BPJ Task Loop is answering right now. Last checked 6 min ago. It exposes 2 tools. Last commit 24 Oct 2026.
BPJ rule-based task-state reviews and workflow tool discovery. Free, no account required.
What the code does
We read the source, 2 h ago · tools taken from the live server · rules 995398eba69f
A value the model can set ends up inside a file or shell call. That is not a flaw by itself — for a terminal server it is the job — but it is where things go wrong when it is not.
title_result = subprocess.run(
Things with no honest explanation: a promise that contradicts the code, code that runs at install time while hiding what it does, data leaving the machine.
…te=sf.read(raw);factor=max(1,len(samples)/rate/(b-a-.25));assert factor<1.35,(i,factor);fitted=OUT/f'voice-fit-{i}.wav';subprocess.run(['ffmpeg','-v','error','-y','-i',str(raw),'-af',f'atempo={factor:.6f}','-ar',str(sr),str(fitted)],check=True);samples,_=sf.read(fitted);start=int…
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.
assert.match(r.findings[2].text,/description（可能截断；发布者自述，未独立核验）/);assert.ok(!r.evidence.some(x=>x.field==='stars'));assert.doesNotMatch(r.nextActions[0].action,/steal|perfect/);
local_path = os.path.join(tmp_dir, f"episode{ext}")
check = subprocess.run(
result = subprocess.run(cmd, shell=True, capture_output=True, text=True, check=check)
…入记录；选择本身不会改动已有计划。')}</p>${fitQuestions.map(q=>`<label class="field">${q.label[lang]}<select id="commercial-${q.id}"><option value="unknown">${t('Not established','尚未明确')}</option><option value="yes">${t('Yes','是')}</option><option valu…
return spawnSync(process.execPath,['--input-type=module','--eval',command],{encoding:'utf8',timeout:10000});
document.getElementById("concepts").innerHTML = DATA.concepts.map((c, i) => `
for ep_dir in sorted(episodes_dir.iterdir()):
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
A tool parameter here reaches a dangerous call
That is not a flaw by itself — but it is where things go wrong when it is not the job. We re-read this code on every release. Watch it and you hear from us the day another one appears.
Connect this server
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 6 min ago.
claude mcp add bpj-ai-tools --transport http https://baipiaoji.com/api/ai-mcphttps://baipiaoji.com/api/ai-mcp[mcp_servers.bpj-ai-tools]
url = "https://baipiaoji.com/api/ai-mcp"{
"mcpServers": {
"bpj-ai-tools": {
"url": "https://baipiaoji.com/api/ai-mcp"
}
}
}{
"servers": {
"bpj-ai-tools": {
"type": "http",
"url": "https://baipiaoji.com/api/ai-mcp"
}
}
}Available tools 2
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
list_bpj_ai_tools
review_task_state
Endpoints
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://baipiaoji.com/api/ai-mcp | streamable-http | answering | 218 ms | 6 min ago |
Alternatives to BPJ Task Loop
same job, measured the same way73 x402-paid Base and Solana APIs with free discovery, samples, workflows, and Pixel Acre.
Discover, run, inspect, build, test, and privately reuse AI workflows.
Free public n8n, AI support and software acceptance templates; scoped private delivery workflows.
SEO research, keyword discovery, site audits, Search Console, backlinks and content workflow.
Discover and retrieve published Amo.ng Prompts, Workflows, and Skills.
Free small-business facts and stateless workflow review kits: quotes, invoices and order handoffs.
Secure MCP access to Big Red Cloud accounting data, workflows, help and training.
Build and operate Dapr Workflows and Durable Agents on Diagrid Catalyst. Sign-in required.
BPJ Task Loop — questions
Answers built from our own checks of this server.