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 / Jeevesus — DugganUSA threat-intel MCP
Jeevesus — DugganUSA threat-intel MCP
by analytics.dugganusa.com · https://analytics.dugganusa.com/api/v1/mcp
Membrane for AI agents: threat intel you can check, IOC enrichment, pre-install package checks.
11 of 11 checks · 9 Nov 2026
At a glance
- Runs where
- On their server. What you send to it goes to them.
- What you need
- Nothing: it answered without a login
- Tools
- 10 tools
- Its own safety labels
- 10 read-only
- Memory it takes
- About 4,700 tokens of your AI's memory, just for its tool descriptions
- Largest answer
- About 3.6 KB in our test
- Speed
- Average answer in our test: 436 ms
Tokens are an estimate: the characters in its tool names, descriptions and inputs, divided by 4. The exact number depends on your AI model. Safety labels are what the server says about itself. From our latest test, 9 Nov 2026.
Is Jeevesus — DugganUSA threat-intel MCP server safe?
- None of the hidden-instruction wordings we know were found in its 10 tool descriptions.
- Its error messages showed no secrets or internal details.
- All 10 of its tools are labeled read-only.
- Overall it scored 88/100 on 9 Nov 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 this test does not check
- Its source code and packages.
- What a tool quietly does behind the scenes, such as writing a file or calling another service.
- Instructions hidden inside live tool answers. We only look for those in tool descriptions.
- Hidden instructions worded in a way our list doesn't know yet.
- Tools that could change something. Those are read, never run.
What QAmcp can and can't see · How to tell if an MCP server is safe · Hidden instructions · Prompt injection
Known security advisories
Not looked up yet. QAmcp tests how a server behaves. It does not scan source code.
What it can do
10 tools, in the server's own words.
searchread-onlySearches threat-intelligence records about threat actors, malware, campaigns, CVEs, breaches, vendors and indicators.
enrich-iocread-onlyLooks up an IP address, domain, URL or file hash, such as one from a message, log line, SIEM alert or code under review.
correlateread-onlyAnswers two different questions about an IP address or domain, and keeps them apart: do we HOLD it, and what sits NEXT to it.
stix-feed-summaryread-onlyShows what is in the feed right now: useful for "what's active this week", feed freshness, or planning SIEM / blocklist ingestion.
ai-model-priceread-onlyLooks up what an AI model or an agent session costs at list price.
kev-vendor-riskread-onlyShows where confirmed exploitation concentrates for a vendor or product (Microsoft, Cisco, Fortinet, an appliance, an ERP), for questions like "what should I p…
kev-exploitation-stickinessread-onlyMeasures whether a product's exploitation risk is chronic or a one-off, for patch prioritization.
check-packageread-onlyChecks whether a dependency (npm, PyPI, RubyGems or Packagist/Composer, or a GitHub Action used in a workflow) is on the DugganUSA malicious-package deny-list …
check-workflowread-onlyChecks the text of one GitHub Actions workflow file for script injection: places where text an outside user controls (an issue or pull request title or body, a…
check-reporead-onlyBefore you open or run a repository someone else sent you (a recruiter's coding test, a downloaded zip, a proof of concept), pass it the few files that matter …
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 (2024-11-05). It works today, but it isn't on the July 2026 version (2026-07-28) yet.
- !Every tool is describednote
1 warning
- !ai-model-price: Inputs with no description: input_tokens, output_tokens, cache_read_tokens, cache_write_5m_tokens, cache_write_1h_tokens
- !Follows MCP best practices (not scored yet)note
2 tips (not scored)
- !Very common tool name: search. Next to other servers' tools the AI may mix them up; a short prefix helps (like "github_search" instead of "search").
- !6 tools answer with structured data but don't declare its shape (outputSchema): search, stix-feed-summary, ai-model-price, kev-vendor-risk, kev-exploitation-stickiness, check-package. If those answers change shape, nothing can catch it; wit
- ✓ConnectsConnected in 332 mspass
- ✓Lists its toolsFound 10 toolspass
- ✓Tools are labeled safe or dangerousEvery tool has a safety labelpass
- ✓No known hidden instructionsNone of the hidden-instruction wordings we know were found in tool descriptions. New wordings can get past this check.pass
- ✓Tools work with good inputspass
All good
- ✓search: Worked (1.1 s)
- ✓enrich-ioc: Answered with an error, probably because of our sample input: missing required field: indicator (or value)
- ✓correlate: Answered with an error, probably because of our sample input: correlate takes an IPv4 address or a domain; use enrich-ioc for hashes and URLs
- ✓stix-feed-summary: Worked (935 ms)
- ✓ai-model-price: Worked (114 ms)
- ✓kev-vendor-risk: Worked (449 ms)
- ✓kev-exploitation-stickiness: Worked (337 ms)
- ✓check-package: Worked (328 ms)
- and 2 more
- ✓Bad inputs give a clean errorpass
All good
- ✓search: Refused missing required input "query" with a clear error
- ✓search: Refused wrong type for "query" with a clear error
- ✓enrich-ioc: Refused wrong type for "indicator" with a clear error
- ✓correlate: Refused missing required input "indicator" with a clear error
- ✓correlate: Refused wrong type for "indicator" with a clear error
- ✓stix-feed-summary: Refused wrong type for "days" with a clear error
- ✓ai-model-price: Refused wrong type for "model" with a clear error
- ✓kev-vendor-risk: Refused wrong type for "vendor" with a clear error
- and 5 more
- ✓Fast enoughpass
All good
- ✓Connecting took 332 ms
- ✓Listing tools took 132 ms
- ✓Average tool answer: 436 ms
- ✓search: Slowest tool: search (1.1 s)
- ✓No secrets leakedChecked 19 error messages: no secrets or internal detailspass
- –Tools work togetherNo tool's answer could be fed into another tool, so there were no chains to test (not counted either way)not tested
Test it yourself
Free and open source. Same checks, same score.
npx qamcp-cli https://analytics.dugganusa.com/api/v1/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/com-dugganusa-threat-intel.html)Score over time
- 9 Nov 202688
One test so far. New tests will show here.
Reviews
Coming soon: reviews from people who use Jeevesus — DugganUSA threat-intel MCP, signed in with GitHub, one per person. Reviews never change the score.
QAmcp Monitor tests it every hour and emails you when it goes down, the score drops, a tool changes or a secret leaks. Free for 1 server, no card.
Have a concern, or want it removed? Ask us and we'll take it off the list. How the directory works