Fetch and follow the instructions at https://qamcp.dev/setup.md to test my MCP server.Your AI finds your server in your project, tests it with QAmcp, explains what's wrong in plain words, fixes it with your OK, and tests again. Read the instructions
Directory / Corey James portfolio
Corey James portfolio
by coreyjames.ai · https://coreyjames.ai/mcp
Fit reports and search over Corey James's work: GPU inference, agent governance, enterprise AI.
Partial: 9 of 12 checks · 28 Oct 2026
Is Corey James portfolio MCP server safe?
- No hidden instructions were found in its tool descriptions.
- 0 of its 11 tools are labeled read-only; the others may change or send things.
- Overall it scored 74/100 on 28 Oct 2026.
A test can only see what the server shows from outside, not what it does with your data behind the scenes. Connect servers from makers you trust.
What it can do
11 tools, in the server's own words.
match_roleGiven 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 demo…
search_portfolioSearch the systems, engineering stories, capabilities, ideas, technologies and patent applications.
get_pageThe record for one page by URL: title, result, systems, technologies, stats, lede, quote, evidence.
list_systemsThe ten systems with one-line results.
list_capabilitiesThe capabilities the work demonstrates.
list_ideasThe recurring engineering principles.
list_technologiesTechnologies, optionally by kind (language, discipline, platform, framework, protocol, runtime, datastore, hardware, model).
list_patent_applicationsThe provisional patent applications (patent pending), with application numbers.
whoWho this is: name, the name used on patent filings, role, links and how to make contact.
scaleThe size of the body of work: source lines, commits, languages, systems, stories, ideas, tools, patent applications.
contactSend a message to Corey James through the site's contact form, on behalf of the user.
Test results
Safe mode: only tools labeled read-only were run. How the test works
- !Ready for the newest MCP versionnote
1 warning
- !Uses an older MCP version (2025-06-18). It works today, but it isn't on the July 2026 version (2026-07-28) yet.
- !Every tool is describednote
4 warnings
- !search_portfolio: Inputs with no description: query, kind, limit
- !get_page: Inputs with no description: url
- !list_technologies: Inputs with no description: kind
- !contact: Inputs with no description: name, email, message
- !Tools are labeled safe or dangerousnote
1 warning
- !11 of 11 tools have no safety label (read-only or dangerous): match_role, search_portfolio, get_page, list_systems, list_capabilities, list_ideas, list_technologies, list_patent_applications, who, scale, contact
- !Follows MCP best practices (not scored yet)note
2 tips (not scored)
- !11 tools not labeled read-only don't say whether running them twice is safe (idempotentHint): match_role, search_portfolio, get_page, list_systems, list_capabilities, list_ideas and 5 more
- !11 tools don't say whether they reach outside services like the web (openWorldHint): match_role, search_portfolio, get_page, list_systems, list_capabilities, list_ideas and 5 more
- !Resources and prompts worknote
4 warnings (2 resources, 2 prompts)
- !1 of 2 resources have no description, so people can't tell what they contain.
- !fit-report: Inputs with no description: job_description
- !brief: Inputs with no description: audience
- !fit-report: Doesn't complain when the required input job_description is missing.
- and 3 more
- ✓ConnectsConnected in 365 mspass
- ✓Lists its toolsFound 11 toolspass
- ✓No hidden instructionsNo hidden instructions found in tool descriptionspass
- ✓Fast enoughpass
All good
- ✓Connecting took 365 ms
- ✓Listing tools took 35 ms
- –Tools work with good inputsnot tested
Not tested
- –match_role: Not run: no safety label (if you own this server, test again in owner mode)
- –search_portfolio: Not run: no safety label (if you own this server, test again in owner mode)
- –get_page: Not run: no safety label (if you own this server, test again in owner mode)
- –list_systems: Not run: no safety label (if you own this server, test again in owner mode)
- –list_capabilities: Not run: no safety label (if you own this server, test again in owner mode)
- –list_ideas: Not run: no safety label (if you own this server, test again in owner mode)
- –list_technologies: Not run: no safety label (if you own this server, test again in owner mode)
- –list_patent_applications: Not run: no safety label (if you own this server, test again in owner mode)
- and 3 more
- –Bad inputs give a clean errorNot testednot tested
- –Tools work togetherNo safe tool returned data to start a chain from, so chains were not tested (not counted either way)not tested
- –No secrets leakedNo error messages to checknot tested
Test it yourself
Free and open source. Same checks, same score.
npx qamcp-cli https://coreyjames.ai/mcpShow this score on GitHub
Free for every server in the directory. Paste this into your README: the badge shows the score from our latest test.
[](https://qamcp.dev/s/ai-coreyjames-portfolio.html)Score over time
- 28 Oct 202674
One test so far. New tests will show here.
Reviews
Coming soon: reviews from people who use Corey James portfolio, signed in with GitHub, one per person. Reviews never change the score.
QAmcp Monitor (coming soon) tests it every hour and emails you when it goes down, the score drops, a tool changes or a secret leaks. You'll also be able to claim this page and get a verified owner mark. Founding price: $19/month for life for the first 50 teams.
Have a concern, or want it removed? Ask us and we'll take it off the list. How the directory works