<!-- twin of https://specstream.ai/firecrawl-mcp -->
# Firecrawl MCP server: setup, price and pages at $0.80 per 1,000

Compared on Nov 12, 2026. The page: https://specstream.ai/firecrawl-mcp

Firecrawl MCP runs hosted at `https://mcp.firecrawl.dev/v2/mcp` or on your machine with `npx -y firecrawl-mcp`. With a key it lists 31 tools. A page costs 1 credit and 10 search results 2, from $19 a month for 5,000 credits.

SpecStream is the live web data engine for teams and agents. Keep `firecrawl-mcp`, set `FIRECRAWL_API_URL` to `https://api.specstream.ai/firecrawl`, and scrape, crawl and map cost $0.80 per 1,000 pages, search $1 per 1,000. Or add `https://api.specstream.ai/mcp`.

[Get an API key](https://specstream.ai/signup?src=alternatives-firecrawl-mcp&utm_source=alternatives-md&utm_campaign=firecrawl-mcp&returnTo=%2Fworkspace%2Fsearch%3Froute%3Dfirecrawl) New accounts get $10 of credit, no card. It covers 12,500 pages or 10,000 fast searches.

## SpecStream, Firecrawl MCP and Tavily MCP, side by side

| | SpecStream | Firecrawl MCP | Tavily MCP |
|---|---|---|---|
| Address or install line | `https://api.specstream.ai/mcp` over Streamable HTTP, with OAuth or an API key. Or keep `firecrawl-mcp` with `FIRECRAWL_API_URL` set to `https://api.specstream.ai/firecrawl` | `https://mcp.firecrawl.dev/v2/mcp` hosted, or `env FIRECRAWL_API_KEY=fc-YOUR_API_KEY npx -y firecrawl-mcp` on your machine | `https://mcp.tavily.com/mcp/`, or `claude mcp add tavily --transport http https://mcp.tavily.com/mcp/` in Claude Code |
| Tools your agent gets | `search_web`, `read_pages` (up to 20 pages a call), and Deep Search through `compile`, `quote_capacity_work` and `authorize_capacity_work`. Through `firecrawl-mcp`: `firecrawl_scrape`, `firecrawl_search`, `firecrawl_map`, `firecrawl_crawl` and `firecrawl_check_crawl_status` | 31 tools with a key, among them `firecrawl_scrape`, `firecrawl_search`, `firecrawl_map`, `firecrawl_crawl` and `firecrawl_agent`. 3 with no key: `firecrawl_scrape`, `firecrawl_search` and `firecrawl_parse` | `tavily_search`, `tavily_extract`, `tavily_crawl`, `tavily_map` and `tavily_research` |
| Price per 1,000 pages read | $0.80, the same for a scrape, a crawled page or a map | 1 credit a page: $3.80 on Hobby ($19 for 5,000 credits), $0.99 on Standard ($99 for 100,000). The JSON format adds 4 credits a page | 1 credit for every 5 pages on basic extract: $1.60 at $0.008 a credit. A basic crawl of 10 pages costs 3 credits, $2.40 per 1,000 pages |
| Price per 1,000 searches | $1 for up to 10 results on the fast search, $5 with the answer and the page it was read on | 2 credits per 10 results: $7.60 on Hobby, $1.98 on Standard | 1 credit a basic search and 2 an advanced one: $8 or $16 at $0.008 a credit |
| A page that fails | A page that gives no text is not charged. A busy call gets `429` with `Retry-After` and costs nothing | A page that answers 403 or 404 is returned and costs 1 credit | A failed URL extraction is not charged |
| Free to start | $10 of credit, no card. It covers 12,500 pages or 10,000 fast searches | 1,000 credits a month, no card: 500 searches or 1,000 pages. The hosted server runs scrape, search and parse with no key, rate limited | 1,000 credits a month, no card |
| When the credits run out | Calls draw on your balance, with a spending limit on each key. No monthly plan to buy | Pay as you go adds credits in 5 USD increments up to a limit you set, on paid plans only | $0.008 a credit pay as you go |
| Every match as structured rows | Deep Search returns every match on the live web as rows, at 5¢, 15¢ or $1 a row. The most a run can cost is shown and approved before it runs | `firecrawl_agent`: 5 daily runs free, then priced in credits by agent tokens | `tavily_research`: 4 to 110 credits a request on mini, 15 to 250 on pro |

## Why agents read the web through SpecStream

### Keep firecrawl-mcp and change one variable

`firecrawl-mcp` reads `FIRECRAWL_API_URL`, which its README names as the custom API endpoint. SpecStream answers Firecrawl's v2 scrape, search, map and crawl requests at `https://api.specstream.ai/firecrawl` in Firecrawl's own JSON. Set that address, put a SpecStream key in `FIRECRAWL_API_KEY`, and `firecrawl_scrape`, `firecrawl_search`, `firecrawl_map` and `firecrawl_crawl` run on SpecStream with your prompts unchanged. In `claude_desktop_config.json`:

```
{
  "mcpServers": {
    "mcp-server-firecrawl": {
      "command": "npx",
      "args": ["-y", "firecrawl-mcp"],
      "env": {
        "FIRECRAWL_API_URL": "https://api.specstream.ai/firecrawl",
        "FIRECRAWL_API_KEY": "YOUR_SPECSTREAM_KEY"
      }
    }
  }
}
```

`firecrawl_agent`, `firecrawl_interact`, `firecrawl_parse`, the monitor tools and the Alexandria tools call Firecrawl endpoints that SpecStream does not answer. For research across many sites, add SpecStream's own server beside it and use Deep Search.

### 10,000 pages for $8

On Firecrawl's Hobby plan, 10,000 pages take 10,000 credits, twice the 5,000 that $19 a month holds. On SpecStream they cost $8 from your balance, with no plan to buy. Firecrawl charges 1 credit for a page that answers 403 or 404 and 5 credits for a page in JSON format. On SpecStream a page that gives no text costs nothing, and every page that does costs $0.0008.

### The most accurate web search API in the world, behind both servers

`firecrawl_search` and `search_web` both run SpecStream's Search API. It scores 97.9 F-score on all 1,000 official SimpleQA Verified questions (978 correct), and 64.0 item F1 and 43.4 row F1 on all 200 official WideSearch tasks. The Extract API behind `firecrawl_scrape` and `read_pages` scores 0.908 F1 on WCXB. The scores and the method are on the [benchmarks page](https://specstream.ai/benchmarks?utm_source=alternatives&utm_campaign=firecrawl-mcp).

### SpecStream's own server in one line

In Claude Code, run this and sign in when the browser opens. Nothing runs on your machine:

```
claude mcp add --transport http specstream https://api.specstream.ai/mcp
```

Your agent gets `search_web` for search, `read_pages` for up to 20 pages or documents a call, and Deep Search for every match on the live web as structured rows, with the source URL and read time on every value. Cursor, VS Code, ChatGPT and the other clients take the same address; the [MCP client guides](https://specstream.ai/docs/mcp/clients?utm_source=alternatives&utm_campaign=firecrawl-mcp) show where each one keeps it.

## Other Firecrawl MCP alternatives

### Tavily MCP

Tavily's hosted server at `https://mcp.tavily.com/mcp/` offers search, extract, crawl, map and research. Basic extract costs 1 credit for every 5 pages, $1.60 per 1,000 pages at $0.008 a credit, and a basic search costs 1 credit, $8 per 1,000. SpecStream reads pages at $0.80 per 1,000 and searches at $1 per 1,000.

### Exa MCP

Exa's server at `https://mcp.exa.ai/mcp` gives `web_search_exa` and `web_fetch_exa` by default. Search starts at $4 per 1,000 requests and page contents cost $1 per 1,000 pages. SpecStream's `read_pages` costs $0.80 per 1,000 pages, and its search API scores 97.9 F-score on SimpleQA Verified.

### Apify MCP

Apify's server at `https://mcp.apify.com` lets an agent find and run Actors from Apify Store. The free plan gives $5 to spend in Apify Store, and compute costs $0.2 per compute unit, so the price of a page depends on the Actor you run. SpecStream prices every page the same, $0.0008.

## How to move from Firecrawl MCP to SpecStream

1. Sign up at specstream.ai. The account starts with $10 of credit, no card. Create a key under Agents & API in the workspace.

2. In `claude_desktop_config.json`, or in Cursor's `mcp.json`, keep the `firecrawl-mcp` entry and change its `env`:

```
"env": {
  "FIRECRAWL_API_URL": "https://api.specstream.ai/firecrawl",
  "FIRECRAWL_API_KEY": "YOUR_SPECSTREAM_KEY"
}
```

3. Restart the client. Your agent keeps calling `firecrawl_scrape`, `firecrawl_search`, `firecrawl_map` and `firecrawl_crawl`, and each call is billed by SpecStream.

4. To use SpecStream's own server, add `https://api.specstream.ai/mcp`. Your agent calls `search_web` where it called `firecrawl_search`, and `read_pages` where it called `firecrawl_scrape`.

5. To go back, remove `FIRECRAWL_API_URL` and put your Firecrawl key in `FIRECRAWL_API_KEY`. The same address works for Firecrawl's SDKs: see the [Firecrawl migration guide](https://specstream.ai/migrate/firecrawl?utm_source=alternatives&utm_campaign=firecrawl-mcp) and [crawl and map](https://specstream.ai/migrate/firecrawl-crawl?utm_source=alternatives&utm_campaign=firecrawl-mcp).

## Frequently asked questions

### Is there an official Firecrawl MCP server?

Yes. Firecrawl publishes `firecrawl-mcp` on npm under the MIT License and hosts the same server at `https://mcp.firecrawl.dev/v2/mcp`. With a key it lists 31 tools.

### How do I install the Firecrawl MCP server?

Run `env FIRECRAWL_API_KEY=fc-YOUR_API_KEY npx -y firecrawl-mcp`, or add an `mcpServers` entry with `"command": "npx"`, `"args": ["-y", "firecrawl-mcp"]` and your key in `env` to `claude_desktop_config.json` or Cursor's MCP settings. The hosted address takes the key as `Authorization: Bearer`.

### Does Firecrawl MCP work without an API key?

Yes, for 3 tools. The hosted keyless tier runs `firecrawl_scrape`, `firecrawl_search` and `firecrawl_parse` at a rate limit; crawl, map and agent need a key.

### How much does Firecrawl MCP cost?

The server is free; its calls spend Firecrawl credits: 1 a page and 2 per 10 search results. The free plan gives 1,000 credits a month, Hobby is $19 a month for 5,000 and Standard $99 a month for 100,000.

### Can I point firecrawl-mcp at SpecStream?

Yes. Set `FIRECRAWL_API_URL` to `https://api.specstream.ai/firecrawl` and `FIRECRAWL_API_KEY` to a SpecStream key. Scrape, crawl and map then cost $0.80 per 1,000 pages and search $1 per 1,000.

### What does SpecStream's MCP server cost?

$1 per 1,000 searches of up to 10 results on the fast search, $5 per 1,000 with the answer, $0.80 per 1,000 pages read, and 5¢, 15¢ or $1 a row for Deep Search. New accounts get $10 of credit with no card.

## Sources

SpecStream wrote this page. Each install line, tool name and price comes from the project's own README or the company's own page, read on Nov 12, 2026.

- [firecrawl-mcp README](https://github.com/firecrawl/firecrawl-mcp-server), read Nov 12, 2026
- [Firecrawl MCP server docs](https://docs.firecrawl.dev/mcp-server), read Nov 12, 2026
- [Firecrawl pricing](https://www.firecrawl.dev/pricing), read Nov 12, 2026
- [Tavily MCP](https://docs.tavily.com/documentation/mcp), read Nov 12, 2026
- [Tavily credits and pricing](https://docs.tavily.com/documentation/api-credits), read Nov 12, 2026
- [Exa MCP](https://docs.exa.ai/reference/exa-mcp), read Nov 12, 2026
- [Exa pricing](https://exa.ai/pricing), read Nov 12, 2026
- [Apify MCP server](https://docs.apify.com/platform/integrations/mcp), read Nov 12, 2026
- [Apify pricing](https://apify.com/pricing), read Nov 12, 2026
- [SpecStream benchmarks](https://specstream.ai/benchmarks), read Nov 12, 2026
- [SpecStream for agents](https://specstream.ai/agents.md), read Nov 12, 2026