// Web search, content crawling, code context lookup, company research, and deep AI research via Exa. Use when the user needs to search the web, fetch page content from a URL, find code examples or documentation, research a company, or run a deep research report on a complex topic.
| name | exa |
| description | Web search, content crawling, code context lookup, company research, and deep AI research via Exa. Use when the user needs to search the web, fetch page content from a URL, find code examples or documentation, research a company, or run a deep research report on a complex topic. |
Web search, crawling, code context, and deep research via the Exa MCP server (exa-mcp-server).
exa-mcp-server (npm, stdio transport)~/.pi/agent/mcp.json → mcpServers.exaEXA_API_KEY in ~/.zshrc.local, interpolated via ${EXA_API_KEY}mcp gateway tool)Access all tools through the mcp gateway:
mcp({ server: "exa" }) # List available tools
mcp({ search: "exa" }) # Search for exa tools
mcp({ describe: "tool_name" }) # Show tool details
Search the web for any topic. Returns clean text content from top results.
mcp({ tool: "web_search_exa", args: '{"query": "latest AI agent frameworks", "numResults": 5}' })
| Parameter | Required | Description |
|---|---|---|
query | yes | Search query |
numResults | no | Number of results (default: 8) |
livecrawl | no | fallback (default) or preferred |
type | no | auto (default) or fast |
contextMaxCharacters | no | Max characters for context (default: 10000) |
Find code examples, documentation, and programming solutions from GitHub, Stack Overflow, and docs.
mcp({ tool: "get_code_context_exa", args: '{"query": "React useState hook examples", "tokensNum": 10000}' })
| Parameter | Required | Description |
|---|---|---|
query | yes | Programming search query |
tokensNum | no | Tokens to return, 1000–50000 (default: 5000) |
Get the full content of a specific webpage from a known URL.
mcp({ tool: "crawling_exa", args: '{"url": "https://example.com/docs"}' })
| Parameter | Required | Description |
|---|---|---|
url | yes | URL to crawl |
maxCharacters | no | Max characters to extract (default: 3000) |
Research a company for business information, news, and insights.
| Parameter | Required | Description |
|---|---|---|
companyName | yes | Company name |
numResults | no | Number of results (default: 3) |
Start an AI research agent for complex topics (15s–3min depending on model).
Start:
| Parameter | Required | Description |
|---|---|---|
instructions | yes | Detailed research question |
model | no | exa-research-fast (~15s), exa-research (15–45s), exa-research-pro (45s–3min) |
Check:
| Parameter | Required | Description |
|---|---|---|
researchId | yes | Research ID from start |
Keep calling check until status is completed.
| Variable | Location | Description |
|---|---|---|
EXA_API_KEY | ~/.zshrc.local | Exa API key from dashboard.exa.ai |
EXA_API_KEY is set: echo $EXA_API_KEYsource ~/.zshrc.localmcp({ server: "exa" })~/.pi/agent/mcp.json is valid JSONmcp({ connect: "exa" }) to force reconnectCreate, update, migrate, and debug MCP server configuration for Pi using pi-mcp-adapter. Use when adding an MCP server, editing ~/.pi/agent/mcp.json, importing MCP configs, switching from legacy MCPorter workflows, or documenting MCP setup. Use proactively when auth, server wiring, direct tools, or environment-variable based config is involved.
Create, structure, and refine Agent Skills (OpenClaw format) — the open standard for extending AI agents with specialized knowledge. Use when asked to create a SKILL.md, build an agent skill, write an OpenClaw skill, make a skill for Cursor/VS Code/Claude Code/Copilot/Gemini CLI, or package reusable agent instructions. Triggers include "create a skill", "agent skill", "SKILL.md", "openclaw", ".agents/skills", "skills for my repo", "package this workflow as a skill".
Set up GitHub repo CI with Husky git hooks, commit-check-action, conventional commits, and conventional branch naming. Handles greenfield and existing repos intelligently — detects existing CI, package managers, and config before making changes. Use when setting up CI, adding git hooks, enforcing commit conventions, or standardizing branch naming. Examples: - user: "Set up CI for this repo" → assess repo, install husky + commit-check - user: "Add conventional commits" → configure local hooks + GitHub Action - user: "Enforce branch naming" → add commit-check branch validation - user: "/setup-ci" → full CI pipeline setup with interactive questions - user: "Add husky to this project" → install and configure husky hooks
Create and manage pi skills with proper SKILL.md format, frontmatter, and organization. Use for skill creation, naming conventions, bundled resources (scripts/references/assets), progressive disclosure patterns, MCP-related skill documentation, and deciding when to use skills vs Pi MCP servers. Use proactively when user says "create a skill", "SKILL.md", "add a skill", "document this workflow", "add MCP server docs", or asks about skill structure.
Search for real-world code examples across a million GitHub repositories. Use when you need to find actual code patterns, library usage examples, or implementation patterns. Triggers include "search GitHub for", "find code examples of", "how do developers use", "show real-world usage of", or any need to see production code patterns.
RFC 2119 keywords and XML tag structure guide for agent prompts, skill definitions, and internal documentation. Use when writing, reviewing, or refactoring markdown files that instruct AI agents — including skills, prompt templates, system prompts, and workflow docs. Provides keyword semantics, XML tag catalog, nesting best practices, and before/after examples. Examples: - user: "Refactor this skill to use RFC keywords" → apply RFC 2119 keyword conventions - user: "Add XML structure to this prompt" → wrap sections in semantic XML tags - user: "Review my SKILL.md formatting" → audit RFC keyword usage and XML structure - user: "Convert this doc to RFC+XML style" → full transformation with style guide - user: "/refactor-rfc-xml ./prompts" → batch refactor all markdown in a folder