nansen-web-searcher — Claude Code skill: parallel web search
Runs several search queries at once through the Serper API and returns titles, links and snippets. Useful when on-chain Nansen data needs fresh news or prices next to it.
npx skills add nansen-ai/nansen-cli --skill nansen-web-searcher -a claude-codeWhat nansen-web-searcher does
The skill wraps the nansen web search command. Queries go in as positional arguments or --query flags, and both forms combine: everything is searched in parallel. Each query returns 10 results by default, --num-results takes 1 to 20, and --pretty prints readable JSON.
The output is results[], one entry per query, each holding organic[] with title, link, snippet and date, plus an optional knowledge_graph. Some domains never show up: paywalled and unfetchable sites such as bloomberg.com and twitter.com are excluded. For a specific URL there is nansen web fetch.
You need the nansen binary and a NANSEN_API_KEY, which takes precedence over a browser session. Run nansen auth status to check. If the selection turns anonymous or a renewal fails, the skill stops rather than falling back to anonymous x402 payment.
What it helps with
- pull fresh news on several coins in one call
- add market prices to on-chain Nansen data
- check what is being written about a token before reading transactions
- get links and snippets for a list of queries without searching by hand
- grab publication dates alongside titles and links
Example prompts for the agent
- search the web for solana ecosystem news, 5 results per query
- run queries for "ethereum ETF" and "bitcoin ETF", 3 results each
- what's being written about bitcoin right now — add it to the Nansen data
How to install nansen-web-searcher
1Skills CLI (Vercel)
npx skills add nansen-ai/nansen-cli --skill nansen-web-searcher -a claude-code2Manually: put the files in place
~/.claude/skills/nansen-web-searcher/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/nansen-web-searcher/
1Skills CLI (Vercel)
npx skills add nansen-ai/nansen-cli --skill nansen-web-searcher -a codex2Manually: put the files in place
.agents/skills/nansen-web-searcher/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add nansen-ai/nansen-cli --skill nansen-web-searcher -a cursor2Manually: put the files in place
.cursor/skills/nansen-web-searcher/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install nansen-ai/nansen-cli nansen-web-searcher2Manually: put the files in place
.github/skills/nansen-web-searcher/SKILL.md1Skills CLI (Vercel)
npx skills add nansen-ai/nansen-cli --skill nansen-web-searcher -a gemini-cli2Platform CLI
gemini skills install https://github.com/nansen-ai/nansen-cli --path skills/nansen-web-searcherManually: put the files in place
.devin/skills/nansen-web-searcher/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add nansen-ai/nansen-cli --skill nansen-web-searcher -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about nansen-web-searcher
How do I install nansen-web-searcher in Claude?
Run npx skills add nansen-ai/nansen-cli --skill nansen-web-searcher -a claude-code. The skill lands in ~/.claude/skills/nansen-web-searcher/SKILL.md.
What does nansen-web-searcher do?
It searches the web for one or more queries in parallel via the Serper API and returns titles, links, snippets and dates. Handy when on-chain Nansen data alone is not enough context.
What does the skill need to run?
The nansen binary and a NANSEN_API_KEY. The key takes precedence over a browser session, and nansen auth status shows the current state.
Source text
SKILL.md · MIT
---
name: nansen-web-searcher
description: Search the web for one or more queries in parallel. Use when you need current information, news, prices, or any web content to complement on-chain Nansen data.
metadata:
openclaw:
requires:
bins:
- nansen
primaryEnv: NANSEN_API_KEY
install:
- kind: node
package: nansen-cli
bins: [nansen]
allowed-tools: Bash(nansen:*)
---
## Authentication
Nansen account API calls accept a selected `nansen:api` browser session or conventional API key with the same permissions. `NANSEN_API_KEY` takes precedence; optional `primaryEnv` preserves configured-key injection. Run `nansen auth status` for offline selection. Cached access expiry alone permits automatic renewal during an authorized task. Stop on anonymous selection, invalid state, blocked/uncertain renewal or actual auth failure; never drop a credential or fall back to anonymous x402 payment. Browser login does not grant wallet signing, privileged service identity or a persistent MCP integration key. Preserve all confirmation, signing, sanctions and geographic checks below. Browser login is available in CLI 2.0.0 within the [macOS arm64 preview scope](https://github.com/nansen-ai/nansen-cli/blob/main/docs/browser-login.md#preview-platform-scope).
# Web Search
Search the web for one or more queries in parallel via the Serper API.
```bash
nansen web search "bitcoin price"
nansen web search "solana ecosystem news" --num-results 5
nansen web search --query "ethereum ETF" --query "bitcoin ETF" --num-results 3
```
Positional args and `--query` flags can be combined — all become queries.
| Flag | Values | Default | Purpose |
|------|--------|---------|---------|
| `--query` | string | — | Query string (repeatable for multiple queries) |
| `--num-results` | 1–20 | 10 | Results per query |
| `--pretty` | flag | off | Human-readable JSON |
Returns `results[]` — one entry per query, each with `organic[]` (title, link, snippet, date) and optional `knowledge_graph`.
**Note:** Some domains are excluded from results (paywalled/unfetchable sites like bloomberg.com, twitter.com). Use `nansen web fetch` to retrieve content from specific URLs.
© nansen-ai · MIT · nansen-ai/nansen-cli
