> For the complete documentation index, see [llms.txt](https://agpt.co/docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://agpt.co/docs/integrations/block-integrations/alexandria.md).

# Firecrawl Alexandria

Blocks for Firecrawl Alexandria, a catalogue of structured-data providers behind the Firecrawl API key: people and company search and enrichment (Apollo, People Data Labs, FullEnrich, Data Legion), jobs, finance and filings, public records, places, retail and thousands more. Finding tools is free; running one costs the Firecrawl credits listed on it.

## Firecrawl Find Data Tools

### What it is

Finds structured-data tools in Firecrawl Alexandria, free of charge: people and company search and enrichment (work emails, job titles, firmographics via Apollo, People Data Labs, FullEnrich), jobs, finance and filings, public records, places, retail and thousands more. Pass a tool's provider, capability and options to 'Firecrawl Run Data Tool'.

### How it works

This block calls Firecrawl's free `find-tools` capability. With a query it returns the tools that best match the data you describe; with provider or capability IDs it lists those tools; with only category IDs it lists the providers in those categories; with nothing it lists the categories.

Each tool comes back with its `provider` and `capability` IDs, a description, its price in Firecrawl credits and, when contracts are included, the `options` it accepts and the shape of its response. Feed those straight into the Firecrawl Run Data Tool block.

### Inputs

| Input              | Description                                                                                                                                                                       | Type       | Required |
| ------------------ | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------- | -------- |
| query              | What data you need, in plain words, e.g. 'work email for a person at a company' or 'sales leaders at Series B software companies'. Leave empty to browse by provider or category. | str        | No       |
| providers          | Limit to these provider IDs, e.g. 'apollo' or 'peopledatalabs'. Alone, lists that provider's tools.                                                                               | List\[str] | No       |
| capabilities       | Capability IDs to inspect within the providers above, e.g. 'people/search'. Returns each one's full contract.                                                                     | List\[str] | No       |
| categories         | Category IDs, e.g. 'people' or 'company'. Lists the providers in those categories.                                                                                                | List\[str] | No       |
| include\_contracts | Include each tool's inputs and response shape, so its options can be filled in for 'Firecrawl Run Data Tool'.                                                                     | bool       | No       |
| limit              | Most results to return (1-100)                                                                                                                                                    | int        | No       |
| offset             | Results to skip, for paging                                                                                                                                                       | int        | No       |

### Outputs

| Output  | Description                                                                                                                                                                         | Type                   |
| ------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------- |
| error   | Error message if the operation failed                                                                                                                                               | str                    |
| results | Matching tools, each with its provider, capability, description, price in Firecrawl credits and, when asked for, its input options. When browsing, providers or categories instead. | List\[Dict\[str, Any]] |
| result  | Each result in turn                                                                                                                                                                 | Dict\[str, Any]        |
| level   | What the results are: tools, providers, groups or categories                                                                                                                        | str                    |
| total   | Total number of matches                                                                                                                                                             | int                    |

### Possible use case

**Lead generation**: Ask for "sales leaders at Series B software companies" and get the people-search tools that can answer it.

**Picking a data source**: Compare the providers and prices available for company enrichment before building a workflow around one.

**Checking tool inputs**: Look up a tool's input contract before adding it to a workflow, so the request fields match what the tool expects.

***

## Firecrawl Run Data Tool

### What it is

Runs a Firecrawl Alexandria data tool and returns its typed, sourced records: find people by title and company, get verified work emails, enrich a company from its domain, and thousands more. Find the tool and its inputs with 'Firecrawl Find Data Tools' first. Costs the Firecrawl credits listed on the tool.

### How it works

This block sends one Alexandria call (provider, capability and options) to Firecrawl's `/v2/scrape` endpoint and returns the tool's records. The options must match the tool's contract, which Firecrawl Find Data Tools returns.

The call is billed at the Firecrawl credits the response reports, including when the tool fails. Some providers require a Firecrawl organization admin to accept their terms first; the error then includes the dashboard link where that is done.

### Inputs

| Input       | Description                                                                                                                                              | Type            | Required |
| ----------- | -------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------- | -------- |
| provider    | Provider ID from 'Firecrawl Find Data Tools', e.g. 'apollo'                                                                                              | str             | Yes      |
| capability  | Capability ID from 'Firecrawl Find Data Tools', e.g. 'people/search'                                                                                     | str             | Yes      |
| options     | The tool's inputs, exactly as its contract declares them (see the tool's options in 'Firecrawl Find Data Tools')                                         | Dict\[str, Any] | No       |
| timeout     | Seconds to wait for the provider (at most 120)                                                                                                           | int             | No       |
| request\_id | Only when retrying a call Firecrawl couldn't confirm: the request ID from its error, so the call isn't run and billed twice. Leave empty for a new call. | str             | No       |

### Outputs

| Output        | Description                                                                                                                          | Type  |
| ------------- | ------------------------------------------------------------------------------------------------------------------------------------ | ----- |
| error         | Error message if the operation failed                                                                                                | str   |
| data          | The records the tool returned                                                                                                        | Data  |
| records       | How many records were returned, as Firecrawl reports it. If it doesn't, the length of a list, 0 for no data, or 1 for any other data | int   |
| credits\_cost | Firecrawl credits this call cost                                                                                                     | float |

### Possible use case

**Prospect lists**: Find people by title and company, then resolve each to a verified work email.

**Account research**: Enrich a company from its domain with funding, headcount and technologies.

**Compliance checks**: Screen names against sanctions and politically exposed persons lists.

***


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://agpt.co/docs/integrations/block-integrations/alexandria.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
