Agentrisk MCP Server

by trycoin-ai Your server? Claim it

local only

Agentrisk runs on your own machine — the client starts it, so there is no endpoint to ping. 123 installs a week from pypi. Last commit 28 Sep 2026.

Risk guardrails for AI trading agents. Your agent proposes; your policy decides.

Installs per day peak 48 · avg 20 · +2% w/w

a month agotoday

123

Installs / week

pypi · agentrisk

Stars

0 open issues

28 Sep 2026

Last commit

from GitHub

MIT

License

Python

Nothing serious here today

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

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.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add agentrisk -- uvx agentrisk

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "agentrisk": {
      "command": "uvx",
      "args": [
        "agentrisk"
      ]
    }
  }
}

~/.codex/config.toml

[mcp_servers.agentrisk]
command = "uvx"
args = ["agentrisk"]

.cursor/mcp.json

{
  "mcpServers": {
    "agentrisk": {
      "command": "uvx",
      "args": [
        "agentrisk"
      ]
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "agentrisk": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "agentrisk"
      ]
    }
  }
}

Alternatives to Agentrisk

same job, measured the same way

Agentpay Sentinel MCP

by rumblingb

Security guardrails for AI agent payments

local only

Mandateguard

by ezequiellich44-cmd

Deterministic payment policy guardrail for AI agents - budgets, allowlists, signed mandates.

local only

Pit Officer

by openpitkit

Pre-trade risk limits for AI trading agents: every order is checked before it reaches your broker.

local only

Paper rails: payment rehearsal universe

by textforagents

Paper trading for agent payments: rehearse buying flows, earn policy-bound receipts.

answering

Hood MCP

by nirholas

Robinhood Chain data + guarded trading for AI agents: Stock Token quotes, portfolios, launches

64 installs/wk local only

Boundra — Payment Approval Gateway for AI Agents

by boundra

Allow, ask, or veto — a policy decision point your agent consults before signing any payment

14 tools answering

Trading Signals

by roman-rr

Live AI crypto trading signals for agents. Try 3 signals without a key; sign in from your agent.

5 tools answering

Tradememory Protocol

by mnemox-ai

Tamper-evident decision audit trail and outcome-weighted memory for AI trading agents.

187 installs/wk local only

Agentrisk — questions

Answers built from our own checks of this server.

Why is there no uptime for Agentrisk?

Agentrisk 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 pypi package agentrisk was installed 123 times last week.

How do I connect Agentrisk?

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 agentrisk straight from pypi; nothing to host, nothing to sign up for.

How many people use Agentrisk?

The pypi package agentrisk was installed 123 times in the last week. Week over week that is +2%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.

Is Agentrisk open source?

Yes — it is published under the MIT licence, written in Python and 2 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.