Banco MCP
Server Details
Brazilian Open Finance MCP — 30+ banks (Itaú, Nubank, etc.) to Claude/Cursor. Read-only.
- Status
- Healthy
- Last Tested
- Transport
- Streamable HTTP
- URL
- Repository
- douglac/banco-mcp
- GitHub Stars
- 0
Glama MCP Gateway
Connect through Glama MCP Gateway for full control over tool access and complete visibility into every call.
Full call logging
Every tool call is logged with complete inputs and outputs, so you can debug issues and audit what your agents are doing.
Tool access control
Enable or disable individual tools per connector, so you decide what your agents can and cannot do.
Managed credentials
Glama handles OAuth flows, token storage, and automatic rotation, so credentials never expire on your clients.
Usage analytics
See which tools your agents call, how often, and when, so you can understand usage patterns and catch anomalies.
Tool Definition Quality
Average 4.2/5 across 3 of 3 tools scored.
Each tool serves a distinct purpose: login authentication, bug reporting, and version display. There is no overlap or ambiguity between them.
All tools use a consistent verb_noun pattern in snake_case (authenticate, report_bug, show_version), creating a predictable naming convention.
With only 3 tools, the set is minimal but appropriate for a focused auxiliary server handling auth, feedback, and version info. Not over- or under-scoped for this limited purpose.
The server covers essential auxiliary functions (auth, feedback, version), but for a server named 'Banco MCP' that likely manages MCP itself, core operations like listing or managing servers/tools are absent, leaving notable gaps.
Available Tools
3 toolsauthenticateAIdempotentInspect
MCP.AI for IDE agents (Cursor, etc.): log in in the browser, copy the access token, paste here. Call with { token: "" } after the user pastes, or with no args to get the link.
| Name | Required | Description | Default |
|---|---|---|---|
| token | No | The Bearer JWT from the agent-auth page. Omit to get the login URL. |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations indicate idempotent and non-destructive. Description adds token handling flow but does not disclose whether token is cached or if side effects persist. Some behavioral gaps.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, front-loaded with key info, no wasted words. Highly efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema, description does not explain return values or success/failure states. Covers input usage but incomplete for a full agent decision.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Single parameter fully described in schema; description adds usage context (JWT from agent-auth page, omit for URL). Value beyond schema but not deeply detailed.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states it authenticates users via browser login and token paste. Distinguishes two modes: with token for auth, without for obtaining login link.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explains when to provide token vs omit it. Context of browser flow guides usage. No explicit alternatives, but siblings are unrelated, so no confusion.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
report_bugAIdempotentInspect
Report a bug, missing feature, or send feedback. Include the conversation array with recent messages for reproduction.
| Name | Required | Description | Default |
|---|---|---|---|
| context | No | Optional: tool name that failed, error message, or what the user was trying to do | |
| message | Yes | Free-text description of the bug, missing feature, or feedback | |
| conversation | No | JSON array of recent conversation messages leading to the bug. Each entry: {"role":"user"|"assistant"|"tool_call"|"tool_result", "content":"...", "tool_name":"..." (if tool_call/tool_result)}. Include the last 5-10 relevant turns. For tool_call, include tool name and args. For tool_result, include the response (truncated if large over 500 chars). | [] |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate idempotentHint=true and destructiveHint=false, so the description doesn't need to restate those. The description adds the context of including conversation for reproduction but provides no additional behavioral traits beyond what annotations convey.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single clear sentence that immediately conveys the tool's function and key instruction. No unnecessary words or redundancies.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a bug-reporting tool with three parameters and no output schema, the description is adequate. It specifies the purpose and a critical usage detail (include conversation). However, it could further explain the expected outcome or success/error responses.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with detailed descriptions for all three parameters. The description mentions including the conversation array, but this does not add meaning beyond the schema's existing detail on the 'conversation' parameter.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Report a bug, missing feature, or send feedback.' This specific verb and resource set distinctly differentiates it from sibling tools 'authenticate' and 'show_version'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides context for when to use the tool: when reporting bugs or feedback. It also advises including the conversation array for reproduction. While it doesn't explicitly say when not to use it, siblings are unrelated, making the guidance sufficient.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
show_versionARead-onlyIdempotentInspect
Show the current MCP platform and adapter versions.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already provide readOnlyHint, idempotentHint, and destructiveHint. The description adds specific context about what versions are shown (platform and adapter), adding value beyond annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single, clear sentence with no wasted words, front-loading the purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple, parameter-less tool with no output schema, the description sufficiently covers its functionality. It states exactly what versions are shown.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
There are no parameters, so the baseline is 4. The description does not need to add parameter details.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('Show') and clearly identifies the resource ('MCP platform and adapter versions'), distinguishing it from sibling tools like authenticate and report_bug.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for retrieving version info, but does not explicitly state when to use vs alternatives. However, given the tool's simplicity, it is clear enough.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Claim this connector by publishing a /.well-known/glama.json file on your server's domain with the following structure:
{
"$schema": "https://glama.ai/mcp/schemas/connector.json",
"maintainers": [{ "email": "your-email@example.com" }]
}The email address must match the email associated with your Glama account. Once published, Glama will automatically detect and verify the file within a few minutes.
Control your server's listing on Glama, including description and metadata
Access analytics and receive server usage reports
Get monitoring and health status updates for your server
Feature your server to boost visibility and reach more users
For users:
Full audit trail – every tool call is logged with inputs and outputs for compliance and debugging
Granular tool control – enable or disable individual tools per connector to limit what your AI agents can do
Centralized credential management – store and rotate API keys and OAuth tokens in one place
Change alerts – get notified when a connector changes its schema, adds or removes tools, or updates tool definitions, so nothing breaks silently
For server owners:
Proven adoption – public usage metrics on your listing show real-world traction and build trust with prospective users
Tool-level analytics – see which tools are being used most, helping you prioritize development and documentation
Direct user feedback – users can report issues and suggest improvements through the listing, giving you a channel you would not have otherwise
The connector status is unhealthy when Glama is unable to successfully connect to the server. This can happen for several reasons:
The server is experiencing an outage
The URL of the server is wrong
Credentials required to access the server are missing or invalid
If you are the owner of this MCP connector and would like to make modifications to the listing, including providing test credentials for accessing the server, please contact support@glama.ai.
Discussions
No comments yet. Be the first to start the discussion!