firecrawl

Web search and scraping of human-readable pages via Firecrawl.

Source: packages/oracle-runtime/src/plugins/firecrawl/

Attribute	Value
Feature key	firecrawl
Visibility	on-demand
Stability	stable
Category	data
Default state	Auto-detect (env: FIRECRAWL_MCP_URL)
Depends on	—

Summary

Web search and scraping via Firecrawl. Exposes a sub-agent (call_firecrawl_agent) that wraps the upstream Firecrawl MCP server’s firecrawl_search and firecrawl_scrape tools. The manifest specifically routes the main agent away from API endpoints (use sandbox) and IXO entities (use domain-indexer).

Environment variables

Var	Required	Description
FIRECRAWL_MCP_URL	yes	Firecrawl MCP HTTP(S) URL. Also triggers auto-detect.

What it contributes

• Tools (inside the sub-agent): firecrawl_search, firecrawl_scrape.
• Sub-agents: call_firecrawl_agent.
• Middleware: none.
• HTTP routes: none.
• Shared state: none.

Opt out / Opt in

const app = await createOracleApp({
  config,
  features: { firecrawl: false }, // never load
  // features: { firecrawl: true }, // force load (will fail env validation if FIRECRAWL_MCP_URL missing)
  // features: { firecrawl: 'auto' }, // run autoDetect (default)
});

When to use it

• User asks the agent to search the web for current information.
• User wants the contents of a specific page summarised or extracted.
• A question can only be answered by recent public web content.

When NOT to use it

• Fetching from an API endpoint (URLs containing /api/, /v1/, /v2/, /v3/, or that return JSON/XML) — use sandbox.
• IXO entity lookups — use domain-indexer.
• Personal memory or past-conversation recall — use memory.

Where to read next

Add a sub-agent

How sub-agents like call_firecrawl_agent are built.

Plugin vs Skill

When to wrap an MCP server as a plugin vs ship it as a skill.