← 返回 Skills 市场

Exa Web Search Nodeskai

Name: Exa Web Search Nodeskai
Author: yumoezhung

作者 YumoeZhung · GitHub ↗ · v1.0.0

cross-platform ✓ 安全检测通过

320

总下载

当前安装

版本数

在 OpenClaw 中安装

/install exa-web-search-nodeskai

功能描述

NodeSkai's optimized Free AI search via Exa MCP. Enhanced web search for news/info, code search for docs/examples from GitHub/StackOverflow, and deep company...

使用说明 (SKILL.md)

Exa Web Search (Free)

Neural search for web, code, and company research. No API key required.

Setup

Verify mcporter is configured:

mcporter list exa

If not listed:

mcporter config add exa https://mcp.exa.ai/mcp

Core Tools

web_search_exa

Search web for current info, news, or facts.

mcporter call 'exa.web_search_exa(query: "latest AI news 2026", numResults: 5)'

Parameters:

query - Search query
numResults (optional, default: 8)
type (optional) - "auto", "fast", or "deep"

get_code_context_exa

Find code examples and docs from GitHub, Stack Overflow.

mcporter call 'exa.get_code_context_exa(query: "React hooks examples", tokensNum: 3000)'

Parameters:

query - Code/API search query
tokensNum (optional, default: 5000) - Range: 1000-50000

company_research_exa

Research companies for business info and news.

mcporter call 'exa.company_research_exa(companyName: "Anthropic", numResults: 3)'

Parameters:

companyName - Company name
numResults (optional, default: 5)

Advanced Tools (Optional)

Six additional tools available by updating config URL:

web_search_advanced_exa - Domain/date filters
deep_search_exa - Query expansion
crawling_exa - Full page extraction
people_search_exa - Professional profiles
deep_researcher_start/check - AI research agent

Enable all tools:

mcporter config add exa-full "https://mcp.exa.ai/mcp?tools=web_search_exa,web_search_advanced_exa,get_code_context_exa,deep_search_exa,crawling_exa,company_research_exa,people_search_exa,deep_researcher_start,deep_researcher_check"

# Then use:
mcporter call 'exa-full.deep_search_exa(query: "AI safety research")'

Tips

Web: Use type: "fast" for quick lookup, "deep" for thorough research
Code: Lower tokensNum (1000-2000) for focused, higher (5000+) for comprehensive
See examples.md for more patterns

Resources

安全使用建议

This skill is coherent: it simply documents mcporter commands that point at an Exa MCP endpoint. Before installing, verify the mcporter binary is legitimate and under your control, and confirm the Exa endpoints (https://mcp.exa.ai and the referenced GitHub/npm projects) are trustworthy. Treat any query you send as visible to that external service—do not include secrets, private URLs, or confidential data. If you need stronger guarantees, prefer a skill with a published homepage or an official source, or run mcporter calls in an isolated environment or behind egress controls. If you plan to let the agent call skills autonomously, consider restricting autonomous use or auditing calls to avoid accidental disclosure.

功能分析

Type: OpenClaw Skill Name: exa-web-search-nodeskai Version: 1.0.0 The skill bundle provides a legitimate interface for the Exa AI Model Context Protocol (MCP) search service. It uses the 'mcporter' utility to perform web, code, and company searches via official Exa AI endpoints (mcp.exa.ai). No malicious code, data exfiltration, or prompt injection attempts were found in SKILL.md or references/examples.md.

能力评估

✓ Purpose & Capability

Name/description match the runtime instructions: all SKILL.md examples call mcporter to invoke exa.* endpoints. Declaring mcporter as a required binary is appropriate for a mcporter-based search integration. Provided GitHub/npm/docs links align with the described Exa MCP service.

ℹ Instruction Scope

Instructions are narrowly scoped to running mcporter commands and adding an MCP config URL. They do not instruct reading local files, environment variables, or unrelated system state. However, the skill tells the agent to configure mcporter to use https://mcp.exa.ai/mcp (and a variants URL with tool flags) — this will send user queries and any passed content to that external endpoint. Advanced tools (crawling, deep_researcher, people_search) can cause broader external crawling/collection if used.

✓ Install Mechanism

There is no install spec and no code files (instruction-only), so nothing will be written to disk by the skill itself. The only runtime dependency is the mcporter binary which is declared. This is the lowest-risk install posture for a skill, but mcporter itself is the trust boundary.

✓ Credentials

The skill requests no environment variables, credentials, or config paths. That is proportional to a read-only web/search integration. Note: user queries (which may include secrets) will be transmitted to the external MCP endpoint if used.

✓ Persistence & Privilege

always is false and the skill does not request elevated persistence or to modify other skills. The skill can be invoked autonomously by the agent (platform default) — combined with external network calls this increases exposure only if the agent invokes it without user oversight.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install exa-web-search-nodeskai
安装完成后，直接呼叫该 Skill 的名称或使用 /exa-web-search-nodeskai 触发
根据 Skill 的参数说明提供必要输入，即可获得结构化输出

版本历史

v1.0.0

- Initial release of exa-web-search-nodeskai. - Offers AI-powered web, code, and company research with no API key required. - Supports core tools for web search, code context (from GitHub/Stack Overflow), and company research. - Provides optional advanced tools for deeper domain/date-filtered search, profile lookups, and research agents via configuration. - Simple setup and usage instructions included.

元数据

Slug exa-web-search-nodeskai

版本 1.0.0

许可证 —

累计安装 0

当前安装数 0

历史版本数 1

常见问题