Rede MCP server
MCP server for Rede — Itaú-owned BR acquirer: authorize/capture/refund, zero-auth, card tokens
271 stars25 downloads/wk
Reviews
Write oneNobody has reviewed Rede yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Rede tools (22, 7 write)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
authenticate_3dsInitiate a 3DS (EMV 3-D Secure) authentication for a card charge. Returns a threeDSecure reference id and, when required, a challenge URL for cardholder interaction.
authorize_debitAuthorize a debit card transaction on Rede. Requires a prior 3DS authentication — pass threeDSecure.embedded=true and a valid threeDSecure reference, or use authorize_with_3ds after authenticate_3ds.
authorize_transactionAuthorize a credit card transaction on Rede. Set capture=true to authorize + capture atomically; capture=false to authorize only (use capture_transaction later).
authorize_with_3dsAuthorize a transaction after a successful 3DS authentication, attaching the 3DS reference for liability shift. Works for both credit and debit.
cancel_boletowrite actionCancel an unpaid boleto. Paid boletos cannot be canceled — issue a refund via the payer's bank instead.
cancel_transactionwrite actionCancel an authorized-but-uncaptured transaction (void). Rede uses the refunds endpoint for both voids and refunds — cancel means full amount on an uncaptured transaction.
capture_transactionCapture a previously authorized transaction (when capture=false was used). Pass amount for partial capture; omit for full.
create_boletowrite actionIssue a boleto registrado via Rede. Rede registers the slip with the banking network and returns the typable line (linha digitável) plus the PDF/URL.
create_recurrencewrite actionCreate a native Rede recurrence (subscription). Rede handles retries and cardholder updates automatically.
delete_tokenwrite actionDelete a previously created card token.
disable_recurrenceDisable (cancel) an active recurrence. Stops all future billings.
get_3ds_statusCheck the current status of a 3DS authentication by its reference id. Returns whether the cardholder completed the challenge and the resulting 3DS reference to attach to an authorize call.
get_boletoRetrieve a boleto by Rede boleto id or by merchant reference. Returns status (REGISTERED, PAID, EXPIRED, CANCELED) and typable line.
get_recurrenceRetrieve a recurrence by Rede recurrence id.
get_recurrence_transactionsList transactions generated by a recurrence (one row per billing cycle executed).
get_tokenRetrieve metadata for a previously stored card token (brand, last 4, expiration). Does not return the PAN.
get_transactionRetrieve a transaction by Rede tid OR by merchant reference. Pass exactly one of tid or reference.
list_transactionsList transactions in a date range. Useful for reconciliation. Rede paginates results; pass page/size to walk pages.
refund_transactionwrite actionRefund a captured transaction. Pass amount for a partial refund; omit for full. Same endpoint as cancel; amount controls the behaviour.
tokenize_cardTokenize a card for PCI-safe reuse. Returns a token (storageCard) to pass into authorize_transaction.storageCard.
update_recurrencewrite actionUpdate an existing recurrence — change amount, card (storageCard), end date, or pause/resume. Pass only the fields you want to change.
zero_authValidate a card without charging (zero-auth / account verification). Returns whether the card is authorizable, without creating a transaction.
Public scan report
scanner v0.1.9 · 2026-09-26 · same rubric, same numbers if you re-run it
- 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 29 days ago15/15
- Maintainer identityregistry namespace matches repository owner7/10
How Rede compares
Against every graded Security MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 82/100
- higher than 66% of 915 Security servers
- Tools
- 22
- the typical Security server has 6
- Tools that change things
- 32%
- typical: 0%. Fewer write tools means less an agent can break
- GitHub stars
- 271
- more than 97% of 587 Security servers
- Downloads a week
- 25
- more than 11% of 248 Security servers with a package
What its tools let an agent do: 14 read · 2 create · 3 change · 3 delete
Install Rede in Claude Code, Cursor or VS Code
Runs npx -y @codespar/mcp-rede on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add mcp-rede -- npx -y @codespar/mcp-rede
What the publisher says
From the Rede repository's README, as published. We do not edit it. Read it on GitHub
MCP Dev LATAM 🌎 Every commerce API your AI agent needs to run a business in Latin America. Brazil 🇧🇷 · Mexico 🇲🇽 · Argentina 🇦🇷 · Colombia 🇨🇴 · Chile 🇨🇱 · Peru 🇵🇪 · plus 4 agentic payment protocols. MCP servers for LATAM commerce · live in the official MCP Registry · MIT License Machine-readable catalog: codespar.dev/api/servers Catalog · Quick Start · Agentic Protocols · All Servers · Contribute
The Problem
AI agents can write code, analyze data, and chat. But they can't operate a business — collect payments, issue invoices, ship products, or notify customers. Especially not in Latin America, where every service has its own API, auth pattern, and quirks (mTLS for BACEN Pix v2, JWT-RSA for STP-SPEI, AFIP web services, contract-gated developer portals, and on).
Meanwhile, four agentic payment protocols are shipping in parallel — checkout protocols (Stripe ACP, Google UCP), authorization layers (AP2), and micropayment rails (x402) — and none of them compose cleanly with each other or with the regional rails businesses actually run on.
MCP Dev LATAM bridges both gaps. Traditional LATAM services + the new agentic payment protocols, all accessible through a single MCP interface.
The Solution
Each MCP server in this repo wraps a real provider — payments, fiscal, logistics, messaging, banking, ERP, identity, fraud, crypto, and the agentic protocols — so your agent can operate a complete business workflow.
🛒 Customer places order
→ 💳 Agent charges via Pix (Asaas / Mercado Pago / Zoop)
→ 📄 Agent issues NFe (Nuvem Fiscal / Focus NFe / NFe.io)
→ 📦 Agent generates shipping label (Melhor Envio / Skydropx)
→ 📱 Agent sends tracking via WhatsApp (Z-API / WhatsApp Cloud)
→ 📊 Agent records in ERP (Omie / Bling / Tiny)
→ 🏦 Agent reconciles balance (Stark Bank / Itaú / BTG)Six systems. Zero human intervention. One agent.
Agentic Payment Protocols
Four servers for the emerging agentic payment stack:
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
Rede: common questions
- Is Rede MCP server safe?
- Mostly: it is graded B (82/100). Read the Rede safety report
- How do I install Rede?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does Rede need an API key?
- Yes. The registry entry asks for
REDE_TOKEN. - Is Rede maintained?
- The last commit was 67 days ago (2026-08-29). The latest release is v0.2.0-alpha.3.
- What can I use instead of Rede?
- Servers from other publishers that do the same job: Oauth Auditor MCP server, MCPProxy MCP server and Raziel MCP server.
- How does Rede compare with other Security MCP servers?
- safety score 82/100 (higher than 66% of 915 Security servers); tools 22 (the typical Security server has 6); tools that change things 32% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.
Alternatives to Rede
Same job from other publishers: the closest match first, then the best rated.
- Oauth AuditorScans MCP server auth code for OAuth 2.1 anti-patterns: token passthrough, missing audiencenot reviewedGrowingA
- MCPProxyLocal-first MCP proxy with BM25 tool discovery, security scanning, quarantine & ~99% token savingsnot reviewedGrowingB
- RazielMCP server teaching AI agents to implement TideCloak: auth, E2EE, IGA, security analysisnot reviewedGrowingA
- MyMedi-AIDME billing and medical coding: code lookup, DMEPOS fee schedules, Medicare prior-auth checksnot reviewedGrowingA
- Healthclaw GuardrailsGuardrailed FHIR access for AI agents: PHI redaction, audit trail, step-up auth, tenant isolationnot reviewedGrowingA