Entropy0dev MCP server

by entropy0dev·io.github.entropy0dev/mcp·v0.1.3·1 stars

No reviews yet

Entropy0 MCP server — source trust and URL safety tools for AI agents

C69/100grade C

Write a review Install

What users say

No reviews yet

Be the first

Safety scan

C69/100

full report

Adoption

New

1 stars38 downloads/wk

Reviews

Write one

Nobody has reviewed Entropy0dev yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Entropy0dev tools (6, 1 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

entropy0_create_trust_receiptwrite action
Create a structured trust receipt that records the entropy0 evaluation result alongside the action the agent actually took. Use this to attach auditable evidence to agent actions before writing to logs, memory, or an audit trail. Every external source should get a trust receipt before it enters the agent workflow.
entropy0_decide_domain
Evaluate a domain's trust posture before any agent interaction with it. Use for domain-level checks where full URL path context is not needed \u2014 for example before adding a domain to an allowlist, before connecting to an API on that domain, or before resolving it in a multi-step workflow. Returns the same stable decision shape as entropy0_decide_url.
entropy0_decide_url
Evaluate whether an agent should proceed with a URL before fetching, navigating, downloading, or submitting credentials to it. Use this before any agent fetches, summarises, cites, downloads, or follows a URL. Returns a stable decision object: action (proceed / proceed_with_caution / sandbox / escalate_to_human / deny), scores, reason codes, fetch policy, and explanation.
entropy0_explain_decision
Returns a plain-language explanation of the decision, including key evidence and reason codes. Use this when you only need the explanation text \u2014 for example to surface trust context to a user. For the complete decision (scores + policy + explanation), use entropy0_check_source instead.
entropy0_filter_urls
Evaluate a list of URLs or domains in parallel and return them grouped by trust decision: approved (proceed/proceed_with_caution), sandboxed, or denied. Use this after a web search to gate which sources the agent may fetch before ingestion. Maximum 20 URLs per call.
entropy0_get_fetch_policy
Returns only the fetch policy for a URL or domain \u2014 allow/block flags for credentials, JavaScript, and downloads, plus a content_treatment label. Use this when you only need the policy flags and not the full score breakdown. For the complete decision (scores + reason codes + policy + explanation), use entropy0_decide_url or entropy0_decide_domain instead.

Public scan report

scanner v0.1.9 · 2026-09-27 · same rubric, same numbers if you re-run it

no findings

Code scan5 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 128 days ago8/15
Maintainer identityregistry namespace matches repository owner6/10

Overall 69/100. Components that don't apply are left out of the denominator. Any critical finding is an F.Rubric Appeal a finding JSON

How Entropy0dev compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score: 69/100; higher than 33% of 48,255 servers
Tools: 6; the typical server has 7
Tools that change things: 17%; typical: 0%. Fewer write tools means less an agent can break
GitHub stars: 1; more than 65% of 28,688 servers
Downloads a week: 38; more than 29% of 12,191 servers with a package

What its tools let an agent do: 5 read · 1 change

Install Entropy0dev in Claude Code, Cursor or VS Code

Runs npx -y @entropy0/mcp on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add mcp -- npx -y @entropy0/mcp

Add to Cursor

What the publisher says

From the Entropy0dev repository's README, as published. We do not edit it. Read it on GitHub

Entropy0 SDK

AI agents fetch URLs, follow links, and act on domains they've never seen before. Most of the time that's fine. Sometimes it isn't — phishing infrastructure, newly registered lookalike domains, brand impersonation sites, or plain malware hosting.

Entropy0 adds a trust gate between your agent and the external web. One API call returns a machine-readable recommended action your agent can reason about before it fetches, navigates, or transacts.

Try it without signing up →

POST /v1/decide
{ "domain": "secure-login-verify-account.xyz" }

→ recommended_action: "deny"
  confidence: 91%
  signals: [NEWLY_REGISTERED_DOMAIN, BRAND_MISMATCH, CERTIFICATE_ANOMALY]

Packages

Quick start

LangChain (Python)

pip install entropy0-langchain

from entropy0_langchain import Entropy0Tool

tools = [Entropy0Tool(api_key="sk_ent0_xxxx")]
# Agent will call entropy0_trust_check before fetching any external URL

Express (Node.js)

npm install @entropy0/express

import { entropy0Guard } from "@entropy0/express";

app.use(entropy0Guard({ apiKey: process.env.ENTROPY0_API_KEY! }));
// Requests to flagged domains are blocked before your handlers run

Direct API

curl -X POST https://entropy0.ai/v1/decide \
  -H "X-API-Key: sk_ent0_xxxx" \
  -H "Content-Type: application/json" \
  -d '{"domain": "example.com"}'

How it works

Each decision runs a deterministic pipeline — same inputs always produce the same output:

Classifies the domain (Clear Threat → Safe Known) using WHOIS, DNS, SSL, and threat intel feeds
Maps classification to a base action under your chosen policy
Shifts strictness based on interaction risk (fetch vs transactional vs privileged)
Applies confidence clamps — low-confidence negatives never hard-deny
Returns recommended_action + reason codes + uncertainty + bounded validity window

No probabilistic black boxes. Auditable, explainable, overridable.

Examples

LangGraph trust gate demo

This example shows a four-layer retrieval pipeline:

Search returns candidate sources
Entropy0 evaluates whether each source should enter the workflow
The extraction layer retrieves page content
The evidence usability layer determines whether the agent can safely cite the content

Example run:

[entropy0] 5 approved / 1 sandboxed / 0 denied / 0 unverified
  SANDBOX    outpost24.com
             trust signals: ['LONG_OPERATIONAL_HISTORY', 'STRONG_BRAND_ALIGNMENT']
             sandbox reason: ['ELEVATED_DEVIATION']

[evidence layer]
  ! microsoft.com/security/blog/...   boilerplate_dominant — usability=low
  ! genai.owasp.org/llmrisk/...       boilerplate_dominant — usability=low
  ✓ pmc.ncbi.nlm.nih.gov/...          body_text_captured   — usability=high
  ✓ securecodewarrior.com/...         body_text_captured   — usability=high

The agent answered only from high-usability evidence and refused to attribute claims to sources where article body text was not captured.

This prevents a common failure mode in AI search agents:

Treating a reputable URL as equivalent to usable evidence.

Links

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Entropy0dev: common questions

Is Entropy0dev MCP server safe?: With care: it is graded C, so read the findings first (69/100). Read the Entropy0dev safety report
How do I install Entropy0dev?: It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Entropy0dev need an API key?: Yes. The registry entry asks for ENTROPY0_API_KEY.
Is Entropy0dev maintained?: The last commit was 165 days ago (2026-05-22). The latest release is v0.1.3.
How does Entropy0dev compare with other MCP servers?: safety score 69/100 (higher than 33% of 48,255 servers); tools 6 (the typical server has 7); tools that change things 17% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.