Connect AI agents to databases, data warehouses, cloud storage, and SaaS apps to query, analyze, join, validate, and transform data across multiple sources.
Codex is OpenAI's coding agent for the terminal. It reads MCP servers from its config and signs in to remote ones with OAuth.
This guide connects Marcopolo MCP to Codex through MewCP, so Codex can use Marcopolo MCP's 5 tools, like workspace_shell, connections_list and data_query, without your Marcopolo MCP credentials ever reaching the app.
Marcopolo 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
Full Google Search Console control for search analytics, sitemaps, sites, and URL inspection, directly from your AI workflows. This MCP server exposes the Google Search Console API for querying search traffic data, managing sitemaps and site properties, and inspecting the indexing status of any URL. It is built for SEO teams monitoring search performance, developers automating sitemap and property management, and analysts pulling search traffic data into reporting pipelines.
Search for available domain names and check domain availability using GoDaddy's MCP server. Discover domain ideas for businesses, products, and projects through AI assistants
Hex MCP Server lets AI agents analyze data in Hex through natural-language Threads, search projects, retrieve analysis results and visualizations, and— with editing access—create, edit, and run SQL, Python, and Markdown notebooks.
Access AI-powered MSP market intelligence with company profiles, technographics, technology stacks, reputation, hiring signals, SEO performance, security exposure, market sizing, revenue estimates, and competitive benchmarks.
Other clients
Marcopolo MCP works the same way in every client below. Pick yours for its own guide.
Free to start.
Scope access to the exact Marcopolo 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.
Run this and approve access in the browser window.
Start a new chat and ask: "List the tools you can use from MewCP." You should see your connected apps.
Run a shell command in the persistent /workspace runtime. Use for all agent-side work: query authoring, analytics, DuckDB joins, workspace files, scripts, git, diagnostics, and cron. The `connection` and `cron` CLIs exist only inside this runtime and must be invoked through this tool.
List visible Marcopolo connections and their provider authorization state. Use only entries with `queryable: true` for `data_query`. Entries with `authorization_state: "authorization_required"` need user authorization from Connections in Marcopolo; follow `next_actions`. Capabilities and workspace paths describe supported commands for authorized connections.
Run a bounded governed query against a visible connection. Use this tool in generated code that re-queries live data at view or load time: Remote Artifacts, external web apps, scheduled scripts, and any other programmatic interface that fetches fresh data on each run. Do NOT use it for agent-side analytics or one-off snapshot visualizations — use the `workspace_shell` tool with the connection query CLI instead. Pass the full workspace-relative `query_file` path including the connection prefix, e.g. `connections/<name>/queries/<file>`. Paths resolve from `/workspace`, not from any current directory. Author new query files through `workspace_shell` before calling this tool so query text is durable and reusable. Returns `rows` as a parsed list of record dicts and `row_count` as the total — no JSON parsing needed. Results are capped by `max_rows` (1–5000).
Create a browser setup URL for a credentialed connection. Use a canonical `type` when known; otherwise pass `intent_text`. For hosted demo data with no credentials, use `install_demo_connection`.
Install hosted demo data with no user credentials. Pass a demo id or natural-language request. Use `connection_setup` for real user-owned connections.
