# Remote MCP Server vs Local: Which and Why

Remote vs local MCP servers: what each setup demands, who holds credentials in each model, and when running your own server is still right.

Glossary · Published 2026-08-10, updated 2026-10-22.

> A remote MCP server runs on hosted infrastructure and is reached by a URL you paste into your AI client; a local MCP server runs on your own machine as a process the client launches. The protocol and tools are identical — what changes is who installs, patches and secures the server, and where credentials live. For connectors touching live ad spend, that is a security decision, not a convenience one.

This entry is about where an MCP server runs and who holds the keys, not about what a server is (that is the [MCP server entry](https://adcopilot.cloud/glossary/mcp-server)). Local means a process on your machine, launched by the client and configured by you. Remote means hosted infrastructure you reach as a URL. The tools can be identical; everything that differs is operational: installation, credentials, updates, revocation. For a server that can move advertising money, those differences are the decision.

## How remote differs from local

### What running locally really involves

A local Google Ads MCP server is a small self-hosting project. You install a runtime — typically Python or Node — then assemble credentials: a Google Cloud project, [Google Ads API access](https://adcopilot.cloud/google-ads-api-access) on that project, an OAuth client, and a refresh token you generate and paste into a config file on disk. When the server updates, you update it. When the API changes versions, you migrate. When the laptop sleeps mid-call, that is your outage. None of this is exotic for a developer; all of it is real work, repeated on every machine that needs access.

### What remote changes

A hosted connector inverts the setup. You paste the connector URL into your AI client and sign in with your own Google account — an OAuth consent, no password shared. There is nothing to install, so non-developers can connect. Patching is central: the vendor updates once and every user is current. And access control becomes administrative rather than physical: a connector can be scoped to specific accounts, revoked per person, or killed org-wide without touching anyone's laptop.

## The trust trade: who holds credentials in each model

This is the honest core of the choice. Local custody means the refresh token sits in files on your machine: nothing leaves your hardware, and its safety equals your machine's safety — disk encryption, OS updates, who else has admin. Remote custody means the vendor stores the token, and their [security posture](https://adcopilot.cloud/security) becomes part of yours: encryption at rest, whether anything beyond the token is stored, audit logging, revocation paths, verified OAuth status. Neither model is free of trust. Local trusts your operational discipline; remote trusts a vendor's — and a vendor you can interrogate, scope and revoke is a fair counterparty to a laptop you never audit.

## Hosting decides who gets to use the agent

Hosting determines who can use the AI at all. Local servers gate access on comfort with runtimes and tokens — in practice, developers. Remote connectors make "paste this URL" the entire onboarding, which is what lets an account manager or a founder use the same tools as the engineer.

Hosting also determines what happens on the worst day. With local servers, offboarding a person or containing a leak means finding every machine with a token in a config file. With a hosted connector, it is revoking a key — and with per-member sign-in, revoking one person's key touches nobody else's.

When is local still the right call? When you are a developer testing against your own account; when policy forbids third-party credential custody; when you want to modify the server's code itself. Those are real cases. For a team operating live budgets through AI clients, the hosted model — scoped, revocable, centrally patched — is the one that survives contact with staff turnover.

Start with [what an MCP server is](https://adcopilot.cloud/glossary/mcp-server); if you are weighing self-hosting, the [Google Ads API access guide](https://adcopilot.cloud/google-ads-api-access) shows exactly what the credential assembly involves.

## Questions

### Is a remote MCP server less secure than local?

It is differently secure. Local keeps credentials on hardware you control — and makes you responsible for OS hygiene, plaintext config files, updates and anyone who shares the machine. Remote concentrates custody with a vendor — who must then show encryption at rest, scoping, audit logs, revocation and verified OAuth. The honest comparison is your operational discipline against the vendor's, not cloud versus laptop.

### Do remote MCP servers work in every client?

Most major clients — Claude (desktop and web), Claude Code, ChatGPT, GitHub Copilot, Gemini CLI, Cursor, OpenCode — connect to remote servers over streamable HTTP. Support arrived at different speeds, and a few clients still handle only local process-based servers or lag on auth flows. Check your client's connector settings for a remote server or URL option before assuming.

---

This is the markdown copy of https://adcopilot.cloud/glossary/remote-mcp-server. The index of the site's pages is https://adcopilot.cloud/llms.txt.
