Remote MCP server to run your Atako AI agents: chat, projects, files, integrations and channels.
- Passed: Handshake
- Passed: Tools listed
- Passed: Updated recently
Median latency 132 ms · Last checked
Explore
Evidence for your next connection.
Independent measurements of remote MCP servers. Every observation has a timestamp.
Read-only probesMCP server · Code & DevOps
Open Finance API and MCP discovery for developers and AI agents building in Brazil.
2 failed · 8 not measured
Median of successful probes over 7 days
Share of countable probes over 30 days, including daily rollups. Auth challenges are excluded.
Tool definitions returned by this server
Independent monitoring
Responded
The server completed its last measured handshake. This is an observation, not a guarantee.
Last checked| Test area | Passed | Failed | Unmeasured |
|---|---|---|---|
ConnectionCan a client connect and discover tools? | 5 | 0 | 0 |
Reliability & speedDoes it respond consistently and quickly? | 0 | 0 | 4 |
Access & authenticationWhat is required to use this server? | 1 | 0 | 2 |
Tool qualityAre the tool definitions usable by an agent? | 4 | 0 | 0 |
Publisher identityCan the publisher be traced to its source? | 2 | 2 | 2 |
Unmeasured means there is not enough evidence to decide. How these checks work
Start using RPG Connecta
Choose your client, copy the configuration, then enable the server in your client’s MCP settings.
Run this command in your terminal, then restart Claude Code.
Claude Code
claude mcp add --transport http rpg-connecta https://www.rpgcapital.com.br/api/connecta/discovery-mcpCapabilities
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.
DiscoveredUse 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.
DiscoveredUse 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.
DiscoveredUse 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.
DiscoveredRecent measurements
| Checked | Result | Response | Tools |
|---|---|---|---|
| Connected | 927 ms | 4 |