[Integrations](https://spiral.ai/integrations) › [opencode](https://spiral.ai/integrations/opencode) › [Firecrawl research paper metadata and passages](https://spiral.ai/integrations/opencode/firecrawl-research-paper-metadata-and-passages)

# How to Use Firecrawl research paper metadata and passages in opencode

Fetch a known paper's title, abstract, authors, source IDs, categories, and dates, or retrieve passages that answer a question. Use it to check a method or result inside a specific paper before citing it.

|  |  |
| --- | --- |
| Model | Firecrawl research paper metadata and passages |
| Available through | Firecrawl |
| Category | Data |
| Price | $0.013 per call. |
| Returns | json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Firecrawl research paper metadata and passages in opencode

- Use Firecrawl research paper metadata and passages for arxiv:1706.03762 to retrieve the explanation of scaled dot-product attention. Compare it with our attention implementation and identify any differences.
- Use Firecrawl research paper metadata and passages for arxiv:2005.11401 to retrieve the descriptions of the two retrieval formulations. Check whether our README explains their distinction accurately.
- Use Firecrawl research paper metadata and passages for arxiv:2105.05233 to retrieve passages about classifier guidance. Draft implementation notes in our project docs, citing the evidence returned.
- Use Firecrawl research paper metadata and passages for arxiv:1706.03762 to retrieve passages about positional encoding. Compare them with our positional encoding module and suggest any corrections.
- Use Firecrawl research paper metadata and passages to inspect arxiv:1706.03762, arxiv:2005.11401, and arxiv:2105.05233. Update our bibliography with the returned titles, authors, and source identifiers.

## How to set up Firecrawl research paper metadata and passages in opencode

Pick the way that suits you. Each takes about two minutes.

### Use Spiral's MCP server

1. **Add the server**: Leave out `--global` to add Spiral to the current project only. No header and no client ID or secret: opencode registers itself with Spiral.

```bash
opencode mcp add spiral --global --url https://api.spiral.ai/mcp
```

2. **Sign in**: Your browser opens. Sign in to Spiral, pick the organization and click Authorize, then return to the terminal. No API key. Inside opencode, `/mcps` starts the same sign-in.

```bash
opencode mcp auth spiral
```

3. **Check it**: Spiral shows as connected.

```bash
opencode mcp list
```

### Use the Spiral skill

1. **Send opencode this message**: Your agent reads Spiral's skill and sets itself up.

```
set up https://spiral.ai/SKILL.md
```

2. **Sign in or paste a key**: Approve Spiral in the browser, or give the agent a key from the console.

### Use the Spiral CLI

1. **Install and sign in**: Installs the Spiral CLI, signs you in and adds its skill to your coding agents.

```bash
npx -y spiral-cli@latest init
```

### Call the Spiral API

1. **Create an API key**: In the console, under API keys.

2. **Run Firecrawl research paper metadata and passages**: One request; the result comes back by polling or a webhook.

```bash
curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "firecrawl",
    "model": "firecrawl/research-paper",
    "input": {
      "id": "<id>"
    }
  }'
```

Then paste one of the prompts above: opencode finds Firecrawl research paper metadata and passages on Spiral, shows the price and runs it.

Setup guide in the docs: https://spiral.ai/docs/quickstarts/opencode

## Firecrawl research paper metadata and passages tools and prices

- [Firecrawl Research · Read a Paper](https://spiral.ai/tools/firecrawl/firecrawl/research-paper) (Firecrawl): $0.013 per call.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| k | 1 to 50 | — | Passage count for read mode. Only valid when query is present. |
| query |  | — | When present, returns the top matching full-text passages for this question. Omit it to inspect metadata only. |

## What can you do with Firecrawl research paper metadata and passages in opencode?

Check an implementation or technical explanation against passages from its cited research paper. A coding agent can compare those passages with project files and propose changes supported by the retrieved evidence.

### Check a citation before publishing

Retrieve passages addressing the exact claim in a draft, then decide whether the cited paper supports that wording.

### Prepare a reproduction checklist

Ask a known paper about its training procedure, evaluation data, and experimental constraints. Turn the returned evidence into a checklist for a replication attempt.

### Build a literature evidence table

For a supplied reading list, collect bibliographic metadata and passages answering the same research question across papers.

### Prepare for journal club

Pull passages about a paper's methods, results, and limitations to support a focused discussion with the original evidence beside each question.

### Compare benchmark reporting

Read selected papers for the datasets, metrics, and conditions behind their reported results before putting their numbers in a comparison.

### Review technical documentation

Compare a project's explanation of an algorithm with relevant passages from its cited paper, then flag statements that need correction or more evidence.

### Maintain a paper reading queue

Revisit a supplied list of paper identifiers and collect metadata or newly available passages for questions left unanswered in earlier reads.

## Overview

- [Firecrawl](https://spiral.ai/providers/firecrawl)
- [All opencode guides](https://spiral.ai/integrations/opencode)

## Firecrawl research paper metadata and passages in other agents

- [Amp](https://spiral.ai/integrations/amp/firecrawl-research-paper-metadata-and-passages)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/firecrawl-research-paper-metadata-and-passages)
- [Claude](https://spiral.ai/integrations/claude-desktop/firecrawl-research-paper-metadata-and-passages)
- [Claude Code](https://spiral.ai/integrations/claude-code/firecrawl-research-paper-metadata-and-passages)
- [Cline](https://spiral.ai/integrations/cline/firecrawl-research-paper-metadata-and-passages)
- [Codex](https://spiral.ai/integrations/codex/firecrawl-research-paper-metadata-and-passages)
- [Cursor](https://spiral.ai/integrations/cursor/firecrawl-research-paper-metadata-and-passages)
- [Devin](https://spiral.ai/integrations/devin/firecrawl-research-paper-metadata-and-passages)
- [dots](https://spiral.ai/integrations/dots/firecrawl-research-paper-metadata-and-passages)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/firecrawl-research-paper-metadata-and-passages)
- [Gemini](https://spiral.ai/integrations/gemini/firecrawl-research-paper-metadata-and-passages)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/firecrawl-research-paper-metadata-and-passages)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/firecrawl-research-paper-metadata-and-passages)
- [goose](https://spiral.ai/integrations/goose/firecrawl-research-paper-metadata-and-passages)
- [Grok](https://spiral.ai/integrations/grok/firecrawl-research-paper-metadata-and-passages)
- [Grok Build](https://spiral.ai/integrations/grok-build/firecrawl-research-paper-metadata-and-passages)
- [Hermes](https://spiral.ai/integrations/hermes/firecrawl-research-paper-metadata-and-passages)
- [Instinct](https://spiral.ai/integrations/instinct/firecrawl-research-paper-metadata-and-passages)
- [Manus](https://spiral.ai/integrations/manus/firecrawl-research-paper-metadata-and-passages)
- [Muse](https://spiral.ai/integrations/muse/firecrawl-research-paper-metadata-and-passages)
- [Muse Code](https://spiral.ai/integrations/muse-code/firecrawl-research-paper-metadata-and-passages)
- [n8n](https://spiral.ai/integrations/n8n/firecrawl-research-paper-metadata-and-passages)
- [Notion](https://spiral.ai/integrations/notion/firecrawl-research-paper-metadata-and-passages)
- [OpenClaw](https://spiral.ai/integrations/openclaw/firecrawl-research-paper-metadata-and-passages)
- [Perplexity](https://spiral.ai/integrations/perplexity/firecrawl-research-paper-metadata-and-passages)
- [Raycast](https://spiral.ai/integrations/raycast/firecrawl-research-paper-metadata-and-passages)
- [VS Code](https://spiral.ai/integrations/vscode/firecrawl-research-paper-metadata-and-passages)
- [Windsurf](https://spiral.ai/integrations/windsurf/firecrawl-research-paper-metadata-and-passages)
- [Zapier](https://spiral.ai/integrations/zapier/firecrawl-research-paper-metadata-and-passages)

## More opencode guides

- [Firecrawl related research papers](https://spiral.ai/integrations/opencode/firecrawl-related-research-papers)
- [Gemini content classification](https://spiral.ai/integrations/opencode/gemini-content-classification)
- [Firecrawl paper search](https://spiral.ai/integrations/opencode/firecrawl-paper-search)
- [GitHub Repository](https://spiral.ai/integrations/opencode/github-repository)
- [Firecrawl government documents](https://spiral.ai/integrations/opencode/firecrawl-government-documents)
- [GitHub contribution activity](https://spiral.ai/integrations/opencode/github-contribution-activity)

## Questions about Firecrawl research paper metadata and passages in opencode

**Can opencode use Firecrawl research paper metadata and passages?**

Yes. Add Spiral to opencode as an MCP server, and opencode can find and run Firecrawl research paper metadata and passages like any built-in tool.

**How much does Firecrawl research paper metadata and passages cost in opencode?**

$0.013 per call. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your opencode plan is separate.

**Do I need a Firecrawl account to use Firecrawl research paper metadata and passages in opencode?**

No. Spiral runs Firecrawl research paper metadata and passages on its own Firecrawl account. You sign in to Spiral once and never paste a key.

**How long does it take to set up Firecrawl research paper metadata and passages in opencode?**

About two minutes: add the server, then sign in, then check it.

**Does opencode wait while Firecrawl research paper metadata and passages runs?**

Firecrawl research paper metadata and passages runs in the background. opencode starts the run, checks on it and gives you the json when it's ready.

**What research does Firecrawl cover?**

The Research Index contains roughly 43 million abstracts. About 90% is biomedical and life sciences from PubMed, bioRxiv, and medRxiv, with arXiv coverage for physics, mathematics, and computer science.

**Does it return an abstract or text from inside the paper?**

It supports both: metadata inspection returns the abstract and bibliographic details, while a question retrieves matching full-text passages from one paper. Use the passage response to examine a specific method or result.

**Is full text available for every paper?**

No. Firecrawl documents an unavailability notice when it cannot return full text, so the abstract count does not establish full-text coverage.

**Which paper identifiers does Firecrawl recognize?**

Firecrawl supports arXiv, PMC, PMID, and DOI identifiers for known-paper metadata lookup. These let you reference papers across its biomedical and arXiv coverage.

**Can I reuse retrieved arXiv text under one license?**

Check the license of the particular paper version you intend to reuse. arXiv explicitly says different versions of the same work can have different licenses.

