Search the web and extract content with Exa's AI-powered search engine. Perform semantic and keyword search with domain and date filtering, extract clean LLM-ready content from URLs, generate cited AI answers, and run autonomous research agents toward a goal.
Hermes is Nous Research's command-line agent. MCP servers are declared in its YAML config and reloaded without a restart.
This guide connects Exa to Hermes through MewCP, so Hermes can use Exa's 9 tools, like search_web, get_contents and get_answer, without your Exa credentials ever reaching the app.
Your Exa API key is stored encrypted and injected only at call time. Your agent never holds it, so it can never leak it, log it or paste it into a prompt.
More apps
Crawl websites and extract clean structured data optimized for AI applications and automation. Collect content from the web at scale while maintaining high-quality outputs.
Extract structured data from websites and public web pages. Fetch content, parse information and transform online data into formats that can be consumed by applications, agents and workflows.
TinyFish MCP for running AI-driven browser automation tasks, deep web research, persistent browser login profiles, remote CDP browser sessions, and agentic wallet payments.
Scrape, extract, and understand the web, plus identify any company from a domain, email, name, or transaction string. This MCP server exposes Context.dev's API for web scraping in multiple formats (raw HTML, Markdown, screenshots, images, sitemaps, and web search), schema-driven structured data extraction, design-system extraction (styleguides and fonts), and brand intelligence lookups. It's built for AI agents that read, summarize, or monitor web content, for enriching CRM, KYC, or fintech pipelines with company and brand data, and for extracting a competitor's design system or structured product and pricing data at scale.
Other clients
Exa works the same way in every client below. Pick yours for its own guide.
Free to start.
Scope access to the exact Exa tools and accounts you allow, work and personal side by side. Anything outside that scope is refused at call time, even when the model asks for it.
Each call is logged: what ran, on which account, and whether it worked. Failures come back structured, so the agent knows whether to retry instead of guessing.
Every app sits behind one secure MCP URL, and there is no server for you to deploy or keep running. Add an integration in the dashboard and it is live on the next call, with no config to change and no new credentials to wire up. Tools load only when a task needs them, so your agent stays fast and focused however many apps you connect.
Edit config.yaml in your Hermes config directory (~/.hermes).
Put this under the top-level "mcp_servers:" key.
Run /reload-mcp in Hermes, or start a fresh session. Sign in when the browser window opens.
Start a new chat and ask: "List the tools you can use from MewCP." You should see your connected apps.
Perform an Exa web search and return results. Takes a query and optional filters for domain inclusion/exclusion, date range, and search type. Returns matching web results with titles, URLs, published dates, and text snippets. Use `autoprompt` from the response to refine or repeat the search.
Extract clean, LLM-ready content from URLs. Returns structured content per URL including text, highlights, and summaries. Supports text, HTML, or markdown output formats.
Get an LLM answer to a question informed by Exa search results. Returns a generated answer text with citations from source URLs. Use for Q&A, research, and fact-finding tasks.
Creates a new Exa agent run. Starts an agent process that works toward a specified goal and returns the run details. Use the returned run ID to check status, list events, or cancel the run.
Retrieves the details of a specific agent run. Returns run status, goal, model, and result if completed. Use to check whether a run has finished or to get its output.
Retrieves a list of agent runs. Returns runs with their current status, goal, and creation timestamps. Use to browse all runs and find specific ones by their IDs.
Cancels an in-progress agent run. Stops the agent's execution and updates the run status. The response includes both the previous and current status.
DESTRUCTIVE — REQUIRES EXPLICIT USER CONFIRMATION BEFORE CALLING. Permanently deletes an existing agent run. This action is irreversible — the run record and all associated data will be permanently removed. NEVER call this tool autonomously or as part of an automated flow. You MUST stop, tell the user exactly what will be deleted and that it is permanent, and wait for their explicit written confirmation before proceeding.
Retrieves a list of events for a specific agent run. Returns chronological events including steps, tool calls, and results. Use to monitor run progress or inspect what the agent did.
