How to Use Firecrawl related research papers in Amp
Find ranked research papers connected to a seed paper through citations and related work, with paper records and the evaluated candidate pool size. Use it to trace references, discover citing papers, or build a reading list around a known study.
Prompts to try with Firecrawl related research papers in Amp
Copy an example into Amp, or ask in your own words.
Use Firecrawl related research papers with arxiv:1706.03762 to find 20 candidates about memory-efficient attention. Save the returned identifiers, titles, abstracts, and scores in research/attention-candidates.json.
Use Firecrawl related research papers with arxiv:2006.11239 to find 15 papers about faster diffusion sampling. Create a Markdown reading list in the project using the returned titles and abstracts.
Use Firecrawl related research papers to find papers citing arxiv:2106.09685, focused on parameter-efficient adaptation. Compare their abstracts with this project's fine-tuning approach and propose three papers to read.
Use Firecrawl related research papers to retrieve references from arxiv:1810.04805 relevant to language-model pretraining. Add a background-reading section to the project's research notes.
Use Firecrawl related research papers with arxiv:2005.11401 to find 20 candidates about retrieval-augmented generation evaluation. Build a CSV of returned identifiers, titles, abstracts, and scores for manual screening.
How to set up Firecrawl related research papers in Amp
Pick the way that suits you. Each takes about two minutes.
Use Spiral's MCP server
- Add the server
No header and no client ID or secret: Amp registers itself with Spiral.
amp mcp add spiral https://api.spiral.ai/mcp
- Sign in
Start amp. Amp opens Spiral's sign-in page in your browser: sign in, pick the organization and click Authorize. No API key.
- Check it
amp mcp doctor
Use the Spiral skill
- Send Amp this message
Your agent reads Spiral's skill and sets itself up.
set up https://spiral.ai/SKILL.md
- Sign in or paste a key
Approve Spiral in the browser, or give the agent a key from the console.
Use the Spiral CLI
- Install and sign in
Installs the Spiral CLI, signs you in and adds its skill to your coding agents.
npx -y spiral-cli@latest init
Call the Spiral API
- Create an API key
In the console, under API keys.
- Run Firecrawl related research papers
One request; the result comes back by polling or a webhook.
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-similar", "input": { "id": "<id>", "intent": "<intent>" } }'
Then paste one of the prompts above: Amp finds Firecrawl related research papers on Spiral, shows the price and runs it.
Firecrawl related research papers providers and prices
Spiral runs Firecrawl related research papers through Firecrawl. Open a card for today's price, with every fee included.
Settings you can ask for
Ask Amp for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| K | 1 to 500 | 40 | Maximum number of related papers to return. |
| Mode | similar, citers, or references | similar | Structural expansion mode. |
| Rerank | on or off | Apply an additional rerank over fused candidates. |
Every API field of Firecrawl Research · Related Papers is on its tool page: open its card above.
What can you do with Firecrawl related research papers in Amp?
Build a reading list tied to the method your project implements by expanding from its seed paper. A coding agent can organize Firecrawl's returned paper records into project notes and propose candidates for experiments.
Build a literature review reading list
Start with a study central to your topic, collect related papers, and use their titles and abstracts to shortlist the next papers to read.
Find follow-up research
Retrieve papers citing a known study and rank them around a question such as replication, efficiency, or evaluation.
Trace a method's foundations
Follow a paper's references to create a reading list of earlier work relevant to its methods.
Choose implementation candidates
Expand from a paper behind your current approach and shortlist related methods for an engineering experiment using the returned abstracts.
Prepare a journal club
Pair a seed study with related papers and citing work, then prepare an agenda that distinguishes background reading from follow-up research.
Maintain a citation watch
Repeat a citing-paper search for a fixed study and compare returned identifiers with previous results to flag newly surfaced papers.
Expand a review bibliography
Use a paper already selected for a review to find additional citation-connected candidates for screening.
Explore adjacent research
Expand from a familiar paper with a focused question, such as reducing attention memory use, and organize the returned candidates into a reading plan.
More on Firecrawl related research papers and Amp
Overview
Firecrawl related research papers in other agents
Questions about Firecrawl related research papers in Amp
Can Amp use Firecrawl related research papers?
Yes. Add Spiral to Amp as an MCP server, and Amp can find and run Firecrawl related research papers like any built-in tool.
How much does Firecrawl related research papers cost in Amp?
$0.013 per call. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Amp plan is separate.
Do I need a Firecrawl account to use Firecrawl related research papers in Amp?
No. Spiral runs Firecrawl related research papers 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 related research papers in Amp?
About two minutes: add the server, then sign in, then check it.
Does Amp wait while Firecrawl related research papers runs?
Firecrawl related research papers runs in the background. Amp starts the run, checks on it and gives you the json when it's ready.
Which research sources does Firecrawl cover?
Firecrawl documents roughly 43 million paper abstracts. Sources include PubMed journal articles, bioRxiv and medRxiv preprints, and arXiv papers in computer science, physics, and mathematics.
How fresh is the index?
Firecrawl's launch announcement describes daily refreshes for its arXiv and research-repository index. That statement concerns the index described at launch, rather than a documented update schedule for every source in today's larger corpus.
Can I follow citations in both directions?
Yes. You can retrieve papers that cite a seed study or papers that the seed study cites, with candidates ranked against your research intent.
How many related papers can one request return?
The documented maximum is 500 papers per request. The response also reports the size of the evaluated candidate pool.
What information comes back about a paper?
Research Index paper records include a title, abstract, canonical identifier, source identifiers, and ranking score. Related-paper discovery returns ranked candidates and the evaluated pool size.
Start using Firecrawl related research papers in Amp
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Amp:
set up https://spiral.ai/SKILL.md


