Alexandria

Alexandria gives agents access to structured data through Firecrawl. Discover a tool, inspect its inputs, then run it. Discovery is free; execution uses the credits listed on the tool. Browse providers · Manage provider terms

Built for agents

Install the CLI or connect the MCP server.

Firecrawl CLI
MCP

# Find tools alongside web results.
firecrawl search "podcast conversations about AI agents" --sources web,alexandria --domain-tools --limit 2

# Inspect inputs and pricing.
firecrawl find-tools --providers particle --level tools --expand options,response

# Run the tool.
firecrawl scrape particle/podcasts/episodes/search --options '{"keyword_search":"AI agents","limit":2}'

Install with npm install -g firecrawl-cli and sign in with firecrawl login.

Ask your agent: “Find Particle’s podcast tools, inspect episode-search inputs and pricing, then find conversations about AI agents.”The agent uses firecrawl_search to discover tools, firecrawl_find_tools to inspect them, and firecrawl_scrape to execute them.

Use it from the SDKs and API

Find the right tool

Describe what you need. Alexandria returns relevant tools alongside your web results.

const result = await firecrawl.search(
  "podcast conversations about AI agents",
  {
    sources: ["web", "alexandria"],
    limit: 2,
  },
);

result = firecrawl.search(
    "podcast conversations about AI agents",
    sources=["web", "alexandria"],
    limit=2,
)

curl https://api.firecrawl.dev/v2/search \
  -H "Authorization: Bearer $FIRECRAWL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "query": "podcast conversations about AI agents",
  "sources": [
    "web",
    "alexandria"
  ],
  "limit": 2
}'

Results contain web pages and ranked tools. Each tool includes its provider, capability, inputs, response contract, and price.

Check what it needs

Read the selected tool’s options, response, and execution price before calling it. Use Find Tools for more detail.

Get the data

Use scrape to call the tool with the inputs from its contract. Supply the provider and capability under alexandria; no page URL is needed.

const episodes = await firecrawl.scrape({
  alexandria: {
    provider: "particle",
    capability: "podcasts/episodes/search",
    options: {
      semantic_search: "AI agents",
      limit: 2,
    },
  },
});

console.log(episodes.alexandria[0].data);

episodes = firecrawl.scrape(
    alexandria={
        "provider": "particle",
        "capability": "podcasts/episodes/search",
        "options": {
            "semantic_search": "AI agents",
            "limit": 2,
        },
    },
)

print(episodes.alexandria[0].data)

REQUEST_ID="$(uuidgen)"

curl https://api.firecrawl.dev/v2/scrape \
  -H "Authorization: Bearer $FIRECRAWL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "x-request-id: $REQUEST_ID" \
  -d '{
  "alexandria": {
    "provider": "particle",
    "capability": "podcasts/episodes/search",
    "options": {
      "semantic_search": "AI agents",
      "limit": 2
    }
  }
}'

Read the result from episodes.alexandria[0].data. Check each tool result for errors before using its data. Raw HTTP responses wrap the SDK result in data.

Find Tools

Use findTools / find_tools to browse providers and inspect their tools for free. Follow an item’s next request for more detail; the top-level next paginates the catalogue.

const catalogue = await firecrawl.findTools({
  providers: ["particle"],
  limit: 2,
});

// Each next request reveals another part of the catalogue.
const next = catalogue.items[0]?.next;
if (next) {
  const details = await firecrawl.scrape({ alexandria: next });
  console.log(details.alexandria[0].data);
}

catalogue = firecrawl.find_tools(providers=["particle"], limit=2)

if catalogue.items and catalogue.items[0].get("next"):
    details = firecrawl.scrape(alexandria=catalogue.items[0]["next"])
    print(details.alexandria[0].data)

Pricing and access

Tool discovery: free. Use sources: ["alexandria"] for tools only, or ["web", "alexandria"] to include paid web results.
Execution: charged at the tool’s listed price.
Provider terms: a THIRD_PARTY_DATA_TERMS_REQUIRED error includes requiresAction.url. An org admin must review and accept the terms there. Agents need explicit user authorization before accepting terms.

Find tools for a website

Add domainTools: true to a search or ordinary URL scrape to include tools matched to the website. Matching is free; the web search or page scrape is billed normally. Results include matchedBy and matchedUrls.Search enables domain matching by default when sources includes alexandria; set domainTools: false to disable it. For URL scrapes, domain matching is off by default.

Feedback

Report issues or request capabilities with firecrawl alexandria feedback. Run firecrawl alexandria feedback --help for options.

Get Started

Core Endpoints

More

Quickstarts

Developer Guides

Webhooks

Use Cases

Other

Contributing

Built for agents

Use it from the SDKs and API

Find Tools

Pricing and access

Feedback

​Built for agents

​Use it from the SDKs and API

​Find Tools

​Pricing and access

​Feedback

Built for agents

Use it from the SDKs and API

Find Tools

Pricing and access

Feedback