| FMRS | 69 / 100 · C | 75 / 100 · B | 73 / 100 · B |
|---|
| Reliability | 10 / 20 | 13 / 20 | 12 / 20 |
|---|
| Security and permissions | 14 / 20 | 12 / 20 | 13 / 20 |
|---|
| Maintenance | 13 / 20 | 16 / 20 | 16 / 20 |
|---|
| Documentation | 17 / 20 | 17 / 20 | 16 / 20 |
|---|
| Setup experience | 15 / 20 | 17 / 20 | 16 / 20 |
|---|
| Best for | - Teams that need AI access to one or more MediaWiki wikis.
- Users combining wiki retrieval with controlled content maintenance.
- Users of Claude, Codex, VS Code, Cursor, or other listed MCP clients.
| - 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 | - Knowledge bases or content systems that do not use MediaWiki.
- Workflows requiring writes without configuration or permissions.
- Users expecting client or protocol compatibility that is not evidenced by the source.
| - 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 | - Read operations depend on the wiki being public or configured and reachable.
- Write tools require the corresponding MediaWiki permissions; write tools are hidden from tools/list when the default wiki is read-only.
- File uploads require allowed upload directories to be configured.
- Cargo queries may require the runcargoqueries user right.
- Private wikis and authenticated operations require OAuth, tokens, bot passwords, or another configured authentication method.
| - 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 | - In HTTP mode, Authorization Bearer tokens are forwarded to MediaWiki; authentication should be handled by a reverse proxy with TLS termination outside an untrusted network.
- Before exposing HTTP to others, configure allowed hosts and origins to reduce DNS-rebinding and cross-origin risks.
- Write, delete, move, and upload tools can change wiki content or files; use least-privilege credentials.
- Outbound URL fetching and uploads are subject to SSRF and size limits; internal destinations require MCP_TRUSTED_HOSTS.
- Tool responses have content, file-data, request-body, and upload size caps.
| - 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 Code, Codex, Claude Desktop, VS Code, Cursor, Antigravity, OpenCode, Devin Desktop, Zed, LM Studio | Claude Desktop, VS Code, Cursor, Windsurf, Zed, Amp | Claude Desktop, Claude Code, VS Code, Cursor, Windsurf, Zed, Amp, Kiro, LM Studio, Antigravity |
|---|
| Tools | 46 | 11 | 4 |
|---|