Misakanet runs on your own machine — the client starts it, so there is no endpoint to ping. 2 574 installs a week from pypi. Last commit 2 Nov 2026.
Failure-memory layer for coding agents: search evidence-rated failure lessons by error text.
We read the source, 11 min ago · rules 995398eba69f
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
"problem": "`crontab -e` 设置好后,作业从未执行。输出没有、日志没有、进程没有。",
const child = spawn(cmd, args, { detached: true, stdio: 'ignore' });
fixture_path = os.path.join(fixture_dir, fixture_name)
if (/SELECT key FROM kv_store/i.test(text)) {
const filtersExpiry = /expires_at\s+IS\s+NULL\s+OR\s+expires_at\s*>\s*datetime\('now'\)/i.test(text);
r = subprocess.run(
…ential store\n\n```bash\n# 确认 credential.helper=store 还在\ngit config --global credential.helper store\n# 确认 .git-credentials 里有有效 token\ncat ~/.git-credentials\n# 格式: https://<username>:<token>@github.com\n```\n\n### 4. 验证\n\n```bash\ngit ls-remote ori…
import { existsSync, mkdirSync, readFileSync, readdirSync, copyFileSync, rmSync,
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add misakanet -- uvx misakanet
{
"mcpServers": {
"misakanet": {
"command": "uvx",
"args": [
"misakanet"
]
}
}
}
[mcp_servers.misakanet]
command = "uvx"
args = ["misakanet"]
{
"mcpServers": {
"misakanet": {
"command": "uvx",
"args": [
"misakanet"
]
}
}
}
{
"servers": {
"misakanet": {
"type": "stdio",
"command": "uvx",
"args": [
"misakanet"
]
}
}
}
Efficient context management: code search, evidence packs, and memory for coding agents.
Persistent memory for AI coding agents. Hybrid search, auto-session capture, context routing.
Evidence-backed project memory and checkpoints for AI coding agents.
A self-improving, verifiable memory layer for AI coding agents.
Team memory for AI coding agents and code reviews, reviewed by humans and served over MCP.
Session memory for AI coding agents. Search past sessions, extract rules, and track what works.
Persistent memory graph for coding agents: hypotheses, evidence, and decisions survive sessions.
Memory, docs, and repo context layer for engineering agents.
Answers built from our own checks of this server.