Credit score and analysis for people and companies: score, dossier, defaults, positive reports, Cent
Scored across 17 tools
Several credit tools overlap heavily, such as credito_dossie vs credito_relatorio_pf_completo, credito_relatorio_pf_mais vs credito_relatorio_pf_completo, and credito_score vs credito_risco_pj. The marketplace tool also blurs the server's identity by providing generic platform capabilities that overlap with connect and toolkit_info.
Most tool names use consistent snake_case, and the credit tools follow a clear 'credito_' prefix pattern. However, generic platform tools like marketplace, report_bug, show_version, and toolkit_info break the semantic verb_noun pattern, creating a minor inconsistency.
At 17 tools, the server is on the heavier side. The credit-specific subset (13 tools) is reasonably scoped, but the inclusion of non-domain tools (marketplace, report_bug, show_version, toolkit_info) inflates the count and makes it feel bloated for a credit-focused server.
The credit data domain is well covered, including negative records, positive reports, protests, SCR, score, risk, and credit limits. The only noticeable gaps are the absence of writing operations (e.g., update/delete) and the disconnect between the platform tools and the credit domain, but the core read-only workflows are thorough.
MCP.AI for IDE agents (Cursor, etc.): log in in the browser, copy the access token. Best: add it to this server's config as a header Authorization: Bearer <token> for a permanent, non-expiring connection. Or paste it here for a session-only login: call with { token: "" } after the user pastes, or with no args to get the link.
Inputs: token.
Returns connection status and URLs. When all providers are connected, returns authenticated:true and empty pending[]. When credentials are missing, returns connect_url for the toolkit and per-install URLs.
Inputs: no named parameters.
Detalhamento de negativações/pendências de um CPF ou CNPJ.
Inputs: CPF, CNPJ, completo.
Dossiê de crédito completo de um CPF ou CNPJ.
Inputs: CPF, CNPJ, completo.
Limite de crédito sugerido (positivo) de pessoa jurídica.
Inputs: CNPJ, completo.
Protestos em cartório (nacional) por CPF/CNPJ.
Inputs: CPF, CNPJ, completo.
Protestos em cartório de SP por CPF/CNPJ.
Inputs: CPF, CNPJ, completo.
Relatório de crédito completo (positivo) de pessoa física.
Inputs: CPF, completo.
Relatório de crédito (positivo, intermediário) de pessoa física.
Inputs: CPF, completo.
Risco de crédito (positivo) de pessoa jurídica.
Inputs: CNPJ, completo.
Score de crédito de um CPF ou CNPJ.
Inputs: CPF, CNPJ, completo.
Resumo do SCR do Banco Central (histórico de crédito) — exige autorização do titular.
Inputs: CPF, CNPJ, completo.
SCR detalhado do Banco Central — exige autorização do titular.
Inputs: CPF, CNPJ, completo.
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.
Inputs: limit, query, action, mcp_id, +19 more.
Report a bug, missing feature, or send feedback. Include the conversation array with recent messages for reproduction.
Inputs: message (required), context, conversation.
Show the current MCP platform and adapter versions.
Inputs: no named parameters.
Returns the current toolkit state: installed MCPs, their connection status, the accounts connected to each one, and how many catalog tools each exposes.
Inputs: no named parameters.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Full credit dossier of a person or company: registration data, risk score, and delinquencies. Platfo
Credit score and risk analysis of a person or company. Platform-hosted, no credentials, pay per quer
Delinquencies of a person or company: protests, lawsuits, recoveries, and other restrictions. Platfo
Consumer credit check from a CPF: registration data, score, delinquencies, and history. Platform-hos
Add one secure layer between your agents and this server.
