RPG Connecta MCP server
io.github.REYMANnN/rpg-connectaREYMANnNstreamable-httpv1.0.0Scanned
Open Finance API and MCP discovery for developers and AI agents building in Brazil.
4 tools: 4 change things.
- Reads private data · 0
- Reads text others write · 0
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
4 tools here change things. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the RPG Connecta MCP server can do
The RPG Connecta MCP server is published by the GitHub account REYMANnN. It has 4 tools. It can create or change data (4 tools: connecta_product_info, connecta_pricing, connecta_integration_options and connecta_getting_started), but cannot delete data. None of its tools only reads.
None of its tools reads private data, brings in text other people write, or sends data out.
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 14, 2026, version 1.0.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
4 tools
Changes things 4Claude Code: ask
connecta_getting_startedUse when the user wants to start building now.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Use when the user wants to start building now. Returns the ordered steps: 1) call the API with the public demo key (copy-paste curl), 2) get an own sandbox key via the agent device login (a human approves with Google, no form, no card), 3) build against sandbox data, 4) production: a human registers a card and activates production, then each end customer authorizes their bank. Lists exactly which steps an agent can do alone and which need a human. Takes no parameters. Read-only; it never creates keys or connections.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
connecta_integration_optionsUse when choosing HOW to integrate.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Use when choosing HOW to integrate. Returns each interface with its URL, auth and when to pick it: REST + OpenAPI 3.1 (backend apps, Bearer key), public demo key and keyless sandbox (try without signup), installable Agent Skill (coding agents), this public discovery MCP (product questions only, no auth) and the authenticated operational MCP (agents that read authorized accounts with an rpg_mcp_ token). Takes no parameters. Read-only. Use connecta_getting_started instead when the user wants the ordered steps to go live.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
connecta_pricingUse when the user asks how much RPG Connecta costs or how billing works.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Use when the user asks how much RPG Connecta costs or how billing works. Returns the canonical, machine-readable price: sandbox BRL 0; production BRL 9.99 per active bank connection per month; BRL 0 setup; BRL 0 monthly minimum; pay as you go, charged to a card on file. Also states what counts as a billable connection (an account that completed bank authorization; the same account reconnected in the same month counts once). Takes no parameters. Read-only. Prefer this over connecta_product_info whenever the question is only about price.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
connecta_product_infoUse FIRST when the user asks what RPG Connecta is or whether it fits their need (Brazilian bank data via Open Finance for apps, dashboards or AI agents).No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Use FIRST when the user asks what RPG Connecta is or whether it fits their need (Brazilian bank data via Open Finance for apps, dashboards or AI agents). Returns a JSON overview: one-line definition, target users, what it does and does NOT do, price summary and canonical links (docs, OpenAPI, pricing, agent guide). Takes no parameters. Read-only and public: it never reads, stores or returns customer bank data. For the exact price breakdown call connecta_pricing; for how to integrate call connecta_integration_options; for step-by-step setup call connecta_getting_started.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or untrusted-input or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write0
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 16, 2026, 14:22 UTC, unchanged since Nov 9, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 4
- Protocol version
- 2025-11-25
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 4 tools that change things (4 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://www.rpgcapital.com.br/api/connecta/discovery-mcp: tools/list returned 4 tools to an anonymous client, including connecta_product_info (write), connecta_pricing (write), connecta_integration_options (write), connecta_getting_started (write)
Posture changes
- Nov 9, 2026
- Tools that change things, listed without credentials: 0 to 4
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools4 changed.~4 changedView diff
- Changed:connecta_getting_startedChanges thingsdescriptionannotations
- Changed:connecta_integration_optionsChanges thingsdescriptionannotations
- Changed:connecta_pricingChanges thingsdescriptionannotations
- Changed:connecta_product_infoChanges thingsdescriptionannotations
PostureRemote posture changed. Tools that change things, listed without credentials: 0 -> 4.View diff
- Tools that change things, listed without credentials: 0 to 4
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http rpg-connecta https://www.rpgcapital.com.br/api/connecta/discovery-mcpclaude mcp add --transport http rpg-connecta https://www.rpgcapital.com.br/api/connecta/discovery-mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [],
"ask": [
"mcp__rpg-connecta__connecta_product_info",
"mcp__rpg-connecta__connecta_pricing",
"mcp__rpg-connecta__connecta_integration_options",
"mcp__rpg-connecta__connecta_getting_started"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as rpg-connecta. Review it before you use it.
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/io.github.REYMANnN/rpg-connecta/verify?hash=fb01f9e0fd1b47dc9f5755ec4518ac7e622fc217b97b141d0cfb6511d9f8d30f" | jq -e '.changed == false'Pinned hash fb01f9e0fd1b, from Nov 14, 2026, 16:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.REYMANnN/rpg-connecta/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.REYMANnN/rpg-connecta)Source: MCP Registry. Synced Nov 1, 2026, 15:17 UTC.
RPG Connecta MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the RPG Connecta MCP server safe?
- No scan can promise that. What its definitions show: 4 tools, 4 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the RPG Connecta MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the RPG Connecta MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the RPG Connecta MCP server have?
- 4 tools: 4 write. connecta_product_info, connecta_pricing, connecta_integration_options and connecta_getting_started.
Does the RPG Connecta MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the RPG Connecta MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the RPG Connecta MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 14, 2026. Every change is on this page and in its Atom feed.