How to Use Read the Docs page index in Claude Code
Returns the Sphinx or MkDocs page index for a documentation version. Use it to map available pages and choose what to read without relying on a topic search.
Prompts to try with Read the Docs page index in Claude Code
Copy an example into Claude Code, or ask in your own words.
Use Read the Docs page index for pypdf's stable documentation to identify pages worth consulting before changing this repository's PDF extraction code.
Use Read the Docs page index to look this up and give me the result as a table. Save the result in ./assets.
Pull the latest numbers from Read the Docs page index and tell me what changed since last week.
Check Read the Docs page index and summarize what you find in three bullet points.
Pull the newest data from Read the Docs page index and give me the result as a table.
How to set up Read the Docs page index in Claude Code
Pick the way that suits you. Each takes about two minutes.
Use Spiral's MCP server
- Add the hosted server
This adds Spiral to the current project. Add --scope user to use it in every project.
claude mcp add --transport http spiral https://api.spiral.ai/mcp
- Sign in
Start claude, type /mcp, choose spiral and Authenticate. Sign in to Spiral in the browser and click Authorize. No API key.
Use the Spiral skill
- Send Claude Code 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 Read the Docs page index
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": "alexandria", "model": "readthedocs-io/developer-documentation/list_pages", "input": { "project": "<project>" } }'
Then paste one of the prompts above: Claude Code finds Read the Docs page index on Spiral, shows the price and runs it.
Read the Docs page index providers and prices
Spiral runs Read the Docs page index through Alexandria. Open a card for today's price, with every fee included.
Settings you can ask for
Ask Claude Code for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Limit | 1 to 1000 | Pages to return (default 200). | |
| Offset | 0 to 100000 | Pages to skip; pass next_offset to continue. |
Every API field of Read the Docs · List pages is on its tool page: open its card above.
What can you do with Read the Docs page index in Claude Code?
Prepare a Pillow or pypdf code change using documentation matched to the project's dependency version. Combine Read the Docs project details, page indexes, search hits, and page text to support the implementation.
Prepare a dependency upgrade
For a Pillow upgrade, identify published documentation versions, inventory relevant reference pages, locate affected APIs, and read the instructions needed for a migration checklist.
Answer a technical support question
Investigate a pypdf text extraction question by checking the documentation versions, browsing available guides, finding relevant sections, and reading the supporting pages before drafting an answer.
Build a documentation reading plan
Create an Argo CD reading plan from published versions, available guide pages, topic search results, and selected page content. Organize it around the team's deployment questions.
Draft an operations runbook
Check Argo CD's published documentation versions, map operational guides, find sync-related sections, and read their instructions to draft a runbook with supporting documentation links.
Review documentation changes
Compare repeated checks of pypdf's published versions, page inventory, topic search results, and selected page text. Report newly available documentation separately from changes to existing instructions.
Evaluate a library against requirements
Assess Pillow for an image processing task by reviewing its published documentation versions, mapping reference pages, locating required operations, and reading the documented behavior before recommending an implementation.
More on Read the Docs page index and Claude Code
Overview
Read the Docs page index in other agents
Questions about Read the Docs page index in Claude Code
Can Claude Code use Read the Docs page index?
Yes. Add Spiral to Claude Code as an MCP server, and Claude Code can find and run Read the Docs page index like any built-in tool.
How much does Read the Docs page index cost in Claude Code?
$0.00873 per call. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Claude Code plan is separate.
Do I need an Alexandria account to use Read the Docs page index in Claude Code?
No. Spiral runs Read the Docs page index on its own Alexandria account. You sign in to Spiral once and never paste a key.
How long does it take to set up Read the Docs page index in Claude Code?
About two minutes: add the hosted server, then sign in.
Does Claude Code wait while Read the Docs page index runs?
Read the Docs page index runs in the background. Claude Code starts the run, checks on it and gives you the json when it's ready.
Does latest mean the latest released software?
No. Read the Docs says the latest documentation can include features that have not been deployed. Choose documentation that matches the software release you need.
When does documentation become searchable?
For Sphinx documentation, Read the Docs indexes documents after a successful build. Search freshness therefore depends on the project's successful documentation builds.
How much historical documentation is available?
Availability depends on which versions the project keeps active. Read the Docs deletes documentation content for inactive versions, so a repository's old tags do not guarantee readable historical docs.
Can a project be missing from documentation search?
Yes. In February 2026, Read the Docs reported removing projects with no builds or searches in the preceding 90 days from its search index. A missing search result alone does not establish that the documentation page is gone.
How many results does Read the Docs search return by default?
Read the Docs reported reducing its upstream default to 15 results in February 2026. That source default does not establish how many results the gateway endpoint returns.
Start using Read the Docs page index in Claude Code
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Claude Code:
set up https://spiral.ai/SKILL.md


