Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@OnePlatform MCP Server search the OnePlatform docs for how to cancel a payment link"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Conecta un agente de código a la documentación de OnePlatform y a la OnePlatform API con sus propias claves, en QA por defecto.
Grupo | Herramientas | Claves |
Documentación |
| No |
Lectura | perfil, historial de saldo, consumo, comercios, links de pago, transacciones, facturas, envíos, sitios y avisos | Sí |
Escritura sin dinero |
| Sí |
La lista exacta está en tools.manifest.json y lo que nunca puede exponerse, en
denylist.json: administración, credenciales, webhooks y toda operación que cobre saldo, emita
documentos fiscales o mueva dinero.
Related MCP server: switch-trust-mcp
ONEPLATFORM_APP_KEY=ak-XXXX… ONEPLATFORM_USER_KEY=sk-XXXX… npx -y @oneplatformlabs/mcpVariable | Valor |
| Clave de aplicación ( |
| Clave de usuario ( |
|
|
Instalación por cliente: https://developer.1platform.pro/docs/saas/1platform-api/integrar-con-ia
node dist/cli.js --http sirve Streamable HTTP sin estado en POST /mcp y GET /healthz. Las claves llegan en
X-OnePlatform-App-Key y X-OnePlatform-User-Key en cada solicitud; el entorno lo fija ONEPLATFORM_ENV al arrancar.
Límites: 30 solicitudes por minuto por IP, 120 por par de claves y 256 KiB por cuerpo.
El despliegue alojado (contenedor junto al API, IP del cliente hacia el API) está pendiente de medir la cadena de proxies en el host real. Hasta entonces el transporte HTTP no escribe
X-Forwarded-Fory no debe exponerse.
Canjea las claves por los dos tokens una vez y los reutiliza hasta dos minutos antes de vencer; un canje fallido se recuerda 60 s.
Ante un 401 vuelve a canjear el token de usuario y, si sigue, el de aplicación (como mucho una vez por minuto). Un
429 no se reintenta.
Devuelve el cuerpo y el código de estado del API tal cual, marcados como datos no confiables, recortados a 100 KiB.
Quita bank_authorization de las transacciones y el token de los sitios.
Los parámetros de ruta se validan contra un patrón fijo: .., / o % se rechazan sin llamar a la red.
Ninguna clave ni token aparece en los registros.
npm ci
npm run fetch-openapi # copia del OpenAPI público (no se versiona)
npm run build-tools # regenera src/generated/tools.ts desde el manifiesto
npm test
npm run buildPublicar en npm lo decide el dueño del paquete: ningún flujo de CI publica.
Devuelve el contrato exacto de una operación de la OnePlatform API (método, ruta, parámetros, cuerpo, respuestas y códigos de error) a partir de su operationId. No necesita claves.
| Name | Required | Description | Default |
|---|---|---|---|
| operationId | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint and openWorldHint, but the description adds a genuinely new behavioral fact the annotations do not encode: "No necesita claves" (no authentication required). It also discloses the shape of what is returned, which is valuable for a read tool with no output schema. It does not cover failure behavior for an unknown operationId or any caching/rate-limit traits.
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 tight sentences, front-loaded with the returned content, then the auth constraint. No filler or redundancy.
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?
The enumeration of return fields compensates well for the absent output schema, but with 0% parameter documentation and no sibling differentiation, an agent still lacks guidance on where operationIds come from and how this differs from the two docs_* tools.
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 description coverage is 0% for the single required parameter, so the description must compensate. It only repeats that input is an "operationId" and adds no format, origin (e.g., from docs_search results), or validity guidance beyond the regex already in the schema.
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?
States a specific verb+resource ("Devuelve el contrato exacto de una operación de la OnePlatform API") and enumerates exactly what the contract contains: método, ruta, parámetros, cuerpo, respuestas y códigos de error. It does not, however, name or contrast the sibling tools (docs_search, docs_get_page), so an agent must infer the boundary itself.
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?
Usage is only implied: the tool is the one to call when you have an operationId and need the full API contract. There is no explicit when-to-use vs. when-not, and no mention of the sibling docs tools as alternatives or prerequisites (e.g., how to first obtain an operationId).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Devuelve una página de la documentación de OnePlatform en Markdown. Acepta la ruta de la página (por ejemplo /docs/saas/1platform-api/links-de-pago) o su URL. No necesita claves.
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes | Ruta o URL de la página en developer.1platform.pro. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds genuinely useful behavioral context on top: the payload is returned in Markdown and no credentials are needed, which tells the agent it can call it blind. What it does not say is what happens on a nonexistent path or whether content is paginated.
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?
Three short sentences: what it returns, what it accepts with an example, and the auth note. Front-loaded with the outcome and zero redundant text.
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 one-parameter read-only fetch with a fully documented schema and no output schema, the description covers return format (Markdown) and auth needs. Only error/not-found behavior is left unaddressed, a minor gap at this complexity level.
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% and the schema already says the parameter accepts a route or URL on developer.1platform.pro. The description nevertheless adds a concrete worked example path (/docs/saas/1platform-api/links-de-pago), which is the piece agents most often guess wrong, so it edges above the baseline 3.
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?
States a specific verb and resource: returns a OnePlatform documentation page in Markdown, which an agent can instantly tell apart from docs_search or api_get_operation. It does not explicitly name a sibling to contrast against, so it stops short of a 5.
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?
Usage is only implied by the name and by the note that no keys are required. There is no explicit guidance on when to use this versus docs_search (e.g. 'use this when you already have the path; use docs_search to find it'), and no exclusions or prerequisites beyond the auth note.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Busca en la documentación de OnePlatform para desarrolladores y devuelve las páginas más relevantes con su URL en Markdown. No necesita claves.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| query | Yes | Qué busca, en palabras (por ejemplo: «crear un link de pago»). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the readOnlyHint/openWorldHint annotations, the description discloses two useful behavioral facts: results come back as Markdown with URLs, and no API key is required. It does not mention ranking behavior, latency, or result-count behavior, keeping it short of a 5.
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 tight sentences with zero waste; the core purpose and return format are front-loaded, and the auth note is appended briefly at the end.
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 two-parameter read-only search tool with annotations present and no output schema, the description covers what it does, what it returns, and that no key is needed. The main gap is the undocumented `limit` parameter and any hint about result ordering or pagination.
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 50%: `query` is documented in the schema with an example, but `limit` has no description anywhere. The description's phrase 'las páginas más relevantes' hints at result selection but never explains the limit parameter, so it adds little over the schema baseline.
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?
States a specific verb (busca) and resource (documentación de OnePlatform para desarrolladores) plus the return shape: most relevant pages with their URL in Markdown. It implicitly separates itself from docs_get_page (fetch a specific page) and api_get_operation, but never names those siblings explicitly.
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?
There is no explicit when-to-use or when-not-to-use guidance, and no mention of when to prefer docs_get_page for full page content or api_get_operation for API references. The only contextual note is 'No necesita claves', which is an auth fact rather than usage routing.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.1.1api_get_operationdocs_get_pagedocs_searchScored across 3 tools
The three tools occupy clearly separate niches: free-text documentation search, direct documentation page retrieval by path/URL, and exact API operation contract lookup by operationId. Search vs. fetch is a well-understood pair, and the API-reference tool is a distinct resource entirely. No two tools could plausibly be confused for one another.
All names follow a strict {domain}_{action} snake_case pattern (docs_search, docs_get_page, api_get_operation), with clear domain prefixes distinguishing documentation from API concerns. Verb choice is consistent and readable throughout.
Three tools is a tight, purposeful surface with no redundancy, and each covers a genuinely different retrieval need. It sits at the low end of comfortable scope, leaving some room for additional reference operations, but nothing feels padded.
Documentation search, page fetch, and operation lookup cover the core reference workflow, but there is no way to enumerate or list available API operations, so api_get_operation depends entirely on the caller already knowing an operationId (or the docs surfacing it). No listing/browsing or discovery operation is a notable gap for an API-reference server.
Read-only search and Markdown pages from the OpenPlanr docs, for coding agents.
Gemmein docs, API reference, error explainers and a live integration check for coding agents.
A read-only verified record of agent-operable GTM tools: search, fetch, compare, track changes.
Verified, pay-per-use API tools for AI agents through one authenticated connection.
