Skip to main content
Glama

BTGPactual MCP

by io.github.mcp-dir

marketplace

The official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them. Covers capability requests like "find an MCP that does X", "consulta um CPF", "is there a tool for Y". Core flow: action=search discovers MCPs by intent → describe returns one MCP's full profile (every tool with its id + params, pricing, auth) so you pick the right tool_id → invoke RUNS that tool. KEY: invoke works even when the MCP is NOT installed — it runs the tool pontualmente (one-off), without adding the MCP to the toolkit and without bloating the tool list. If the MCP needs a credential/login, invoke returns a connect link; if it is paid and the wallet is empty, invoke returns a checkout/top-up link (the user opens it, then you retry). Use install only to make an MCP PERMANENT in the active toolkit (its tools then show up natively in future sessions); prefer invoke for a single/occasional use. list_tools lists what is callable right now. subscribe/cancel handle per-MCP billing; report_bug sends feedback; request_mcp asks us to build a NEW MCP when nothing fits. Search/describe flag installed_in_toolkit vs installed_in_workspace. Writes (install/uninstall/subscribe/cancel and the one-off install behind invoke) require workspace owner/admin. It also carries the mcp.ai PROMPT LIBRARY, which is about ready-made prompt TEXT rather than MCPs: search_prompts finds one, get_prompt returns its full text with {{variables}} filled, and publish_prompt saves a prompt and returns a shareable mcp.ai/p/ link that opens without login.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNo
queryNo
actionNosearch
mcp_idNo
messageNo
tool_idNo
argumentsNo{}
immediateNo
tier_slugNo
prompt_bodyNo
prompt_slugNo
prompt_toolNo
prompt_varsNo{}
conversationNo[]
prompt_titleNo
request_nameNo
cancel_reasonNo
cancel_commentNo
prompt_targetsNo
report_contextNo
prompt_categoryNo
request_detailsNo
prompt_descriptionNo

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Added
  2. Removed
  3. Added
  4. Removed
  5. Added
  6. Removed
  7. Added
  8. Removed
  9. Added
  10. Removed
  11. Added
  12. Removed
  13. Changed9 schema fields changed
    • changedInput schema / properties / action / enum
      Previous value: -[
-  "search",
-  "describe",
-  "install",
-  "uninstall",
-  "subscribe",
-  "cancel",
-  "resume",
-  "report_bug",
-  "request_mcp",
-  "list_tools",
-  "invoke"
-]New value: +[
+  "search",
+  "describe",
+  "install",
+  "uninstall",
+  "subscribe",
+  "cancel",
+  "resume",
+  "report_bug",
+  "request_mcp",
+  "list_tools",
+  "invoke",
+  "search_prompts",
+  "get_prompt",
+  "publish_prompt"
+]
    • addedInput schema / properties / prompt_body
      Added value: +{
+  "default": "",
+  "type": "string"
+}
    • addedInput schema / properties / prompt_category
      Added value: +{
+  "default": "",
+  "type": "string"
+}
    • addedInput schema / properties / prompt_description
      Added value: +{
+  "default": "",
+  "type": "string"
+}
    • addedInput schema / properties / prompt_slug
      Added value: +{
+  "default": "",
+  "type": "string"
+}
    • addedInput schema / properties / prompt_targets
      Added value: +{
+  "default": [],
+  "items": {
+    "enum": [
+      "claude",
+      "chatgpt",
+      "cursor",
+      "lovable"
+    ],
+    "type": "string"
+  },
+  "type": "array"
+}
    • addedInput schema / properties / prompt_title
      Added value: +{
+  "default": "",
+  "type": "string"
+}
    • addedInput schema / properties / prompt_tool
      Added value: +{
+  "default": "",
+  "type": "string"
+}
    • addedInput schema / properties / prompt_vars
      Added value: +{
+  "default": "{}",
+  "type": "string"
+}
  14. Changed1 schema field changed
    • changedInput schema / properties / action / enum
      Previous value: -[
-  "search",
-  "describe",
-  "install",
-  "uninstall",
-  "subscribe",
-  "cancel",
-  "report_bug",
-  "request_mcp",
-  "list_tools",
-  "invoke"
-]New value: +[
+  "search",
+  "describe",
+  "install",
+  "uninstall",
+  "subscribe",
+  "cancel",
+  "resume",
+  "report_bug",
+  "request_mcp",
+  "list_tools",
+  "invoke"
+]
  15. Changed2 schema fields changed
    • addedInput schema / properties / cancel_comment
      Added value: +{
+  "default": "",
+  "type": "string"
+}
    • addedInput schema / properties / cancel_reason
      Added value: +{
+  "enum": [
+    "too_expensive",
+    "missing_features",
+    "switched_service",
+    "unused",
+    "customer_service",
+    "too_complex",
+    "low_quality",
+    "other"
+  ],
+  "type": "string"
+}
  16. Added
  17. Removed
  18. First observed

TDQS

A4.4/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only provide booleans (readOnlyHint=false, openWorldHint=true, idempotentHint=false, destructiveHint=false). The description adds crucial non-obvious behavior: invoke runs tools one-off without installing or bloating the tool list, returns connect/checkout links when credentials/payment are needed, writes require owner/admin, and published prompt links open without login. No contradictions with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long but front-loaded with the core purpose and flow, and every sentence carries a distinct piece of guidance (one-off invoke, install permanence, permission requirements, prompt library). It lacks visual structure such as bullets or sections, making the dense multi-action behavior harder to scan, but it does not waste words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (14 actions, 23 params, no output schema), the description covers most behavioral surfaces: search/describe/invoke flow, one-off vs. permanent install, billing verbs, reporting, requesting new MCPs, prompt library, installed flags, and auth/payment retry behavior. Gaps remain around response formats and exact input combinations for each action, so it is not fully complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema description coverage and 23 parameters, the description needed to map action values to their required parameters, but it only mentions action and tool_id in passing. It does not clarify mcp_id, arguments, limit, query, tier_slug, prompt_* fields, cancel_reason, or how these combine with each action. The action-enum behavior is covered, but the rest of the parameter surface remains opaque.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The opening sentence clearly names the resource ('official mcp.ai marketplace') and its dual role: catalog of every MCP/tool and the way to run them. It distinguishes itself from sibling openfinance/authenticate tools by positioning as the in-platform catalog and execution layer, and it enumerates the full action vocabulary.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly maps a core flow (search → describe → invoke), tells when to prefer invoke over install ('prefer invoke for a single/occasional use'), and names alternatives for billing (subscribe/cancel), feedback (report_bug), new-build requests (request_mcp), and prompt-library operations. It also states that writes require workspace owner/admin, giving clear when-to-use vs. when-not context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All BTGPactual MCP toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.9/5.0
Disambiguation4/5

The openfinance_* family is well-decomposed by resource (accounts, transactions, bills, investments, loans, connections) and by action (list, get, update, sync, disconnect), and the highly detailed descriptions make each tool's boundaries clear. A few pairs can be confused at a glance (list_accounts vs. get_account_balance, list_transactions vs. list_transactions_by_item, connect vs. toolkit_info), but the semantics are ultimately distinguishable.

Naming Consistency3/5

The openfinance_* group follows a strong and consistent verb_noun pattern (list_transactions, get_item_status, force_sync). However, the platform-level tools are a mixed bag—authenticate, connect, marketplace, toolkit_info, show_version, report_bug—so there is no single predictable naming scheme across the whole server.

Tool Count3/5

At 25 tools, the server is at the heavy/borderline boundary, though most of the surface area is genuinely needed for Open Finance reads and connection lifecycle management. Some functions overlap (list_accounts returns balances that get_account_balance also exposes), making the set feel slightly bloated and closer to a two-in-one platform (Open Finance + marketplace).

Completeness4/5

The server covers the full Open Finance discovery and connectivity lifecycle: search, reconnect, force sync, provider health, accounts, transactions, credit cards, investments, loans, and category correction. Gaps like initiating a new connection or executing financial movements are handled through connect URLs rather than direct tools, so the unavoidable dead-end is likely workable and the core read/aggregate domain is well covered.

Resources