Learn Shell (sf-shenfeng/learn-shell) is an MCP server listed on the M8ven Trust Index. It scores 50 out of 100, grade D. It declares 50 tools. No publisher has claimed this listing.

Back to MCP Trust IndexM8ven
D
Caution
50/100

Learn Shell

An agent-native teaching OS that gives AI assistants a persistent classroom with courses, lessons, flashcards, and graded exercises via MCP tools.

→ sf-shenfeng/learn-shell· listed on glama

Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

Code Verified⚡ Live Monitored: not connected

Verified is a snapshot. Live keeps it current, and builds your track record.

⚡ Connect GitHub → continuous verification on every pushwhy connect →

Who stands behind it

sf-shenfeng

Source: Glama

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →

⚡ Connect GitHub for Live Monitored

Install from

Glamanot scored here

The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.

// key findings
⚠️
Known vulnerabilities in dependencies: 8 high
Affects packages this MCP installs at runtime. Upgrade or remove the affected dependency.
✅
No credential exfiltration, no sensitive file access, no obfuscation
Static analysis found nothing flowing your secrets to unexpected places.
// tools this server exposes50 tools

These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.

create_pair
propose_contract
update_contract_cadence
void_contract
update_contract_coverage
complete_contract
create_course
add_lesson
update_lesson
add_lesson_patch
close_lesson_loop
get_lesson_closure_state
publish_lesson
add_document
update_document
add_concept
update_concept

修订已有 concept 的字段 (name / short_definition / source_refs / flashcard_ids).

add_flashcard

添加一张闪卡; FSRS state 由 server 初始化.

update_flashcard
add_mindmap_seed
update_mindmap_seed
add_exercise

为 lesson 添加课后习题.

add_simulated_quiz
verify_prep
grade_exercise
record_post_lesson_evaluation
record_live_evaluation
record_learner_hypothesis
reflect_on_teaching
record_learner_feedback
update_feedback_status
get_context
get_learner_brief
get_teacher_inbox
get_lesson
get_exercise
get_submission
live_pending
live_heartbeat

Agent 端 keep-alive. 在 ttl_seconds 内 bridge 算 online. ⚠️ ttl_seconds 是在线判定窗口, NOT 轮询间隔. 值更契约 v3: 等待不烧模型回合(红线: 禁止模型层轮询), 用看门脚本/live_wait/你家自己的监听机制均可, 见 recipe://live-teaching. 看门脚本会替你打心跳; 走 live_wait 的, 它自带 auto-heartbeat. 回应契约(单层 v3): 实质回答质量优先, 不设硬秒数, 在场感由在线灯负责不由报文. (旧 context_status 参数已退役——上下文余量指示灯已…

live_wait
live_session_get

读 LiveSession 全貌 (session + 全部 moves + 全部 responses). 决定下一步前必读.

live_message_send

追加一条 Teaching Move (Live Teaching 结构化教学). 会话第一条 move (seq=1) 必须 move_type="FRAME"——否则结构化拒绝, 不接受其他类型开场. FRAME content 须覆盖三要素: 本场做什么/多久/怎么算完. ASK/PROBE/CHALLENGE 必须 response_kind="text". REFLECT 必须 "none". content 控制在 300 中文字以内 (EXPLAIN). 一个 move 只做一件事. 自由对话/答疑请用 adhoc_message_send.

live_snapshot_write

在 Live Teaching session 中段 flush 一个 rolling checkpoint. 建议每 3 轮写一次. compact 后用 live_snapshot_get_latest 拿回来, 不用重读全部 moves.

live_snapshot_get_latest

读 session 最近一份 mid-lesson snapshot. compact 恢复时第一步: snapshot + 之后的 moves = 续上 session 的最小集.

adhoc_thread_get
adhoc_ack
adhoc_message_send

Agent 在 AdHoc thread 里回应用户. 自由对话不限 move_type. 富内容用 payload (component_type: interactive_html | whiteboard_svg | tts_audio + body). 学习相关写 is_learning_related=true 会落 SessionEvent.

live_session_complete
live_session_cancel

中止 session (learner 提前结束或 system 超时). idempotent.

live_session_start
// known CVEs in dependencies8 high22 low

Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.

high@hono/node-server@1.13.0GHSA-wc8c-qw6v-h7f6

@hono/node-server has authorization bypass for protected static paths via encoded slashes in Serve Static Middleware

high@modelcontextprotocol/sdk@1.0.0GHSA-w48q-cv73-mx4w

Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default

highdrizzle-orm@0.36.0GHSA-gpj5-g38j-94v9

Drizzle ORM has SQL injection via improperly escaped SQL identifiers

highhono@4.6.0GHSA-3vhc-576x-3qv4

Hono JWK Auth Middleware has JWT algorithm confusion when JWK lacks "alg" (untrusted header.alg fallback)

highhono@4.6.0GHSA-88fw-hqm2-52qc

hono: CORS Middleware reflects any Origin with credentials when `origin` defaults to the wildcard

Depend on this server? Get alerted when its CVEs change.Watch this server free →
// environment variables
To run this server yourself, you supply these values. They go in your own MCP client configuration and stay on your machine. The secret label means the value is sensitive, not that the server mishandles it.
configALLOW_NON_BENCH_DB
configCORS_ORIGINS
configE2E_ADMIN_DB
configE2E_DB_NAME
configE2E_DB_URL_BASE
configHOST
configLEARNER_APP_BASE_URL
configLS_AGENT_NAME
configLS_GRAVEYARD_DIR
configLS_INSPECT
configLS_LEARNER_NAME
configLS_LOCALE
configLS_SIMULATE
configLS_TIMEZONE
configRUN_DB_TESTS
configSSH_REMOTE_DIR
configSSH_TARGET
Deployment configuration, supplied by whoever hosts the server. Users are not asked for these.
deployDATABASE_URL
deployPORT
// quality suggestions

Tool annotations

No tools have read-only/destructive annotations

Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.

All four hints declared on every tool

50/50 tools missing one or more hints — create_pair (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); propose_contract (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); update_contract_cadence (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +47 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.

For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.

README present

No README found

Add a README.md describing the server and its tools.

License file

No license file

Add a LICENSE file (MIT, Apache-2.0, etc.).

Tool test coverage

19/50 tools referenced in tests (38%)

Write tests that reference each tool by name so every tool has at least one test.

Shell command execution

3 child_process calls — runs shell commands

Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.

Production dependencies are patched

0 critical, 8 high severity in production deps — @hono/node-server@1.13.0 (high), @modelcontextprotocol/sdk@1.0.0 (high)

Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.

Domain consistency

npm scope @learn-shell doesn't match GitHub owner sf-shenfeng

Use the same org name across GitHub, npm, and your homepage so users can verify the publisher.

Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.

// full audit trail
The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.
// improvement guidance — verified publishers only
We have 8 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.
// embed badge in your README
[![M8ven Verified](https://m8ven.ai/badge/mcp/sf-shenfeng/learn-shell?variant=verified)](https://m8ven.ai/mcp/sf-shenfeng/learn-shell)
Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.
commit: 080300481b2d68521408460a0ea8a18793d3b66a
code hash: f833c639d9245dae4c1f7c04e2564db5d503277a407f7288f28834f43e5910e7
view raw JSON →
Check MCPs from inside your assistant
Tool Check · MCP

Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.

https://m8ven.ai/api/mcp/tool-check
check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern
How to add it →Free · no account needed · works in any MCP client