Reversecentaur MCP server
io.github.brandonbgreen/reversecentaur-mcp·v0.1.1Hire humans for tasks AI can't do. Fair trade pay floors, prepaid escrow, ethical receipts.
0 stars
Reviews
Write oneNobody has reviewed Reversecentaur yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Reversecentaur tools (6, 3 write)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
cancel_taskwrite actionCancel a previously posted task. Cancellation fees may apply if a worker has already been assigned.
check_taskCheck the status of a previously posted task. Returns the current status and, if completed, the human worker's deliverable.
list_capabilitiesList available task categories, fair trade pay minimums, worker availability, and current platform status.
list_task_messagesList all messages on one of your tasks, oldest first. Includes worker questions (pre-accept or post-accept), your own replies, and any system notices. Calling this marks worker-sent messages as read on the agent side.
post_taskwrite actionPost a task for a human worker to complete via the Reverse Centaur Fair Trade marketplace.
send_task_messagewrite actionSend a message to the human worker on one of your tasks. Use this to answer a clarifying question, add context, or follow up. Messages are scoped to a single task and are visible to the assigned worker (or to workers considering a posted task).
Public scan report
scanner v0.1.9 · 2026-09-27 · same rubric, same numbers if you re-run it
- Code scan29 source files scanned25/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitystatic API keys via environment variables6/15
- Maintenancelast push 9 days ago15/15
- Maintainer identitynamespace and repository owner differ4/10
How Reversecentaur compares
Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 77/100
- higher than 50% of 48,255 servers
- Tools
- 6
- the typical server has 7
- Tools that change things
- 50%
- typical: 0%. Fewer write tools means less an agent can break
What its tools let an agent do: 3 read · 1 delete · 2 send or post
Install Reversecentaur in Claude Code, Cursor or VS Code
Runs npx -y reversecentaur-mcp on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add reversecentaur-mcp -- npx -y reversecentaur-mcp
What the publisher says
From the Reversecentaur repository's README, as published. We do not edit it. Read it on GitHub
reversecentaur-mcp
AI agents hire humans for real-world tasks. Server-enforced pay floor, escrow that pays the worker if the agent goes dark, every fee on the receipt.
This is the MCP server for Reverse Centaur.
When your AI agent needs something only a human can do — verify a fact in the physical world, exercise creative judgment, sign a legal document, taste a wine — post a task to Reverse Centaur and a vetted human worker will complete it.
Installation
npm install -g reversecentaur-mcp
# or use directly with npx (recommended for MCP clients)
npx reversecentaur-mcpConfiguration
Claude Desktop
Add to your claudedesktopconfig.json:
{
"mcpServers": {
"reversecentaur": {
"command": "npx",
"args": ["-y", "@reversecentaur/mcp"],
"env": {
"REVERSECENTAUR_API_KEY": "your-api-key-here"
}
}
}
}Cursor
Add to your Cursor MCP settings:
{
"mcpServers": {
"reversecentaur": {
"command": "npx",
"args": ["-y", "@reversecentaur/mcp"],
"env": {
"REVERSECENTAUR_API_KEY": "your-api-key-here"
}
}
}
}Remote (HTTP Transport)
For remote MCP clients (including Anthropic Claude), run the HTTP server:
npx reversecentaur-mcp-http
# or with OAuth enabled:
REVERSECENTAUR_OAUTH=true npx reversecentaur-mcp-httpThe server listens on port 3001 by default. MCP endpoint: http://localhost:3001/mcp
Windsurf / Other MCP Clients
Any MCP client that supports stdio transport can use this server. Point it at:
npx reversecentaur-mcpWith the environment variables below.
Environment Variables
*Not required in mock mode.
Safety Annotations
All tools include MCP safety annotations:
Transports
Tools
post_task
Post a task for a human worker to complete.
Parameters:
- title (string, required) — Short title for the task (max 200 chars)
- description (string, required) — Detailed description (max 5000 chars)
- category (string, required) — One of: verification, research, physicalaction, creativejudgment, datavalidation, communication, legalidentity, sensory_evaluation, other
- budget_usd (number, required) — Budget in USD (must meet fair trade minimum)
- deadline_minutes (number, optional) — Deadline in minutes (default: 1440 = 24h, min: 15, max: 43200)
- deliverable_format (string, optional) — One of: text, json, image, file, confirmation (default: text)
- callback_url (string, optional) — Webhook URL for completion notification
check_task
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
Reversecentaur: common questions
- Is Reversecentaur MCP server safe?
- Mostly: it is graded B (77/100). Read the Reversecentaur safety report
- How do I install Reversecentaur?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does Reversecentaur need an API key?
- Yes. The registry entry asks for
REVERSECENTAUR_API_KEY. - Is Reversecentaur maintained?
- The last commit was 47 days ago (2026-09-18). The latest release is v0.1.1.
- How does Reversecentaur compare with other MCP servers?
- safety score 77/100 (higher than 50% of 48,255 servers); tools 6 (the typical server has 7); tools that change things 50% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.