Mmcp.market

Nemesis Shield MCP server

by eobi·io.github.eobi/nemesis-shield·v0.2.7
No reviews yet

Positive-security for apps, APIs, LLMs and edge, plus fraud scoring and identity/AML screening.

A92/100grade A
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
A92/100

full report

Adoption
Growing

0 stars33 downloads/wk

Reviews

Write one

Nobody has reviewed Nemesis Shield yet.

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

Nemesis Shield tools (17, 5 write)

write = sends, deletes, buys or posts

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

  • nemesis_approve_routes

    Approve all learned behaviors for an app so it is ready to enforce — the create → learn → approve →

  • nemesis_create_appwrite action

    Create a Nemesis Shield app in the developer's account and return its install token (nsk_). This is

  • nemesis_create_omniguardwrite action

    Create an Omniguard business-logic firewall for money & accounts, pre-loaded with the fraud rules

  • nemesis_edge_status

    List the domains behind Nemesis Edge for the developer's account, with each zone's status

  • nemesis_explain

    Explain how Nemesis Shield covers a security topic (positive-security, idor/bola, prompt-injection,

  • nemesis_list_apps

    List the apps in the developer's Shield account, with each app's mode (observe/alert/enforce) and

  • nemesis_list_frameworks

    List every framework/stack Nemesis Shield has a one-line integration for.

  • nemesis_omniguard_catalog

    List Omniguard sectors and events (and what each protects) so you can pick the right business-logic

  • nemesis_omniguard_score

    Score a transaction against an Omniguard function (allow / review / block) — test the business-logic

  • nemesis_omniguard_verifywrite action

    Run a standalone Omniguard verification/screening check — NO Omniguard function required — using the

  • nemesis_protect

    Return the exact, verified one-line Nemesis Shield install + integration snippet to add positive-security

  • nemesis_protect_llm

    Protect an LLM feature against prompt injection and the OWASP LLM Top 10. Creates an llm-kind Shield

  • nemesis_provision_edgewrite action

    Put a domain behind Nemesis Edge, the positive-security network/DNS layer (a Cloudflare-like edge

  • nemesis_run_learnwrite action

    Run the Nemesis Learn agent locally to exercise every route of your app in dev/staging so the Shield

  • nemesis_scan

    Passively fingerprint a public website or API URL: detected stack, real published CVEs for what's

  • nemesis_server_agent

    Protect a whole server (e.g. an Ubuntu box running several apps) with the Nemesis host agent. Mints

  • nemesis_set_mode

    Set a Shield app's enforcement mode: observe (learn, block nothing), alert, or enforce (block

Public scan report

scanner v0.1.9 · 2026-09-23 · same rubric, same numbers if you re-run it

no findings
  • Code scan6 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 qualitylocal package, no credentials required12/15
  • Maintenancelast push 16 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 92/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

What the publisher says

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

Nemesis Shield - SDKs

Official, open-source SDKs for Nemesis Shield - the unified runtime security platform (application/API/LLM shield, telemetry correlation, network/DNS, response, and compliance). Drop one into your app and Nemesis learns your app's normal behavior, then flags - and, in enforce mode, blocks - anything that deviates. It's a positive-security (allow-list) model: instead of guessing at generic attack signatures, it enforces "this app only ever behaves in these ways."

Building with an AI assistant? Two ways to make your agent add Nemesis Shield as it builds:

1. MCP server - gives Cursor, Claude Code/Desktop and Windsurf 17 callable tools

(nemesisprotect, nemesisscan, nemesis_explain, plus Omniguard fraud scoring and standalone

identity/AML screening via nemesisomniguardverify) so the agent adds security, scans a site,

screens identities, and explains coverage without leaving the editor.

2. AI editor rule pack (AGENTS.md, Cursor, Windsurf, Claude Code) - drop-in rules

that tell the agent to add the one-line SDK by default.

Both are one line per stack, safe by default (observe mode). Full verified reference:

ai-rules/AGENTS.md.

Privacy by design: the SDKs ship only behavioral metadata - HTTP method, the shape of the path (/orders/123 → /orders/{int}), status code, and whether the caller was authenticated. They never send your request bodies, responses, secrets, or source code. Every SDK is fail-open: if Nemesis is unreachable, your app is completely unaffected.

New app? Finish learning in minutes with Nemesis Learn. Drop in an SDK (observe mode),

then run one command and the agent exercises every route of your app in dev/staging - endpoints,

forms, uploads, CRUD flows - so the baseline completes without waiting on real traffic. It's

language- and framework-agnostic (drives your app over HTTP), runs offline, can read your repo to

find routes, and reports coverage back so the console shows exactly when you're ready to enforce.

bash

npx @nemesis-shield-autogon/learn --target http://localhost:3000 --app-token nsk_… --repo .

Front-end (browser)

Shortened. The full README is on GitHub.

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

Install directly

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

claude mcp add nemesis-shield -- npx -y @nemesis-shield-autogon/mcp
Add to Cursor

Nemesis Shield: common questions

Is Nemesis Shield MCP server safe?
Yes, by our scan: it is graded A (92/100). Read the Nemesis Shield safety report
How do I install Nemesis Shield?
It runs on your machine. Copy the Claude Code, Claude Desktop or Cursor config from the install section.
Does Nemesis Shield need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Nemesis Shield maintained?
The last commit was 17 days ago (2026-09-07). The latest release is v0.2.7.
What can I use instead of Nemesis Shield?
Servers from other publishers that do the same job: prodlint MCP server, Avanan MSP (Legacy SmartAPI) MCP server and CrowdStrike Falcon MCP Server. Compare all Nemesis Shield alternatives.

Alternatives to Nemesis Shield

Same job from other publishers: the closest match first, then the best rated.

All Nemesis Shield alternatives →
  • prodlint
    Production readiness for vibe-coded apps. 52 checks for security, reliability, and performance.
    A
  • Avanan MSP (Legacy SmartAPI)
    MCP server for the legacy Avanan SmartAPI: MSP tenant management plus per-tenant security tools.
    More from WYRE-AI →
    B
  • CrowdStrike Falcon MCP Server
    Connects AI agents with CrowdStrike Falcon for security analysis and automation.
    A
  • SSH Manager
    SSH server management for agents, with per-server read-only and allowlist security modes
    B
  • Reversecore MCP
    Security-first MCP server for reverse engineering, malware analysis, forensics, and SAST.
    B
Nemesis Shield vs prodlintNemesis Shield vs Avanan MSP (Legacy SmartAPI)Nemesis Shield vs CrowdStrike Falcon MCP Server

More from eobi →