MCP.Market

HenryKnows MCP server

online · 100% uptime
by henryknows.info·info.henryknows/henryknows·v2.3.0

F-1 and J-1 student immigration answers with citations to regulations and agency guidance.

B75/100grade B
What users say
No reviews yet
Be the first
Safety scan
B75/100

full report

Adoption
New

Little public usage data yet

Reviews

Write one

Nobody has reviewed HenryKnows yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

HenryKnows tools (4)

write = sends, deletes, buys or posts
  • ask_henryFree

    Ask HenryKnows a question about F-1/J-1 student immigration, SEVIS, OPT, CPT or related rules and get a cited answer. Ask in the person's own terms; do not add identifiers. Answers take 10–40 seconds. Read-only: nothing is stored.

  • connectFree

    Connect to the HenryKnows page the person is watching (its light turns green) and get the session for share_to_page. Only for people who gave you a session code or asked to follow along on a page. Side effects: creates a session, or links the one the person gave, and returns that session and the page's watch link; a new session starts each time it is called without a code; nothing is deleted.

  • search_sourcesFree

    Search HenryKnows' knowledge base (regulations, SEVP/USCIS guidance, Federal Register rules) and get the matching passages with their source links, so you can read and cite the text yourself. Fast; no model call. Read-only: nothing is stored.

  • share_to_pageFree

    Add a question and its HenryKnows answer (or a search and its passages) to the thread on the HenryKnows page the person connected, so they can see it there with its sources. Only for people who connected a page. Side effects: appends one entry to that page's thread, kept 24 hours; nothing else changes.

Public scan report

scanner v0.1.10 · 2026-11-03 · same rubric, same numbers if you re-run it

1 low
  • –Code scanremote-only server, no package to scann/a
  • Live reliabilityremote reachable in 1484ms20/20
  • Tool poisoning4 tool descriptions checked15/15
  • Auth qualityopen endpoint, read-only tools10/15
  • Maintenanceno repository listed3/15
  • Maintainer identityendpoint served from the registry-verified namespace domain8/10

Findings (1)

  • lowNo source repository listedmaint.no-repo
Overall 75/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How HenryKnows compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
75/100
higher than 45% of 48,255 servers
Tools
4
the typical server has 7
Tools that change things
0%
typical: 0%. Fewer write tools means less an agent can break
Uptime
100%
of our recent checks; the typical remote server answers 100%
Response time
2,539 ms
faster than 4% of 30,031 servers

What its tools let an agent do: 3 read · 1 send or post

Release history: 2 versions in the registry since 2026-09-23, latest 2026-10-24, typically one every 30 days.

Install HenryKnows in Claude Code, Cursor or VS Code

claude mcp add --transport http henryknows https://henryknows.info/mcp
Add to Cursor

Grade history

  • 2026-11-03restoreC → Bscore 75: No source repository listed

HenryKnows: common questions

Is HenryKnows MCP server safe?
Mostly: it is graded B (75/100). Read the HenryKnows safety report
How do I install HenryKnows?
It runs remotely at henryknows.info. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.
Does HenryKnows need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is HenryKnows maintained?
The latest release is v2.3.0.
Is HenryKnows up?
100% of our last 28 checks got an answer. We check remote servers about four times a day.
How does HenryKnows compare with other MCP servers?
safety score 75/100 (higher than 45% of 48,255 servers); tools 4 (the typical server has 7); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.