mcpbeat Sign in

Plzebo MCP Server

local only

Plzebo runs on your own machine — the client starts it, so there is no endpoint to ping. 52 installs a week from npm. Last commit 14 Aug 2026.

Cost-parity bench for agent loops: $/success and time across model mixes, with verifiable receipts.

Installs per day peak 14 · avg 6 · +11% w/w
a month agotoday
52
Installs / week
npm · plzebo
0
Stars
0 open issues
14 Aug 2026
Last commit
1 release in 90 days
MIT
License
TypeScript

Nothing serious here today

Today is the operative word: we check Plzebo every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Three servers free · no card

Connect this server

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.

run in your terminal
claude mcp add plzebo -- npx -y plzebo
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "plzebo": {
      "command": "npx",
      "args": [
        "-y",
        "plzebo"
      ]
    }
  }
}
~/.codex/config.toml
[mcp_servers.plzebo]
command = "npx"
args = ["-y", "plzebo"]
.cursor/mcp.json
{
  "mcpServers": {
    "plzebo": {
      "command": "npx",
      "args": [
        "-y",
        "plzebo"
      ]
    }
  }
}
.vscode/mcp.json
{
  "servers": {
    "plzebo": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "plzebo"
      ]
    }
  }
}

Optional settings from the registry entry, left out of the block above: ANTHROPIC_API_KEY (Real Anthropic key for placebo-mode arms; arms only ever see placebo keys. Optional when every arm uses passthrough auth), OPENAI_API_KEY (Real OpenAI-compatible key for placebo-mode arms. Optional when every arm uses passthrough auth).

Alternatives to Plzebo

same job, measured the same way
G
Glyt
by glyt

Human-in-the-loop approval for agent actions, with verifiable action-bound receipts.

6 tools answering
Ausca
by ausca

Pay-per-call APIs and MCP services for agents, no accounts or keys, with verifiable receipts.

425 installs/wk 17 tools answering
MELRA
by xagi-lab

Local MCP runtime for policy-governed, verified agent actions with durable receipts.

1 592 installs/wk local only
LLM Pricing
by skakumanu

Real-time, drift-verified LLM pricing across 31 providers with cost+quality model routing.

963 installs/wk 32 tools answering
Wever Labs Agentic Rails
by weverlabs

Agentic rails for complex workflows with receipts, fees, and MCP tool access.

5 tools answering
Concordance
by narrowhighway

Deterministic claim verification with receipts across ~60 domains. No model in the loop.

102 tools answering
Loop Desk
by bot2botlabs

Agent-payable open-loop tracker for refunds, returns, and asks with TRACE receipts.

3 tools answering
Comparr
by comparr

Compare prices across French merchants, with recorded price history and verified price drops.

4 tools answering

Plzebo — questions

Answers built from our own checks of this server.

Why is there no uptime for Plzebo?
Plzebo runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the npm package plzebo was installed 52 times last week.
How do I connect Plzebo?
Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It runs locally, so the command pulls plzebo straight from npm; nothing to host, nothing to sign up for.
How many people use Plzebo?
The npm package plzebo was installed 52 times in the last week. Week over week that is +11%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.
Is Plzebo open source?
Yes — it is published under the MIT licence, written in TypeScript and 0 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.