A powerful neural search integration that enables AI agents to perform advanced web crawling and deep research using the Exa protocol.
The fastest way to install a skill directly from the registry.
npx clawhub@latest install mcp-skill
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
Copy this prompt to OpenClaw to install it automatically.
Help me install mcp-skill using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Get the raw skill files in a ZIP archive.
The Exa Search & Research MCP skill is a specialized bridge between the Exa API and AI agents. It leverages neural search capabilities to provide more relevant and context-aware results than traditional keyword-based search engines. By integrating this into Openclaw Skills, developers can empower their agents to look up code context, crawl specific websites, and conduct multi-step deep research sessions.
This skill is designed for high-performance data retrieval, allowing agents to navigate the web with surgical precision. Whether you are building a research assistant or an automated developer tool, this skill provides the necessary endpoints to turn the entire web into a structured knowledge base.
To utilize this skill, you must have an active Exa API key and configure it within your environment.
# Set your Exa API Key
export EXA_API_KEY="your_exa_api_key_here"
# The skill connects to the following MCP endpoint:
# https://mcp.exa.ai/mcp
The skill organizes data into structured JSON objects suitable for LLM processing. Below is a breakdown of the primary data structures:
| Data Type | Description | Key Fields |
|---|---|---|
| Search Result | Individual web page data | title, url, score, publishedDate, text |
| Research Status | Status of deep research jobs | status, job_id, findings_summary |
| Company Info | Targeted corporate data | company_name, industry, linkedin_profile, description |
| Code Context | Extracted snippets for devs | file_path, code_content, repository_url |
Loading
OpenProse is a specialized programming language that transforms LLMs into high-fidelity virtual machines capable of orchestrating complex multi-agent sessions.

A seamless SSH-based tunneling skill to create public HTTPS URLs for local applications without any signup or software installation.

A comprehensive interface for searching, analyzing, and executing trades on Manifold Markets prediction platforms.

A lightweight CLI tool providing high-quality, privacy-focused web search results for AI agents and developers.

A local image generation workflow supporting Stable Diffusion 1.5 and SDXL models integrated with non-blocking subagent execution.

A local semantic memory system utilizing Ollama to provide vector-based search and storage capabilities for AI agents.








































