[Integrations](https://spiral.ai/integrations) › [opencode](https://spiral.ai/integrations/opencode) › [Stack Exchange question search](https://spiral.ai/integrations/opencode/stack-exchange-question-search)

# How to Use Stack Exchange question search in opencode

Finds questions on one Stack Exchange site and returns question records with titles, tags, scores, and links. Use it to discover relevant discussions before inspecting their answers.

|  |  |
| --- | --- |
| Model | Stack Exchange question search |
| Available through | Alexandria |
| Category | Social Media |
| Price | $0.00873 per call. |
| Returns | json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Stack Exchange question search in opencode

- Use Stack Exchange question search to find Stack Overflow discussions about PostgreSQL deadlocks. Compare the returned problem descriptions with our transaction code and propose a small reproduction case.
- Use Stack Exchange question search to look this up and give me the result as a table. Save the result in ./assets.
- Pull the latest numbers from Stack Exchange question search and tell me what changed since last week.
- Check Stack Exchange question search and summarize what you find in three bullet points.
- Pull the newest data from Stack Exchange question search and give me the result as a table.

## How to set up Stack Exchange question search 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 Stack Exchange question search**: 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": "alexandria",
    "model": "stackexchange-com/questions/search",
    "input": {
      "q": "<q>"
    }
  }'
```

Then paste one of the prompts above: opencode finds Stack Exchange question search on Spiral, shows the price and runs it.

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

## Stack Exchange question search tools and prices

- [Stack Exchange · Search](https://spiral.ai/tools/alexandria/stackexchange-com/questions/search) (Alexandria): $0.00873 per call.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| q |  | — | Free-text query matched against title and body, or up to 5 such terms searched in one call (one upstream request per term; `questions` is the merged, de-duplicated union and `terms` reports each term's own count and total). The site's search syntax applies: `[tag]` matches a tag, quotes match an exact phrase. |
| key |  | — | Optional Stack Exchange application key. Raises the per-IP quota from 300 to 10,000 requests per day and unlocks pages above 25, which the API refuses anonymously. Keys are public identifiers, not secrets. |
| max |  | — | Upper bound on the sort field: score for `sort: votes`, Unix seconds for `activity` or `creation`. Not accepted with `relevance`. |
| min |  | — | Lower bound on the sort field: score for `sort: votes`, Unix seconds for `activity` or `creation`. Not accepted with `relevance`. |
| url |  | — | A pasted site search URL (https://stackoverflow.com/search?q=..., any Stack Exchange host) or tag listing URL (https://superuser.com/questions/tagged/windows+powershell). The site comes from the host, `q` from the search URL and `tagged` from the listing path; `tab` maps to `sort` (a tag listing defaults to `creation`, like the site). Not combinable with `q` or `tagged`; an explicit `site` must match the host. |
| body |  | — | Text that must appear in the body. |

## What can you do with Stack Exchange question search in opencode?

Build a cited troubleshooting guide around the libraries and errors in your project. A coding agent can use Stack Exchange community information, questions, answers, and recorded edits to select relevant evidence and check whether saved explanations have changed.

### Build a troubleshooting handbook

Choose the relevant community, find recurring PostgreSQL errors, collect accepted solutions, and compare other answers against each question's constraints.

### Review migration advice

Find communities covering Ubuntu and Python, search migration problems, collect accepted solutions, and inspect cited answers and their revisions for changes in recommended commands.

### Find gaps in product documentation

Locate the community serving a product's users, search recurring configuration questions, and compare problem descriptions with the explanations supplied in answers.

### Prepare a weekly topic digest

Find recent Kubernetes discussions, summarize accepted solutions and competing answers, and review recorded edits to explanations already covered in earlier digests.

### Explain changes in technical advice

Find discussions about Python packaging, inspect individual answers and alternatives, and compare recorded revisions to explain how installation recommendations changed.

## Overview

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

## Stack Exchange question search in other agents

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

## More opencode guides

- [Stack Exchange question details](https://spiral.ai/integrations/opencode/stack-exchange-question-details)
- [Stack Exchange site directory](https://spiral.ai/integrations/opencode/stack-exchange-site-directory)
- [Stack Exchange question answers](https://spiral.ai/integrations/opencode/stack-exchange-question-answers)
- [Telegram Channel Details](https://spiral.ai/integrations/opencode/telegram-channel-details)
- [Stack Exchange post edit history](https://spiral.ai/integrations/opencode/stack-exchange-post-edit-history)
- [Telegram Channel Posts ScrapeCreators](https://spiral.ai/integrations/opencode/telegram-channel-posts-scrapecreators)

## Questions about Stack Exchange question search in opencode

**Can opencode use Stack Exchange question search?**

Yes. Add Spiral to opencode as an MCP server, and opencode can find and run Stack Exchange question search like any built-in tool.

**How much does Stack Exchange question search cost in opencode?**

$0.00873 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 an Alexandria account to use Stack Exchange question search in opencode?**

No. Spiral runs Stack Exchange question search on its own Alexandria account. You sign in to Spiral once and never paste a key.

**How long does it take to set up Stack Exchange question search in opencode?**

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

**Does opencode wait while Stack Exchange question search runs?**

Stack Exchange question search runs in the background. opencode starts the run, checks on it and gives you the json when it's ready.

**Does Stack Exchange search cover the whole network at once?**

Question searches run against one community at a time. The site directory lists communities across the network so you can choose where to search.

**How fresh is Stack Exchange data?**

API responses are heavily cached, and Stack Exchange considers repeating an equivalent request more than once per minute abusive. The site directory changes much less often; its documentation recommends caching it for at least one day.

**Does one response contain every matching result?**

Stack Exchange generally limits upstream result pages to 100 items, and an endpoint may return fewer. A response indicating more results requires additional pages before the collection is complete.

**Does an accepted answer mean the solution is still correct?**

Acceptance means the question author received an answer that worked for them personally. Stack Exchange explicitly warns that authors may leave an answer accepted even after a better answer appears.

**Does revision history show every edit separately?**

No. Stack Exchange documents that multiple edits can result in a single revision, so recorded revisions cannot establish the exact number of editing actions.

