General Tools

jasonlovell.ai

Provides tools to retrieve Jason Lovell's profile, research studies, and public builds, including summaries and detailed records.

1 endpoint8 known toolsFirst detected September 29, 2026Last detected September 29, 2026

ENDPOINT 1

https://jasonlovell.ai/mcp

No auth detected

MCP server metadata

Name: jasonlovell.ai
Version: 1.0.0

Capabilities

tools.listChanged

Server instructions

Jason Lovell's site: frontier AI research, solution design and engineering. Start with get_profile or list_studies. Every tool is read-only. An open-book exam on the site, scored against people, has its own MCP server at https://jasonlovell.ai/exam/mcp. Each page also has a Markdown twin (https://jasonlovell.ai/work/<slug>.md); the whole site is at https://jasonlovell.ai/llms-full.txt. The tool definitions are signed: check them against the TBOM at https://jasonlovell.ai/tbom.json (keys at https://jasonlovell.ai/.well-known/tbom-keys.json).

Known tools 8

get_profile

Who Jason Lovell is: day role, career from mobile through Samsung, Captivate and PwC, how he builds, what he cares about now, and how to reach him.

Inferred read-only

list_studies

The ten research studies: each one's question, kind of result, a short outcome, date and page.

Inferred read-only

get_study

One study in full: the question, the result, the design decision, what was recorded, the evidence links and where the evidence stops.

Inferred read-only

list_builds

Public repositories by area, newest first.

Inferred read-only

get_build

One build: what it is and includes, and for builds with a design record, the question it answers, the design choice and where it stops.

Inferred read-only

list_releases

Specifications, a white paper and research software, with DOIs where they have them.

Inferred read-only

search_site

Find studies, builds and releases by keyword.

Inferred read-only

contact_routes

Ways to reach Jason, by purpose.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.jasonlovell-ai]
url = "https://jasonlovell.ai/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "jasonlovell-ai": {
      "type": "http",
      "url": "https://jasonlovell.ai/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: jasonlovell-ai
Remote MCP URL: https://jasonlovell.ai/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "jasonlovell-ai": {
      "url": "https://jasonlovell.ai/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "jasonlovell-ai": {
      "type": "http",
      "url": "https://jasonlovell.ai/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "jasonlovell-ai",
  "transport": "streamable-http",
  "url": "https://jasonlovell.ai/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Loading Trust v2 evidence…

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.