MCP Legiti

Name: MCP Legiti
Author: codespar

by codesparversion 0.2.0-alpha.4i★ –iRuns on your computer

Registry nameio.github.codespar/mcp-legiti

Install

Overview

Description from the maker (original English)

DEPRECATED: no live endpoint (collection-prod.inspcdn.net does not resolve)

PopNx MCP’s three pillars

These three are never merged into one score: opinions, measurements and popularity are different things.

User voiceiNo reviews yetReviews open together with accounts in a later step
Our basic checksi1 of 1 passedChecked from public information; code not scanned yet
UsageiNot measured yet★ –

What you can do with it

We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.

Connection: Runs on your computer
Transport: stdio
Category: Other
You need to fill in: LEGITI_API_KEY

Install

Pick the AI app you use, then copy the settings.

Before you install

Basic checks: 1 of 1 passed
Runs on your computer with your user’s permissions (files, network, apps).
You fill in yourself: LEGITI_API_KEY, LEGITI_BASE_URL

Values marked secret are keys to your account. Never share them or paste them into a chat.

You need

npmNode.js installed (for the npx command)

Which app do you use?

ClaudeClaude CodeCursorVS CodeChatGPT

Pick your app above. We remember it, so next time the button says “Install in …”.

Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json

{
  "mcpServers": {
    "legiti": {
      "command": "npx",
      "args": [
        "-y",
        "@codespar/mcp-legiti"
      ],
      "env": {
        "LEGITI_API_KEY": "your-value",
        "LEGITI_BASE_URL": "your-value"
      }
    }
  }
}

Run this in your terminal

claude mcp add legiti --env LEGITI_API_KEY=your-value --env LEGITI_BASE_URL=your-value -- npx -y @codespar/mcp-legiti

Fill in the empty values before running it.

Open in Cursor

Or copy the settings yourself

Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json

{
  "mcpServers": {
    "legiti": {
      "command": "npx",
      "args": [
        "-y",
        "@codespar/mcp-legiti"
      ],
      "env": {
        "LEGITI_API_KEY": "your-value",
        "LEGITI_BASE_URL": "your-value"
      }
    }
  }
}

Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.

Open in VS Code

Or copy the settings yourself

Paste into .vscode/mcp.json in your project

{
  "servers": {
    "legiti": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@codespar/mcp-legiti"
      ],
      "env": {
        "LEGITI_API_KEY": "your-value",
        "LEGITI_BASE_URL": "your-value"
      }
    }
  }
}

Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.

This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.

Your choice stays on this device in a cookie; no account needed.

Values you fill in

LEGITI_API_KEY secret required env
Legiti API key (JWT-format bearer token). Use the sandbox key while testing — Legiti trains its ML models on every request, so test data hitting a production key pollutes the model.
LEGITI_BASE_URL env
Legiti API base URL. Defaults to https://collection-prod.inspcdn.net. Legiti issues customer-specific base URLs — override per contract.

These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.

What it can do

Runs on your computer; the tool list appears in your AI app after you install it.

Basic checksi

We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 7, 2026

✓ Pass
Maker matches the repo
The registry name was verified with the GitHub account codespar, which owns the repo
… Not checked yet
Still maintained
We have not read this repo from GitHub yet
… Not checked yet
Has a licence
We have not read this repo from GitHub yet
– Not applicable
Endpoint responds
This one runs on your computer; there is no internet endpoint
– Not applicable
Sign-in with OAuth
Runs on your computer and uses local settings instead
… Not checked yet
No hidden instructions in tool descriptions
Runs on your computer; we can only read tool lists from internet endpoints

Compared with others in Otheri

More stars than 0% of the other 32709 servers in this category
Published to the registry more recently than 50% of the other 32709 servers in this category
Basic checks equal to or better than 100% of the other 32709 servers in this category

Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.

Common questions

Is MCP Legiti safe?

It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.

What keys or codes does it need?

You need to fill in: LEGITI_API_KEY

Does it run on my computer or in the cloud?

It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).

Is it still maintained?

The GitHub repo last changed –, and the latest version (0.2.0-alpha.4) reached the registry 41 days ago.

Which apps can use it?

Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Node.js on your computer.

What can I use instead?

In the same category: Spec Driven Development, Remote Desktop Commander, SwarmMemo

Alternatives

Servers in the same category from other makers, sorted by stars.

Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi

Spec Driven Development

by formulahendry

MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.

Runs on your computer★ 440MITUpdated 14 months ago

Install

Remote Desktop Commander

by desktop-commander

Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.

Runs in the cloud★ 211Updated 2 days ago

Install

SwarmMemo

by Hugo0

Talk with agent swarms: rooms, private messages and paid tasks for AI agents

Runs in the cloudUpdated today

Install

README from the maker

Open the README

Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.

@codespar/mcp-legiti

Deprecated: no live endpoint. Measured on 2026-09-27 against two public DNS resolvers (8.8.8.8 and 1.1.1.1): collection-prod.inspcdn.net, the host this server calls, does not resolve in DNS. No tool in this server reaches a service. The package is deprecated on npm and stays in this repository for reference only. If you have a working endpoint, point the server at it with LEGITI_BASE_URL. To bring the package back, open an issue in mcp-dev-latam with the provider's documented base URL.

MCP server for Legiti — Brazilian fraud prevention, ticketing-native with a simple synchronous evaluation API.

Fourth entry in the CodeSpar fraud category, after @codespar/mcp-clearsale, @codespar/mcp-konduto, and @codespar/mcp-sift. Legiti (formerly Inspetor, São Paulo) occupies the mid-size BR tier: smaller public footprint than ClearSale, more vertical depth than Konduto for ticketing / events, and a simpler API surface than Sift.

Positioning

	Strength	Typical fit
ClearSale	BR pioneer (2001), large chargeback history	Default for large BR retail
Konduto	BR, API-first, behavioral device intel	Digital-native BR ecommerce
Legiti (this)	BR, ticketing-native, sync evaluation	BR ticketing marketplaces, mid-size retail
Sift	Global, multi-abuse-type ML, workflows	International enterprise

BR merchants frequently bundle 2-3 of these for best-of-breed scoring — Legiti for its ticketing-specific signals, ClearSale or Konduto for the generalist fraud layer, Sift for cross-border flows.

Tools (18)

Tool	Purpose
`evaluate_order`	Submit an order to Legiti for real-time fraud evaluation via the v2 order endpoint.
`update_order`	Notify Legiti of a status change on an existing order (e.g.
`mark_order_fraudulent`	Report a confirmed chargeback / fraud outcome back to Legiti.
`evaluate_sale`	Legacy single-shot sale evaluation via POST /evaluation.
`track_account`	Notify Legiti of an account lifecycle event (created / updated / deleted).
`track_event`	Notify Legiti of an Event (concert, show, match, session) lifecycle change.
`track_sale`	Notify Legiti of a Sale state change (created / updated).
`track_auth`	Notify Legiti of an authentication or password event (login attempt, logout, password recovery request, pas...
`track_login`	Notify Legiti of a login attempt (successful or failed).
`track_logout`	Notify Legiti of a logout event.
`track_signup`	Notify Legiti of a new account creation.
`track_account_update`	Notify Legiti of an account profile change (email, phone, CPF, address).
`track_password_recovery`	Notify Legiti of a password recovery request (the 'forgot password' click).
`track_event_view`	Notify Legiti that a user viewed an event/show page.
`track_payment`	Notify Legiti of a payment-method-level event (authorization attempt, capture, refund, void).
`get_decision`	Fetch the latest Legiti decision for an order.
`update_decision_status`	Manually override Legiti's decision for an order — typically used to accept or decline a sale that landed i...
`mark_dispute_resolution`	Report the outcome of a chargeback dispute back to Legiti — i.e.

Install

npm install @codespar/mcp-legiti@alpha

Environment

LEGITI_API_KEY="eyJhbGciOi..."   # JWT bearer token; required

LEGITI_BASE_URL="..." # optional; defaults to https://collection-prod.inspcdn.net

Authentication

Bearer token (JWT-format):

Authorization: Bearer <LEGITI_API_KEY>

Legiti issues separate sandbox and production keys. The sandbox key tags every request as test data so it does NOT train the ML model. Always develop and run integration tests with the sandbox key — hitting production with test data pollutes the model.

Decision values

evaluate_order and evaluate_sale return one of three decisions:

approve — ship it
reject — block the sale
manual — route to manual review

Evaluation is synchronous; the response may take up to ~20 seconds.

Typical flow (ticketing)

At signup / login, call track_account (create/update) and track_auth (login/logout, password_recovery, password_reset). Every auth attempt — successful or failed — is valuable signal for account-takeover detection.
When a new event (concert, show, match) is published on the platform, call track_event (create). Update on price/capacity/date changes.
At checkout, call evaluate_order with the sale, account, payment, CPF, and the primary event_date_id. Act on the returned decision: approve → ship, reject → block, manual → human review.
As the order progresses (paid, shipped, delivered, cancelled, refunded), call update_order.
When a chargeback is confirmed by the issuer, call mark_order_fraudulent. This is Legiti's primary ML feedback channel — unreported chargebacks degrade future decision quality for similar buyers.

Typical flow (non-ticketing ecommerce)

Skip track_event. The event_date_id fields become optional in evaluate_order — Legiti will still evaluate on account + sale + payment signal, though ticketing-vertical features will be unused.

Alpha note

Shipped as 0.1.0-alpha.1. Legiti's public documentation is tighter than ClearSale's or Konduto's:

Documented in open-source `github.com/legiti/docs-backend`: POST /evaluation, plus the Collection API (account, event, sale, transfer, auth, password) shape and the Authorization: Bearer scheme.
Documented on `docs.legiti.com` integration guides: the v2 order family (POST /v2/order, PUT /v2/order, POST /v2/order/mark_fraudulent).
Dropped from the original category spec: create_rule / list_rules / update_rule / delete_rule — no public custom-rules surface exists on Legiti. If a customer contract exposes one, promote to 0.2.0.

Promote to 0.1.0 once the v2 order payload schema is confirmed in production.

Run

# stdio (default — for Claude Desktop, Cursor, etc)

npx @codespar/mcp-legiti

HTTP (for server-to-server testing)

MCP_HTTP=true MCP_PORT=3000 npx @codespar/mcp-legiti

Enterprise

Need governance, budget limits, and audit trails for agent payments? CodeSpar Enterprise adds policy engine, payment routing, and compliance templates on top of these MCP servers.

License

MIT

MCP Legiti

Overview

PopNx MCP’s three pillars

What you can do with it

Install

Before you install

Values you fill in

What it can do

Basic checksi

Maker matches the repo

Still maintained

Has a licence

Endpoint responds

Sign-in with OAuth

No hidden instructions in tool descriptions

Compared with others in Otheri

Common questions

Alternatives

Spec Driven Development

Remote Desktop Commander

SwarmMemo

README from the maker

@codespar/mcp-legiti

Positioning

Tools (18)

Install

Environment

Authentication

Decision values

Typical flow (ticketing)

Typical flow (non-ticketing ecommerce)

Alpha note

Run

HTTP (for server-to-server testing)

Category

Enterprise

License