Exa is a neural search engine built for finding information by meaning rather than just matching keywords. Search the web for relevant articles, research papers, company information, code, and news; extract clean content from webpages; find similar links; and retrieve structured results with source metadata for research and AI applications.
OpenCode is an open-source agent for the terminal. Remote MCP servers go in its config file and sign in through OAuth.
This guide connects Exa MCP to OpenCode through MewCP, so OpenCode can use Exa MCP's 3 tools, like web_search_exa, web_fetch_exa and agent_run, without your Exa MCP credentials ever reaching the app.
Exa MCP signs in through managed OAuth. MewCP stores the token encrypted, refreshes it before it expires and injects it only at call time. Your agent never holds it, so it can never leak it.
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 MCP works the same way in every client below. Pick yours for its own guide.
Free to start.
Scope access to the exact Exa MCP 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/opencode/opencode.json, or opencode.json in your project root.
Start a new chat and ask: "List the tools you can use from MewCP." You should see your connected apps.
Search the web for any topic and get clean, ready-to-use content. Best for: Finding current information, news, facts, people, companies, or answering questions about any topic. Returns: Clean text content from top search results. Query tips: describe the ideal page, not keywords. "blog post comparing React and Vue performance" not "React vs Vue". Use category:people / category:company to search through Linkedin profiles / companies respectively. If highlights are insufficient, follow up with web_fetch_exa on the best URLs.
Read a webpage's full content as clean markdown. Use after web_search_exa when highlights are insufficient or to read any URL. Best for: Extracting full content from known URLs. Batch multiple URLs in one call. Returns: Clean text content and metadata from the page(s).
Start or resume an Exa Agent run for multi-step research, list-building, or enrichment. Use it instead of running many searches yourself when a task needs multiple searches, cross-source verification, or a structured table of results. Long-running: returns a run ID; resume with runId when the tool reports the run is still running. Not for a single question or lookup (use web_search_exa) or reading a known URL (use web_fetch_exa). An interrupted tool call is not an explicit cancellation request.
