**

- Public web pages, search results, papers, code and government records
- Your credit balance

**It can change**

- Nothing on your machine
- Uses Firecrawl credits for each scrape, crawl, search or agent run
- Creates and deletes page monitors in your account

**Safer setup:** Set a limit and include or exclude paths on every crawl so a single request cannot burn through credits.

### Good for

- Research across many pages
- Pulling structured data (prices, specs, listings) out of sites
- Reading documentation sites into context

### Firecrawl not working? Common fixes

**Crawl, map or agent say a key is needed**
The keyless tier only covers scrape, search and parse. Add an API key or connect through the OAuth address.

**Rate limit exceeded**
Wait and retry, or move to a paid plan. Check what is left with firecrawl_credit_usage.

**A page comes back empty**
It may need a click or scroll first. Use firecrawl_interact, or ask scrape to wait before capturing.

**A crawl runs far longer than expected**
Cap it with limit and maxDiscoveryDepth, or use firecrawl_map first to see how big the site is.

### What are the alternatives to Firecrawl?

| Server | What it does | Tools | Runs on | Licence | Stars |
| --- | --- | --- | --- | --- | --- |
| [Firecrawl](https://mcpshelf.co/servers/firecrawl) | Scrape pages, crawl sites and search, returned as clean Markdown. | 28 | Your computer or hosted | MIT | 7.7K |
| [Exa](https://mcpshelf.co/servers/exa) | Search built for AI: web results, page contents and code examples. | 2 | Hosted or your computer | MIT | 5.2K |
| [Bright Data](https://mcpshelf.co/servers/bright-data) | Search and scraping through Bright Data, for sites that block ordinary requests. | 32 | Hosted or your computer | MIT | 2.7K |
| [SearXNG](https://mcpshelf.co/servers/searxng) | Web search through your own SearXNG instance: no vendor, no API key. | 4 | Your computer | MIT | 1.3K |
| [Apify](https://mcpshelf.co/servers/apify) | Find and run ready-made Apify scrapers for maps, social media, shops and search. | 10 | Hosted or your computer | MIT | 13.6K |
| [BrowserTools MCP](https://mcpshelf.co/servers/browser-tools) | Console logs, network calls, screenshots and Lighthouse audits from your own Chrome tab. | 16 | Your computer | MIT | 7.3K |

### Firecrawl FAQ

#### How do I add Firecrawl MCP to Claude Code?

Run claude mcp add firecrawl -e FIRECRAWL_API_KEY=fc-your-key -- npx -y firecrawl-mcp with your key from firecrawl.dev/app/api-keys. Or skip the local install and add the hosted server, https://mcp.firecrawl.dev/v2/mcp, with an Authorization: Bearer header.

#### Can I use Firecrawl MCP without an API key?

Partly. The hosted server at https://mcp.firecrawl.dev/v2/mcp lets scrape, search and parse run keyless at a low rate. Crawl, map and the agent tool need an account, through OAuth at /v2/mcp-oauth or an API key.

#### Does Firecrawl MCP work with ChatGPT?

Yes, through the hosted server. Add https://mcp.firecrawl.dev/v2/mcp-oauth as a custom MCP server on chatgpt.com/plugins, choose OAuth and sign in to Firecrawl.

#### Is Firecrawl MCP free?

The MCP server is MIT licensed and free; the scraping runs on Firecrawl's API, which is paid with a free allowance. Firecrawl itself is open source too, so you can self-host it and point FIRECRAWL_API_URL at your own copy.

#### Is Firecrawl MCP safe to use?

It only reads public web pages and returns their text; it does not change anything on your computer. The real risk is cost: set a limit and include or exclude paths on crawls, and never paste your key into a chat or put it in the server URL.

#### Why does Firecrawl MCP say I hit a rate limit?

The keyless tier and the free plan have low limits. Add an API key or sign in with OAuth for your own allowance; the server already retries and paces requests on its own, so repeated errors mean the plan limit, not a glitch.

#### Why did Firecrawl return an empty page?

Pages that build their content with JavaScript may need a wait before scraping, and some sites block scrapers. Ask for a wait or the markdown format, or use the search tool to find another source for the same facts.

#### Firecrawl or Bright Data: which should I use?

Firecrawl is the simpler choice for turning sites into clean markdown, crawling docs and searching. Bright Data is built for sites that block scrapers, with proxies and ready-made extractors for big platforms. Both bill per request beyond a free allowance.

#### How do I add Firecrawl to Cursor?

In ~/.cursor/mcp.json, or .cursor/mcp.json for one project, add an entry named firecrawl that runs npx -y firecrawl-mcp, with FIRECRAWL_API_KEY set under env. Save, and the tools show up in Agent chat. Get a key at firecrawl.dev/app/api-keys. On Windows, if npx will not start, the project suggests cmd /c "set FIRECRAWL_API_KEY=your-api-key && npx -y firecrawl-mcp" as the command.

#### Can I use Firecrawl in VS Code?

Yes, through GitHub Copilot. In .vscode/mcp.json, add a server named firecrawl with type stdio that runs npx -y firecrawl-mcp, with FIRECRAWL_API_KEY set under env. Then switch Copilot Chat to Agent mode to use its tools.

#### Does Firecrawl work with Codex?

Yes. Run codex mcp add firecrawl --env FIRECRAWL_API_KEY=fc-your-key -- npx -y firecrawl-mcp in a terminal, or add an [mcp_servers.firecrawl] table to ~/.codex/config.toml, which the Codex CLI and IDE extension share.

Full docs on GitHub: https://github.com/mendableai/firecrawl-mcp-server

## Notes for agents

Fetch these instead of parsing the HTML page:

- llms.txt: https://mcpshelf.co/llms.txt
- llms-full.txt: https://mcpshelf.co/llms-full.txt
- ai.txt: https://mcpshelf.co/ai.txt
- Full catalog (.md): https://mcpshelf.co/catalog.md
- API spec: https://mcpshelf.co/openapi.json
- MCP server: https://mcpshelf.co/mcp
- MCP manifest: https://mcpshelf.co/.well-known/mcp.json
- Developer docs: https://mcpshelf.co/developers

MCP endpoint (Streamable HTTP, no key): https://mcpshelf.co/mcp. REST API: https://mcpshelf.co/api/v1.

