Jake Gaylor · Teach your AI about me

What your assistant can do here

Connect once, then ask in plain English. The server exposes tools for the whole evaluation — from first look to first contact.

Assess my fit

Paste your job description and get an honest read on where I'm strong and where I'm not, scored against my real experience.

“Is Jake a good fit for this role? [paste job description]”

Build the interview

Generate phone screens, technical deep-dives, system design sessions, or behavioral questions tailored to my background and your focus areas.

“Create a phone screen for Jake focused on Kubernetes and API design.”

Pull the source material

My resume, GitHub, LinkedIn, and website content, served as structured resources your assistant reads directly — always current.

“Summarize Jake's career highlights.”

Reach out

Looks like a match? Your assistant can email me directly from the conversation — you review it, the server sends it.

“Draft and send Jake an email about our staff platform engineer role.”

Connect in under a minute

The server is already hosted and running — nothing to install. Add the endpoint to any MCP-capable client, or use the npm package for clients that only speak stdio.

Streamable HTTP

Recommended

https://ai.jakegaylor.com/mcp

SSE

Legacy clients

https://ai.jakegaylor.com/sse

Client setup

Pick your client. Clients without remote MCP support can run the same server locally via the @jhgaylor/me-mcp npm package.

Add this configuration to your Claude config

{
  "mcpServers": {
    "jake-gaylor-mcp": {
      "command": "npx",
      "args": ["-y", "@jhgaylor/me-mcp"]
    }
  }
}

Add this configuration to your Cursor settings

{
  "mcpServers": {
    "jake-gaylor-mcp": {
      "command": "npx",
      "args": ["-y", "@jhgaylor/me-mcp"]
    }
  }
}

Configure Windsurf to connect

{
  "mcpServers": {
    "jake-gaylor-mcp": {
      "command": "npx",
      "args": ["-y", "@jhgaylor/me-mcp"]
    }
  }
}

Set up Zed MCP server configuration

{
  "context_servers": {
    "jake-gaylor-mcp": {
      "settings": {},
      "command": {
        "path": "npx",
        "args": ["-y", "@jhgaylor/me-mcp"]
      }
    }
  }
}

For clients that support direct HTTP connections:

Connect to: https://ai.jakegaylor.com/mcp
Use standard MCP protocol methods to interact with the server
No local installation required — the server is already hosted and ready to use

Example TypeScript connection code

import { Client } from "@modelcontextprotocol/sdk/client/index.js";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp.js";

async function connectToMCP() {
  const baseUrl = new URL("https://ai.jakegaylor.com/mcp");

  try {
    const client = new Client({ name: 'example-mcp-client', version: '1.0.0' });
    const transport = new StreamableHTTPClientTransport(baseUrl);
    await client.connect(transport);
    console.log("Connected to MCP server!");
    const resumeResource = await client.getResource("candidate-info://resume-text");
    console.log("Resume:", resumeResource.contents[0].text);
    const githubUrl = await client.callTool({ toolName: "get_github_url", args: {} });
    console.log("GitHub URL:", githubUrl.content[0].text);
  } catch (error) {
    console.error("Failed to connect to MCP server:", error);
  }
}
connectToMCP();

No MCP client? Copy this instead

Paste the text below into any AI assistant to give it my full background — no tools or special connections needed. Also available at ai.jakegaylor.com/llms.txt.

Error fetching remote content from https://jakegaylor.com/resume.json

Under the hood

This site speaks the Model Context Protocol — the open standard that lets AI assistants call external tools and read external data. Anything that speaks MCP can use it. The server itself is open source: @jhgaylor/candidate-mcp-server.

Tools — actions your assistant can take

assess_role_fit

Assesses my fit for a specific role from a job title, full job description, and key requirements.

generate_interview_questions

Generates tailored questions by interview type — phone screen, technical, behavioral, system design, or culture fit — focused on the areas you choose.

contact_candidate

Sends me an email with your subject, message, and reply address. Your assistant drafts it, you review it, the server delivers it.

get_resume_text / get_resume_url

Returns my resume as plain text, or a URL to the hosted copy: https://jakegaylor.com/resume/.

get_github_url / get_linkedin_url / get_website_url

Return my profile links:

get_website_text

Returns the content of my personal website as text, for assistants that can't browse.

Resources & prompts — data it can read

candidate-info://resume-text

Error fetching remote content from https://jakegaylor.com/resume.json

candidate-info://website-text

Senior · Staff · Engineering Leadership I make good teams ship like great ones. Good teams rarely lack talent. They lack speed, focus, and the visibility to see what’s working. That’s the gap I close, fast. View Resume Email Me Text Me What changed after I showed up The real outcomes teams measured after I joined. 30x faster deploys “Jake is a force for good unlike any other. He migrated our infra to a cheaper and more scalable system, crafted a CI pipeline that accelerated deploys by 30x, and taught the whole company how to make data-driven decisions by building an entire product analytics stack. And that was just his first 6 months.” Aaron Biller, Director of Platform Engineering, Cloaked 3 days to org-wide adoption “I watched Jake redo a build and deploy process over the span of 3 days, whip up a presentation, and get every engineer in the org up to speed using it, a moment I’ll never forget because our productivity EXPLODED afterwards.” Stephen Bapple, Software Engineer, CyberGRX Acquired by Verizon, petabyte scale Protectwise’s product teams never had to ask whether the backing systems would hold. I built the infrastructure ahead of their scale and kept it boring: thousands of Cassandra nodes, petabytes in S3, $10M+/yr of production AWS. My role: Senior DevOps Engineer, Protectwise “We were deploying C# on vSphere when Jake joined our first Node.js team. He brought Docker, we moved to Kubernetes, and our services had the fastest release cycle in the company.” Architect, Food Service Warehouse “Everyone else told us how to work around problems. Jake built us better tools.” Operator, Magic Whatever you’re short on, I’ve shipped it My core is delivery: making teams ship fast and see what’s working. 15+ years across many related disciplines have made me fluent in most and genuinely deep in a few. SaaS & AI Products Spent my career building SaaS, lately deep in AI: LangChain agents at Cloaked, the framework behind Block Party’s internal coding bots, Ravi, an agent-native SaaS for secret management, and Fountain, the control plane that runs my own fleet of sandboxed coding agents. SRE & DevOps Ran SRE on petabyte-scale systems at Protectwise, through dozens of production deploys a day, and across multiple lines of business. Off the clock, same discipline: a GitOps-run k3s cluster serves production from my house. IoT & Firmware Designed custom air-quality sensor PCBs, wrote their firmware, and built the SaaS that drives it all to a target climate. Deployed across a controlled-environment agriculture facility: 100 control units and 200+ sensors. Business Ownership Ran a full-service steakhouse outright: hired and led the team, drove $500K in annual revenue, and owned the vendors, the costs, and the margin. Now I build software with the business math in mind. My first 90 days on your team Anyone can claim they can build. Here’s what I actually do in the first three months, with a receipt behind every move. 1 Make delivery easy I find the slow, error-prone parts of shipping and rebuild them into tools the whole team actually uses, even as AI floods the pipeline with PRs. Receipt CyberGRX went from quarterly manual deploys to shipping on demand. At Food Service Warehouse, teams on my infrastructure ran the company’s fastest release cycle. 2 Bring visibility to the team’s work I get real metrics in place so decisions stop being guesses and everyone can see what’s actually working. Receipt Built the product-analytics stack at Cloaked that taught the company to make data-driven calls. Then an ideation portal, so design, product, engineering, and the executives shared one transparent view of the work in flight. 3 Ship the small first version, instrumented I put an embarrassingly small v1 in front of real users with tracking from day one, then let how they use it decide what’s next. Receipt Ravi, the agent-native SaaS I founded, started as an embarrassingly small instrumented v1, and its real usage data is what won its funding. Fountain, my agent control plane, was largely built using itself. Hiring for a senior, staff, or leadership role? If your team needs someone who can lift the whole team and build at every layer, let’s talk. View Resume Email Me Text Me Or browse my projects & ventures, or tour the homelab. Screening with an AI assistant? Point it at ai.jakegaylor.com. © 2026 Jake Gaylor. All rights reserved. This page now lives at jakegaylor.com.

candidate-info://*-url

Resume, LinkedIn, GitHub, and website URLs, exposed as individual resources (resume-url, linkedin-url, github-url, website-url).

Built-in prompts

Ready-made starting points your MCP client can surface directly: evaluate_job_fit, generate_phone_screen, get_candidate_background, summarize_career_highlights, assess_tech_proficiency, assess_product_collaboration, and assess_startup_fit.

Let your assistant run the first screen.

Connect it, paste your job description, and find out in minutes whether we should talk. If the answer is yes — it knows how to reach me.

Email Me View Resume jakegaylor.com