splash image

March 10, 2025

Model Context Protocol (MCP)

MCP is a protocol for integrating AI applications with external data and other services. It was created by Anthropic as a way for Claude to access resources on the desktop.

MCP servers can be coded do almost anything, including network calls to other services. This has led to MCP being talked about as a foundation for building AI agents, even though its desktop-centric design is far from the Web protocols you might expect.

The following is a quick overview of MCP. For additional information, I recommend:

  1. This video by Mahesh
  2. The MCP user guide
  3. The MCP spec
  4. Reference MCP servers
  5. Swyx's spicy take

MCP slide from the AI engineering summit https://www.youtube.com/watch?v=kQmXtrmQ5Zg

How it works

To make a tool call, the MCP client exchanges JSON-RPC messages with the MCP server.

A desktop client will spawn servers as subprocesses so that it can communicate with them over stdio.

Besides tool calls, the protocol also supports:

There are debugging tools and SDKs for Python, Typescript, Java, and Kotlin.

Why are people excited?

Talking to your own tools feels like magic.

Screenshot of chat with Claude to inspect the local filesystem

Here is another example from Cloudflare.

Gotcha

The way Claude Desktop spawns servers in subprocesses has resulted in a few pitfalls. I ran into this myself after configuring the filesystem server as described in the quickstart.

Screenshot of Claude errors

The error stems from differences in the PATH when Claude Desktop spawns server subprocesses. One fix is to use absolute paths in ~/Library/Application Support/Claude/claude_desktop_config.json on MacOS. E.g.

{
  "mcpServers": {
    "filesystem": {
      "command": "/Users/jldec/n/bin/node",
      "args": [
        "/Users/jldec/mcp/servers/src/filesystem/dist/index.js",
        "/Users/jldec/mcp/claude"
      ]
    }
  }
}

What's next?

The buzz is real, but it's early days and AI agent platforms are just getting started.

🚀

debug

user: anonymous

{
  "path": "/blog/mcp",
  "attrs": {
    "date": "2025-03-10",
    "title": "Model Context Protocol (MCP)",
    "layout": "BlogPostLayout",
    "splash": {
      "image": "/images/courthouse.webp"
    }
  },
  "md": "# Model Context Protocol (MCP)\n\nMCP is a protocol for integrating AI applications with external data and other services. It was created by Anthropic as a way for Claude to access resources on the desktop.\n\nMCP servers can be coded do almost anything, including network calls to other services. This has led to MCP being talked about as a foundation for building AI agents, even though its desktop-centric design is far from the Web protocols you might expect.\n\nThe following is a quick overview of MCP. For additional information, I recommend:\n\n1. [This video](https://www.youtube.com/watch?v=kQmXtrmQ5Zg) by [Mahesh](https://x.com/maheshmurag)\n2. The [MCP user guide](https://modelcontextprotocol.io)\n3. The [MCP spec](https://spec.modelcontextprotocol.io/specification//2024-11-05/)\n4. Reference [MCP servers](https://github.com/modelcontextprotocol/servers)\n4. Swyx's [spicy take](https://www.latent.space/p/why-mcp-won)\n\n![MCP slide from the AI engineering summit https://www.youtube.com/watch?v=kQmXtrmQ5Zg](/images/mcp.webp)\n\n### How it works\n\nTo make a tool call, the [MCP client](https://modelcontextprotocol.io/clients) exchanges JSON-RPC messages with the [MCP server](https://modelcontextprotocol.io/examples).\n\nA desktop client will spawn servers as subprocesses so that it can communicate with them over [stdio](https://spec.modelcontextprotocol.io/specification/2024-11-05/basic/transports/#stdio).\n\nBesides [tool calls](https://spec.modelcontextprotocol.io/specification/2024-11-05/server/tools/), the protocol also supports:\n\n- Server-to-client [notifications](https://spec.modelcontextprotocol.io/specification/2024-11-05/basic/messages/#notifications)\n- URL-based [resources](https://spec.modelcontextprotocol.io/specification/2024-11-05/server/resources/) with subscriptions for change notifications\n- [Prompts](https://spec.modelcontextprotocol.io/specification/2024-11-05/server/prompts/)\n- Nested LLM calls or [sampling](https://spec.modelcontextprotocol.io/specification/2024-11-05/client/sampling/)\n\nThere are [debugging](https://modelcontextprotocol.io/docs/tools/debugging) tools and [SDKs](https://modelcontextprotocol.io/sdk) for Python, Typescript, Java, and Kotlin.\n\n### Why are people excited?\n\nTalking to your own tools feels like magic.\n\n![Screenshot of chat with Claude to inspect the local filesystem](/images/claude-magic.webp)\n\n[Here](https://www.youtube.com/watch?v=vGajZpl_9yA) is another example from Cloudflare.\n\n<iframe width=\"560\" height=\"315\" src=\"https://www.youtube.com/embed/vGajZpl_9yA?start=61\" title=\"YouTube video player\" frameborder=\"0\" allow=\"accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share\" referrerpolicy=\"strict-origin-when-cross-origin\" allowfullscreen></iframe>\n\n### Gotcha\n\nThe way Claude Desktop spawns servers in subprocesses has resulted in a few [pitfalls](https://github.com/modelcontextprotocol/servers/issues/436#issuecomment-2564638983). I ran into this myself after configuring the filesystem server as described in the [quickstart](https://modelcontextprotocol.io/quickstart/user#2-add-the-filesystem-mcp-server).\n\n![Screenshot of Claude errors](/images/claude-errors.webp)\n\nThe error stems from differences in the PATH when Claude Desktop spawns server subprocesses. One fix is to use absolute paths in `~/Library/Application Support/Claude/claude_desktop_config.json` on MacOS. E.g.\n\n```json\n{\n  \"mcpServers\": {\n    \"filesystem\": {\n      \"command\": \"/Users/jldec/n/bin/node\",\n      \"args\": [\n        \"/Users/jldec/mcp/servers/src/filesystem/dist/index.js\",\n        \"/Users/jldec/mcp/claude\"\n      ]\n    }\n  }\n}\n```\n\n### What's next?\nThe buzz is real, but it's early days and AI agent platforms are just getting started.\n\n- I'm optimistic for [HTTP](https://spec.modelcontextprotocol.io/specification/2024-11-05/basic/transports/#http-with-sse) to supplant stdio, especially with the [recent announcement](https://youtu.be/kQmXtrmQ5Zg?t=4409) of remote servers with auth.\n\n  This is particularly important for scaling agents on the network and supporting multiple clients per server.\n\n  _Update:_ See this [RFC](https://github.com/modelcontextprotocol/specification/pull/206) and [discussion](https://github.com/modelcontextprotocol/specification/discussions/102) for connectionless improvements to the HTTP transport. 🎉\n\n- A [registry](https://youtu.be/kQmXtrmQ5Zg?t=4920) should accelerate the network effects of MCP, making servers and their capabilities more discoverable e.g. by other agents.\n\n- [.well-known/mcp.json](https://youtu.be/kQmXtrmQ5Zg?t=5958) provides a way for agents to find AI interfaces on websites without the need for a central registry.\n\n- [Stateless requests, streaming, and namespacing](https://youtu.be/kQmXtrmQ5Zg?t=6095) - all good things adopted from Web protocols.\n\n## 🚀",
  "html": "<h1>Model Context Protocol (MCP)</h1>\n<p>MCP is a protocol for integrating AI applications with external data and other services. It was created by Anthropic as a way for Claude to access resources on the desktop.</p>\n<p>MCP servers can be coded do almost anything, including network calls to other services. This has led to MCP being talked about as a foundation for building AI agents, even though its desktop-centric design is far from the Web protocols you might expect.</p>\n<p>The following is a quick overview of MCP. For additional information, I recommend:</p>\n<ol>\n<li><a href=\"https://www.youtube.com/watch?v=kQmXtrmQ5Zg\">This video</a> by <a href=\"https://x.com/maheshmurag\">Mahesh</a></li>\n<li>The <a href=\"https://modelcontextprotocol.io\">MCP user guide</a></li>\n<li>The <a href=\"https://spec.modelcontextprotocol.io/specification//2024-11-05/\">MCP spec</a></li>\n<li>Reference <a href=\"https://github.com/modelcontextprotocol/servers\">MCP servers</a></li>\n<li>Swyx's <a href=\"https://www.latent.space/p/why-mcp-won\">spicy take</a></li>\n</ol>\n<p><img src=\"/images/mcp.webp\" alt=\"MCP slide from the AI engineering summit https://www.youtube.com/watch?v=kQmXtrmQ5Zg\"></p>\n<h3>How it works</h3>\n<p>To make a tool call, the <a href=\"https://modelcontextprotocol.io/clients\">MCP client</a> exchanges JSON-RPC messages with the <a href=\"https://modelcontextprotocol.io/examples\">MCP server</a>.</p>\n<p>A desktop client will spawn servers as subprocesses so that it can communicate with them over <a href=\"https://spec.modelcontextprotocol.io/specification/2024-11-05/basic/transports/#stdio\">stdio</a>.</p>\n<p>Besides <a href=\"https://spec.modelcontextprotocol.io/specification/2024-11-05/server/tools/\">tool calls</a>, the protocol also supports:</p>\n<ul>\n<li>Server-to-client <a href=\"https://spec.modelcontextprotocol.io/specification/2024-11-05/basic/messages/#notifications\">notifications</a></li>\n<li>URL-based <a href=\"https://spec.modelcontextprotocol.io/specification/2024-11-05/server/resources/\">resources</a> with subscriptions for change notifications</li>\n<li><a href=\"https://spec.modelcontextprotocol.io/specification/2024-11-05/server/prompts/\">Prompts</a></li>\n<li>Nested LLM calls or <a href=\"https://spec.modelcontextprotocol.io/specification/2024-11-05/client/sampling/\">sampling</a></li>\n</ul>\n<p>There are <a href=\"https://modelcontextprotocol.io/docs/tools/debugging\">debugging</a> tools and <a href=\"https://modelcontextprotocol.io/sdk\">SDKs</a> for Python, Typescript, Java, and Kotlin.</p>\n<h3>Why are people excited?</h3>\n<p>Talking to your own tools feels like magic.</p>\n<p><img src=\"/images/claude-magic.webp\" alt=\"Screenshot of chat with Claude to inspect the local filesystem\"></p>\n<p><a href=\"https://www.youtube.com/watch?v=vGajZpl_9yA\">Here</a> is another example from Cloudflare.</p>\n<iframe width=\"560\" height=\"315\" src=\"https://www.youtube.com/embed/vGajZpl_9yA?start=61\" title=\"YouTube video player\" frameborder=\"0\" allow=\"accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share\" referrerpolicy=\"strict-origin-when-cross-origin\" allowfullscreen></iframe>\n<h3>Gotcha</h3>\n<p>The way Claude Desktop spawns servers in subprocesses has resulted in a few <a href=\"https://github.com/modelcontextprotocol/servers/issues/436#issuecomment-2564638983\">pitfalls</a>. I ran into this myself after configuring the filesystem server as described in the <a href=\"https://modelcontextprotocol.io/quickstart/user#2-add-the-filesystem-mcp-server\">quickstart</a>.</p>\n<p><img src=\"/images/claude-errors.webp\" alt=\"Screenshot of Claude errors\"></p>\n<p>The error stems from differences in the PATH when Claude Desktop spawns server subprocesses. One fix is to use absolute paths in <code>~/Library/Application Support/Claude/claude_desktop_config.json</code> on MacOS. E.g.</p>\n<pre><code class=\"language-json\">{\n  &quot;mcpServers&quot;: {\n    &quot;filesystem&quot;: {\n      &quot;command&quot;: &quot;/Users/jldec/n/bin/node&quot;,\n      &quot;args&quot;: [\n        &quot;/Users/jldec/mcp/servers/src/filesystem/dist/index.js&quot;,\n        &quot;/Users/jldec/mcp/claude&quot;\n      ]\n    }\n  }\n}\n</code></pre>\n<h3>What's next?</h3>\n<p>The buzz is real, but it's early days and AI agent platforms are just getting started.</p>\n<ul>\n<li>\n<p>I'm optimistic for <a href=\"https://spec.modelcontextprotocol.io/specification/2024-11-05/basic/transports/#http-with-sse\">HTTP</a> to supplant stdio, especially with the <a href=\"https://youtu.be/kQmXtrmQ5Zg?t=4409\">recent announcement</a> of remote servers with auth.</p>\n<p>This is particularly important for scaling agents on the network and supporting multiple clients per server.</p>\n<p><em>Update:</em> See this <a href=\"https://github.com/modelcontextprotocol/specification/pull/206\">RFC</a> and <a href=\"https://github.com/modelcontextprotocol/specification/discussions/102\">discussion</a> for connectionless improvements to the HTTP transport. 🎉</p>\n</li>\n<li>\n<p>A <a href=\"https://youtu.be/kQmXtrmQ5Zg?t=4920\">registry</a> should accelerate the network effects of MCP, making servers and their capabilities more discoverable e.g. by other agents.</p>\n</li>\n<li>\n<p><a href=\"https://youtu.be/kQmXtrmQ5Zg?t=5958\">.well-known/mcp.json</a> provides a way for agents to find AI interfaces on websites without the need for a central registry.</p>\n</li>\n<li>\n<p><a href=\"https://youtu.be/kQmXtrmQ5Zg?t=6095\">Stateless requests, streaming, and namespacing</a> - all good things adopted from Web protocols.</p>\n</li>\n</ul>\n<h2>🚀</h2>\n"
}