Skip to content
Corey James logo

Corey James MCP server

Which MCP servers are Corey James's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-29

← Back to Corey James

Whose server it is
  • Registry nameai.coreyjames/portfolioverified in the MCP registry

The registry name sits under coreyjames.ai. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-10-29
  • Stateanswerschecked 2026-10-29
  • Tools13
  • Server calls itselfcoreyjames-portfolio
  • Server version1.0.0
  • Protocol version2025-06-18

On 2026-10-29 the server answered initialize and tools/list without a sign-in. First answer in 254 ms.

Should an agent connect itSkip it
  • Its tools do none of the product's use cases we checked: orchestrate governed agents that run in sandboxes driven by events; broker LLM inference tokens across saturated runtimes; turn database limits into sized, admitted write paths.
  • Checked on 4 of the 7 days it takes to judge reliability.

Once connected

  • Parameters are untyped or undescribed in 6 of 13 tools: check arguments before calling.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

Measured dailydaily checks: 4, the first on 2026-10-29
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 4 so far
  • What an agent can do with it0 of 3 use cases
  • Answeredmeasuring4 of the 7 daily checks it takes to print a share
  • Median first answer306 ms
  • Space in an agent's context≈ 779 tokensthe definitions of all its tools (13), which an agent carries on every turn
  • Tool definitionsB · 76 of 100
  • Typed results0 of 13 toolsdeclared outputSchema: results come typed, read once
  • Parameters without a description: in 6 of 13
  • Not saying whether it only reads or can destroy: 13 of 13

What an agent can do with it

  • cannot · orchestrate governed agents that run in sandboxes driven by events
  • cannot · broker LLM inference tokens across saturated runtimes
  • cannot · turn database limits into sized, admitted write paths

Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?

Worth a look

None of the five warning signs in these definitions.

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

Tools it offers13 tools · read 2026-10-29
  • match_role

    Given a job description or a list of requirements, return an evidence-backed fit report: for each requirement, the pages and figures on coreyjames.ai that demonstrate it, plus the gaps. Cites, never asserts.

  • search_portfolio

    Search the systems, engineering stories, capabilities, ideas, technologies and patent applications. Returns ranked pages with their measured results and links.

  • get_page

    The record for one page by URL: title, result, systems, technologies, stats, lede, quote, evidence.

  • search

    Search the portfolio (connector-compatible): returns results with id, title and url. Use fetch with an id for the full document.

  • fetch

    Fetch one portfolio document by id (the page path from search): id, title, text (the page as Markdown), url, metadata.

  • list_systems

    The ten systems with one-line results.

  • list_capabilities

    The capabilities the work demonstrates.

  • list_ideas

    The recurring engineering principles.

  • list_technologies

    Technologies, optionally by kind (language, discipline, platform, framework, protocol, runtime, datastore, hardware, model).

  • list_patent_applications

    The provisional patent applications (patent pending), with application numbers.

  • who

    Who this is: name, the name used on patent filings, role, links and how to make contact.

  • scale

    The size of the body of work: source lines, commits, languages, systems, stories, ideas, tools, patent applications.

  • contact

    Send a message to Corey James through the site's contact form, on behalf of the user. Requires the user's own name and email.

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "portfolio": {
      "type": "http",
      "url": "https://coreyjames.ai/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http coreyjames https://coreyjames.ai/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://coreyjames.ai/mcp as a custom connector in the settings.

OpenAPI spec

13 paths, read 2026-10-29. Open the spec ↗

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.