MisakaNet
mcp-name: io.github.Ikalus1988/misakanet
에이전트 강화
게시자의 자체 URL입니다. PlugMCP 엔드포인트가 아닙니다.
Host a copy with our keys and logs.
https://misakanet.org/mcp위의 Claude 버튼을 누르면 이름과 URL이 채워진 상태로 Claude가 열립니다. 확인은 Claude에서 직접 해야 합니다.
claude mcp add --transport http io.github.ikalus1988-misakanet https://misakanet.org/mcpRun in a terminal.
{ "mcpServers": { "io.github.ikalus1988-misakanet": { "command": "npx", "args": [ "-y", "mcp-remote", "https://misakanet.org/mcp" ] } }}claude_desktop_config.json
원격 URL인가요, 내 컴퓨터에서 실행하는 명령인가요? 두 설치 방식의 차이
PlugMCP에서 실행
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
실행A pip install times out behind a corporate proxy. An agent finds the fix. Days later the same
timeout appears on another machine, under another model — and is debugged from scratch, because the
fix was never written down anywhere the next agent looks.
MisakaNet is that place: a git-backed failure memory. Every lesson is a Markdown file in this repository — graded by evidence, reviewed like code, retrieved by an agent instead of guessed at. You fail once; the next agent does not.
llms.txt,
A2A discovery via .well-known/agent-card.json.The point of an install is a first successful search, not the install. None of these needs an account or a token.
The installer-managed row is what npx @misaka-net/misakanet-setup writes into each host's config.
Updates: dsh plugin --profile web update misakanet@latest.
Installer updates: npx @misaka-net/misakanet-setup@latest.
Full prerequisites and the two-package trap: How to use it.
1. Ask it something you have actually broken. No client installed? This curl is the whole interface:
curl -sS https://misakanet.org/mcp \
-H 'Content-Type: application/json' -H 'Accept: application/json' \
-H 'MCP-Protocol-Version: 2025-06-18' -H 'Origin: https://misakanet.org' \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/call",
"params":{"name":"misakanet_search","arguments":{"query":"database is locked","top":3}}}'
2. Read what came back. A hit returns the lesson, its evidence_level, and its path — open the
file and read the fix before running any command in it. A miss returns no_match plus a ready-to-call
intake: the corpus saying it does not know this one yet.
3. Check the trust signal, not the tone. E0–E3 say how far a lesson was verified; E4 is the
one nobody can write or vote into.
Git-backed failure memory for AI coding agents. An error shows up → the agent searches → it applies a fix somebody already verified → if nothing matches, the miss becomes an intake, and the intake becomes a lesson for the next agent.
Every lesson is a Markdown file: reviewed like code, graded by evidence, retrieved with BM25 over the Python standard library. No vector database, no embedding model, no server unless you want one.
MisakaNet answers for the failures it has indexed, and only those. When nothing matches the reply is
no_match plus a ready-to-call intake — the corpus saying "not this one yet", not a dead end.
A skill teaches an agent how to do something; a lesson records what went wrong before and how not to fail again. MisakaNet is only the second thing. → FAQ
data/badges/lessons.json, regenerated by update-badges.yml, so it can lag a run but is never a
hand-typed total.E4 needs an observation —
two distinct clients actually retrieving a lesson — and the corpus has none yet
(distribution, regenerated and checked by CI).no_match plus an intake instead of an empty page.One narrow question: when you hand a model a lesson, how much of that lesson comes back? The
metric is lesson_hit_rate — the share of the injected lesson's commands reproduced in the answer.
Read the setup before the number: the scenario in this benchmark is each lesson's own title, the injected
lesson is that same lesson,
no retrieval call is made, and correctness is not checked. It measures the recitation half of RAG:
necessary for MisakaNet to help, and not evidence that search finds anything.
The run is paused. Two independent runs of ≈500 scenarios each on 2026-09-22: 46.1% with the
lesson pasted in, 23.3% without. What remains is the last snapshot plus its dated record —
docs/benchmarks/latest.json.
The table below is generated by scripts/update_readme_benchmark.py;
do not hand-edit it.
1155 run(s) in latest.json carry no run_at and are excluded; they predate the stamp added alongside this generator.
with_lesson hit rate (per run date)
43.8% │ ▁
46.1% │ ▄
46.6% │ ▄
48.3% │ ▆
49.1% │ █
└──────────────────
08 09 09 09 10
31 06 14 21 12
Per-run files: docs/benchmarks/ · metric definition: METRIC_DEFINITION in
scripts/benchmark_workers_ai.py.
1. Report a failure the corpus does not have. Search first, then call misakanet_submit_intake —
no account, no email, no token, a five-line report is enough. It becomes a tracked issue.
2. Reuse a lesson and leave the trace. A "this helped" vote is recorded as an E3 hint, not as
proof. The proof is quieter: your retrieval is counted, anonymously, as one more distinct client.
What you get back: attribution. A lesson cites the intake that produced it (source:,
provenance.issue:), and the pipeline can emit a receipt naming the lesson and its evidence level.
Nothing here is a bounty: this repository pays nothing and promises nothing. Some issues carry third-party reward banners added by our own automation; we do not administer them — see Contributing.
Pick one channel; they are independent.
The two-package trap (it cost a real install failure, #1849):
Reads are anonymous and unlimited (a per-address burst window is a speed limit, not a quota).
Registration is for writing: it unlocks misakanet_write_lesson and misakanet_preflight
(why).
Verify an install with npx @misaka-net/misakanet-setup --verify; undo it with --uninstall.
Prerequisites: Node ≥ 18 for the installer, Python ≥ 3.10 for the library and stdio server.
When a workflow fails, the action searches the lessons and comments the closest match on the pull request (optionally reporting the new error). Published on GitHub Marketplace.
on:
workflow_run:
workflows: ["CI"] # your CI workflow's name
types: [completed]
permissions:
actions: read # read the failing job's log (required)
pull-requests: write # post the comment
issues: write # the comment endpoint is issues.createComment
jobs:
intake:
if: ${{ github.event.workflow_run.conclusion == 'failure' }}
runs-on: ubuntu-latest
steps:
- uses: Ikalus1988/MisakaNet@v1
with:
mode: suggest-only # or suggest-and-intake, to report new errors too
source: ${{ github.repository }}
Zero bounty. Maximum rigor. Merge earns credit.
"Zero bounty" is a statement about this repository: MisakaNet pays nothing and promises nothing. It
is not a statement about the issue you are looking at. Some issues carry an Opire banner
advertising a third-party reward, added automatically by our own
scripts/question_autopilot.py — we do not administer those payouts,
and Opire is not mentioned in CONTRIBUTING.md. Verify any reward offer independently before you
plan work around it. The only thing this repository has ever honoured is a merged PR.
(#2903)
python3 scripts/misakanet_cli.py smokepython3 search_knowledge.py "your error here"⚠️ Sandbox your agent before executing retrieved commands. Lessons are community-contributed —
review before running. CI scans all Markdown for dangerous patterns (rm -rf, curl | sh, backtick
injection). See SECURITY.md and LIMITATIONS.md.
Prefer MCP intake for missing or stale lessons; PRs are optional. Search first; if nothing matches,
call misakanet_submit_intake at https://misakanet.org/mcp — no account, no token. Never send
secrets or raw private logs. Protocol: docs/mcp-intake-guide.md.
Built by the network, for the network. Zero bounties paid — only merge approval and eternal network gratitude. ⚡
Apache-2.0 — Copyright 2026 Ikalus1988. Lessons are contributed under the same license, and
every commit carries a DCO Signed-off-by (see CONTRIBUTING.md).
Failure-memory layer for coding agents: search evidence-rated failure lessons by error text.
{ "mcpServers": { "io.github.ikalus1988-misakanet": { "url": "https://misakanet.org/mcp", "headers": {} } }}도구
아직 도구 목록이 없습니다. 원격 서버는 첫 상태 확인 후에 도구 목록이 생깁니다.
FAQ
이 페이지에서 Cursor, Claude Desktop, Claude Code 또는 VS Code용 http 설정을 복사합니다. PlugMCP 프록시가 아니라 게시자의 설치 방식을 사용합니다.
이 레코드에는 필수 환경 변수가 등록되어 있지 않습니다.
Misakanet에는 HTTP로 연결합니다.
마지막 확인: 2026-11-15. Failure-memory layer for coding agents: search evidence-rated failure lessons by error text.