| FMRS | 50 / 100 · D | 75 / 100 · B | 73 / 100 · B |
|---|
| Reliability | 8 / 20 | 13 / 20 | 12 / 20 |
|---|
| Security and permissions | 11 / 20 | 12 / 20 | 13 / 20 |
|---|
| Maintenance | 7 / 20 | 16 / 20 | 16 / 20 |
|---|
| Documentation | 13 / 20 | 17 / 20 | 16 / 20 |
|---|
| Setup experience | 11 / 20 | 17 / 20 | 16 / 20 |
|---|
| Best for | - Users who need to normalize multiple file types and web content into Markdown.
- Users who want local MCP desktop-app integration for Markdown conversion.
- Developers comfortable configuring Bun, Node.js, and Python dependencies.
| - Scenarios needing clean, structured web context fed to an AI assistant
- Users already on the Firecrawl platform who want to call its scraping capability directly via MCP
| - Q&A and research scenarios that need real-time, clean web content
- Users with an existing Exa account who want a zero-deployment remote option
|
|---|
| Not for | - Users seeking structured database or cloud-storage operations.
- Users requiring verified compatibility with a specific MCP client.
- Users running the slim Docker image who need audio transcription or image OCR.
| - Simple static-page scraping where you don't want to depend on a third-party API and incur call costs
- Sites that explicitly disallow automated access (robots.txt)
| - Scenarios requiring a strict allowlist of search sources that can't use a third-party search service
- Budget-sensitive, high-volume search scenarios (remote/API calls may incur cost)
|
|---|
| Required permissions | - The server needs to read the file paths supplied to its file-input tools; MD_ALLOWED_PATHS can restrict readable directories.
- When MD_ALLOWED_PATHS is unset, file access is unrestricted by that setting.
- Tools handling web pages, YouTube, or Bing content need access to the relevant web content; the source does not state any additional authentication requirements.
| - Requires a Firecrawl API key to call; cost and quota are governed by the Firecrawl account
- firecrawl_agent/firecrawl_interact perform automated browser interaction, which may trigger login or form-submission flows on the target site
| - Requires an Exa API key for full functionality; OAuth login is optional in remote mode
- web_fetch_exa retrieves content from a specified URL; agent_run performs multi-step autonomous actions and needs the user to have clear expectations of Agent behavior
|
|---|
| Risks and side effects | - The default file-reading scope is unrestricted; set MD_ALLOWED_PATHS to narrow the readable boundary.
- The published Docker image installs only markitdown[pdf], so audio transcription and image OCR tools fail in that slim image.
- When using Docker, mount only required directories and pass container paths to the tools.
| - Bulk crawl/map tools can generate significant request volume against a target site — respect the site's rate limits and terms of service
- firecrawl_agent's interactive action chain is longer — define task boundaries clearly before running it to avoid accidentally triggering actions on a sensitive site
| - The API key should be stored carefully — avoid leaving it in plaintext in client config files on untrusted machines
- agent_run is a multi-step autonomous tool with a longer action chain — try it on low-risk tasks first
|
|---|
| Supported clients | | Claude Desktop, VS Code, Cursor, Windsurf, Zed, Amp | Claude Desktop, Claude Code, VS Code, Cursor, Windsurf, Zed, Amp, Kiro, LM Studio, Antigravity |
|---|
| Tools | 10 | 11 | 4 |
|---|