Get AI summaries of any video or article — Sign up free
Model Context Protocol | The How | How to connect MCP Servers to Claude Desktop | CampusX thumbnail

Model Context Protocol | The How | How to connect MCP Servers to Claude Desktop | CampusX

CampusX·
6 min read

Based on CampusX's video on YouTube. If you like this content, support the original creators by watching, liking and subscribing to their content.

TL;DR

Claude Desktop can connect to MCP servers using either one-click connectors or manual JSON configuration, depending on whether a curated connector exists.

Briefing

The practical takeaway: Claude Desktop can connect to multiple MCP servers—both local and remote—either through one-click “connectors” (for common SaaS tools) or via manual JSON configuration (for custom or less common servers). That dual approach matters because it lets teams move fast with ready-made integrations while still retaining the freedom to run their own MCP servers when they need specialized capabilities.

The walkthrough starts by setting expectations for a three-part “How” series. Today’s focus is the “how” of MCP communication between a client and servers, using Claude Desktop as the client and existing MCP servers as the targets. The plan is to install Claude Desktop, then connect it to four MCP servers: two local servers and two remote servers. The local pair includes a File System MCP server (for manipulating specific directories on the machine) and a Manim MCP server (for generating math visualizations). The remote pair includes a Google Drive MCP server (for reading documents from Google Drive) and a Twitter/X MCP server (for searching and posting tweets).

A key concept introduced is how Claude Desktop connects to MCP servers. The default method uses a JSON configuration file inside the AI host (Claude Desktop), where server details are added manually. The alternative method uses “connectors,” a built-in Claude feature that links Claude Desktop to MCP servers automatically—without editing JSON. Connectors handle the behind-the-scenes work such as authentication, API keys, and secure sign-in flows, which reduces setup friction for non-technical users and improves consistency compared with manual configuration. The tradeoff is that connectors are curated and managed by Anthropic’s team, mainly around widely used SaaS tools. Because MCP is an open standard that allows anyone to build clients and servers, forcing every MCP server to rely on Anthropic-managed connectors would close the ecosystem and create a bottleneck.

The File System MCP server demo shows how connectors work in practice: after installing the connector and granting access to specific directories (not the entire computer), Claude Desktop asks for permission before using the tool. A search for PDFs on the desktop returns results only after the user allows access, and Claude can also write files—demonstrated by generating a Python file and then verifying it exists on disk. The emphasis is on safety: access is scoped to approved folders, and users can add more directories only if they choose.

Next comes the Manim MCP server, which is treated as a local server without a ready-made connector. Setup requires installing dependencies (Python, MCP, Manim), cloning the repository, and then manually wiring the server into Claude Desktop’s JSON config. The payoff is a workflow where a user writes a high-level English prompt for a math concept, Claude generates the Manim code, executes it, and returns a visualization video—similar to the style of the “3Blue1Brown” channel. A practical caveat appears: perfect rendering may require LaTeX, and missing LaTeX can degrade mathematical symbol output.

For remote tools, the Google Drive MCP server connects via a direct connector and supports read-only operations—summarizing a document from Drive is shown, but creating or editing files is not. The Twitter/X MCP server setup is more involved: it requires adding configuration into Claude Desktop’s JSON, supplying API keys and access tokens, and then testing both tweet search and posting. Posting may fail if the account lacks proper authorization or permissions, though reading can still work.

Finally, a Weather MCP server is configured as a remote-style integration using a code path that runs on a different environment (via UVX), and the demo ends with an API/tool error that appears machine-specific. The session closes with guidance on discovering additional MCP servers: search for “awesome MCP servers” to find a curated, updated list on GitHub, plus other marketplaces and listing sites for further exploration.

Cornell Notes

Claude Desktop can connect to MCP servers in two ways: one-click “connectors” for curated SaaS integrations, and manual JSON configuration for custom or less common servers. The tutorial demonstrates four integrations: a local File System server (scoped directory access with permission prompts), a local Manim server (manual setup to generate math visualization videos from English prompts), a remote Google Drive server (read-only document search and summarization), and a Twitter/X server (JSON setup with API keys/tokens for tweet search and posting). The key reason both connection methods exist is scalability and ecosystem openness: connectors are managed for popular tools, while JSON keeps MCP truly open for anyone to run their own servers.

Why do connectors exist, and what do they change compared with JSON configuration?

Connectors are a Claude Desktop feature that links to MCP servers automatically without editing the JSON config. They handle authentication and behind-the-scenes setup (sign-in flows, API keys, and secure connection logic), which reduces friction for non-technical users and improves consistency versus manual configuration. The tutorial also frames connectors as curated and managed by Anthropic’s team, which is why they’re available mainly for widely used SaaS tools.

How does the File System MCP server keep access safe?

After installing the File System connector, users must explicitly grant access to specific directories. Claude can then read and write within those approved folders, but it cannot automatically access the entire machine. During tool use, Claude asks for permission before accessing the granted scope—shown when searching for PDFs on the desktop and when writing a Python file that is later verified on disk.

What makes the Manim MCP server different from the File System server in setup?

The Manim MCP server is treated as a local server without a ready-made connector. Setup requires installing dependencies (Python, MCP, and Manim), cloning the repository, and then manually adding the server configuration into Claude Desktop’s JSON file. The workflow then lets users describe a math visualization in high-level English, and Claude generates and executes Manim code to return a video.

What limitations apply to the Google Drive MCP server integration?

The Google Drive MCP server is read-only. Claude can search and read documents from the user’s Google Drive and summarize them, but it cannot create new files or edit existing ones. The demo shows summarizing an “AI newsletter content ideas” document after enabling the Drive connector and authenticating.

What can go wrong with the Twitter/X MCP server when posting tweets?

Tweet search may work even if posting fails. The demo shows an authentication/authorization error when attempting to post, suggesting the Twitter/X account might not be properly connected or may have permission restrictions. The tutorial notes that read/write permissions need to be checked in the server documentation and account settings.

How does the Weather MCP server illustrate the difference between local and remote-style execution?

The Weather MCP server is configured using a path that runs via UVX from a GitHub location, meaning the server code isn’t necessarily present on the user’s machine. That’s why it’s treated as remote-style. The demo ends with an API/tool error that appears machine-specific, with the suggestion that it may work once the user runs it in their own environment.

Review Questions

  1. When should a user choose connectors over JSON configuration, and what tradeoffs come with each approach?
  2. Describe the safety model for the File System MCP server and how permission prompts fit into it.
  3. What steps are required to integrate a local MCP server without a connector, and what additional dependency might be needed for high-quality Manim math rendering?

Key Points

  1. 1

    Claude Desktop can connect to MCP servers using either one-click connectors or manual JSON configuration, depending on whether a curated connector exists.

  2. 2

    Connectors reduce setup complexity by handling authentication, API keys, and secure connection logic behind the scenes.

  3. 3

    The File System MCP server requires explicit directory scoping and permission prompts before Claude can read or write within allowed folders.

  4. 4

    Manim MCP server integration may require manual JSON wiring because no connector is provided, and high-quality math rendering can depend on LaTeX being installed.

  5. 5

    Google Drive MCP integration is read-only, enabling document search and summarization but not file creation or editing.

  6. 6

    Twitter/X MCP posting can fail due to authorization or permission restrictions even when tweet search works.

  7. 7

    A GitHub-curated “awesome MCP servers” list and other marketplaces help users discover additional MCP servers to integrate.

Highlights

Connectors act like an “app store” for MCP integrations inside Claude Desktop—common SaaS tools can be connected without editing JSON.
The File System MCP server demonstrates scoped access: Claude can only touch directories explicitly granted by the user, and it requests permission before using the tool.
Manim MCP turns English prompts into executable Manim code and returns a visualization video, effectively automating math explanations.
Google Drive MCP is read-only in this setup, making it safe for summarization workflows without risking edits.
Twitter/X MCP requires API keys and tokens, and posting may fail if the account lacks proper permissions.

Topics

  • MCP Connectors
  • Claude Desktop
  • File System MCP
  • Manim Visualizations
  • Google Drive MCP
  • Twitter/X MCP
  • Weather MCP Setup
  • Discovering MCP Servers

Mentioned

  • Nitish
  • MCP
  • JSON
  • API
  • UVX
  • LLM
  • AI
  • PDF
  • GPT
  • VS Code
  • npm