How to Use Anthropic Claude in Cursor
To use Anthropic Claude in Cursor, connect Spiral to Cursor once, then ask for what you want in plain words. Cursor can then reach all 18 Anthropic Claude tools on Spiral, priced per run from one balance.
Prompts to try with Anthropic Claude in Cursor
Copy an example into Cursor, or ask in your own words.
Ask Anthropic Claude through Spiral to review the diff on this branch and list the three riskiest changes. Save the result in ./assets.
Get a second opinion from Anthropic Claude on this function, then tell me what the call cost.
Summarize these release notes with Anthropic Claude in five bullet points.
Ask Anthropic Claude to write unit tests for the file I have open and explain each case.
Compare Anthropic Claude with my current model on this prompt and tell me which answer is better and what each cost.
How to set up Anthropic Claude in Cursor
Pick the way that suits you. Each takes about two minutes.
Use Spiral's MCP server
- Add the hosted server
Use Add to Cursor on the console's Agents & MCP page, or add this to .cursor/mcp.json (one project) or ~/.cursor/mcp.json (every project):
{ "mcpServers": { "spiral": { "url": "https://api.spiral.ai/mcp" } } } - Sign in
Open Cursor Settings › MCP, click Connect next to spiral, sign in to Spiral and click Authorize. No API key. Spiral then shows as connected, with its tools listed.
Use the Spiral skill
- Send Cursor 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 Anthropic Claude
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": "anthropic", "model": "anthropic/claude-opus-5.5", "input": { "messages": [ { "role": "system" } ] } }'
Then paste one of the prompts above: Cursor finds Anthropic Claude on Spiral, shows the price and runs it.
Anthropic Claude tools you can run in Cursor
3Ready to run from Cursor: today's price, with every fee included.
Up to $0.10686 per run at the default inputs. $5.20 per 1M input tokens, $0.26 per 1M cached input tokens, $6.50 per 1M cache write tokens, $10.40 per 1M 1-hour cache write tokens, $26.00 per 1M output tokens; for a prompt above 200,000 tokens, $10.40 per 1M input tokens, $0.52 per 1M cached input tokens, $13.00 per 1M cache write tokens, $20.80 per 1M 1-hour cache write tokens, $39.00 per 1M output tokens.
Up to $0.05343 per run at the default inputs. $2.60 per 1M input tokens, $0.13 per 1M cached input tokens, $3.25 per 1M cache write tokens, $5.20 per 1M 1-hour cache write tokens, $13.00 per 1M output tokens; for a prompt above 200,000 tokens, $5.20 per 1M input tokens, $0.26 per 1M cached input tokens, $6.50 per 1M cache write tokens, $10.40 per 1M 1-hour cache write tokens, $19.50 per 1M output tokens.
Up to $0.002672 per run at the default inputs. $0.13 per 1M input tokens, $0.013 per 1M cached input tokens, $0.1625 per 1M cache write tokens, $0.26 per 1M 1-hour cache write tokens, $0.65 per 1M output tokens.
What can you do with Anthropic Claude in Cursor?
Cursor can answer, write and review code with Anthropic Claude right in your repository and save the results where you need them: as files in your project, in a script or in your build. One sign-in covers every tool, so your code stays free of provider SDKs and keys.
Second opinions
Have another model review a diff or a plan before you commit to it.
Cheaper bulk work
Send summaries, tagging and rewrites to a smaller model and keep your agent's own model for hard steps.
Models your agent lacks
Reach open and frontier models your agent's vendor does not offer.
Code review at scale
Review every file in a pull request with one model and summarize the risks.
Long documents
Send a long spec or contract to a model with a large context window.
Structured output
Turn messy notes into JSON your code can read.
Anthropic Claude success rate and speed on Spiral
Success and speed over the last 24 hours, across every run of these tools on Spiral.
| Tool | Success | Median time | Runs |
|---|---|---|---|
| Claude Opus 5.5 | Not enough runs | ||
| Claude Sonnet 5.5 | Not enough runs | ||
| Claude Haiku 5.5 | 100.0% | 3.1s | 550 |
More on Anthropic Claude and Cursor
Anthropic Claude in other agents
Questions about Anthropic Claude in Cursor
Can Cursor use Anthropic Claude?
Yes. Add Spiral to Cursor as an MCP server, and Cursor can find and run Anthropic Claude like any built-in tool.
How much does Anthropic Claude cost in Cursor?
Each tool has its own price, for example Claude Opus 5.5: Up to $0.10686 per run at the default inputs. $5.20 per 1M input tokens, $0.26 per 1M cached input tokens, $6.50 per 1M cache write tokens, $10.40 per 1M 1-hour cache write tokens, $26.00 per 1M output tokens; for a prompt above 200,000 tokens, $10.40 per 1M input tokens, $0.52 per 1M cached input tokens, $13.00 per 1M cache write tokens, $20.80 per 1M 1-hour cache write tokens, $39.00 per 1M output tokens; Claude Sonnet 5.5: Up to $0.05343 per run at the default inputs. $2.60 per 1M input tokens, $0.13 per 1M cached input tokens, $3.25 per 1M cache write tokens, $5.20 per 1M 1-hour cache write tokens, $13.00 per 1M output tokens; for a prompt above 200,000 tokens, $5.20 per 1M input tokens, $0.26 per 1M cached input tokens, $6.50 per 1M cache write tokens, $10.40 per 1M 1-hour cache write tokens, $19.50 per 1M output tokens; Claude Haiku 5.5: Up to $0.002672 per run at the default inputs. $0.13 per 1M input tokens, $0.013 per 1M cached input tokens, $0.1625 per 1M cache write tokens, $0.26 per 1M 1-hour cache write tokens, $0.65 per 1M output tokens. You pay per run from one Spiral balance, and failed runs are free.
Do I need an Anthropic account to use Anthropic Claude in Cursor?
No. Spiral runs Anthropic Claude on its own Anthropic account. You sign in to Spiral once and never paste a key.
How long does it take to set up Anthropic Claude in Cursor?
About two minutes: add the hosted server, then sign in.
Does Cursor wait while Anthropic Claude runs?
Anthropic Claude runs in the background. Cursor starts the run, checks on it and gives you the text, json when it's ready.
Why call Anthropic Claude from Cursor?
For a second opinion, a cheaper model for bulk work, or a model your agent doesn't offer. Your agent calls Anthropic Claude through Spiral and pays only for the tokens used.
Which Anthropic Claude tools can Cursor use?
Cursor can reach all 18 Anthropic Claude tools on Spiral, covering LLM. Popular ones include Claude Opus 5.5, Claude Sonnet 5.5, and Claude Haiku 5.5. Ask for one by name, or describe the task and Cursor picks a fitting tool.
Can Cursor compare Anthropic Claude tools?
Yes. Ask Cursor to run the same request on two Anthropic Claude tools and show both results with what each cost. Each run is priced and billed on its own.
What happens if a Anthropic Claude run fails in Cursor?
It is not charged. Spiral holds the estimated price when the run starts and returns it to your balance if the run fails on Spiral's side or the provider's. Cursor gets the error and can retry or try another tool.
Is there a Anthropic Claude subscription or plan?
No. Spiral is pay as you go from one prepaid balance, with no plans or minimums, and credits never expire. Auto top-up keeps Cursor from stopping when the balance runs low.
Start using Anthropic Claude in Cursor
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Cursor:
set up https://spiral.ai/SKILL.md


