API Testing MCP

Overview Schema Related Servers Score Discussions

api_endpoint_detail

Retrieve complete endpoint details including parameters, body schema, and responses. Use to determine the required data structure for any HTTP request.

Instructions

Muestra el detalle completo de un endpoint: parámetros, body schema, y respuestas. Útil para saber qué datos enviar.

Input Schema

TableJSON Schema

Name	Required	Description
`name`	No	Nombre del API importada. Si se omite y solo hay un spec, lo usa automáticamente
`method`	Yes	Método HTTP del endpoint
`path`	Yes	Path exacto del endpoint (ej: "/blog", "/auth/login")

Implementation Reference

src/tools/api-spec.ts:325-465 (registration)

Registration of the 'api_endpoint_detail' tool via server.tool(), including its Zod schema for parameters (name, method, path) and the handler function.

server.tool(
  'api_endpoint_detail',
  'Muestra el detalle completo de un endpoint: parámetros, body schema, y respuestas. Útil para saber qué datos enviar.',
  {
    name: z
      .string()
      .optional()
      .describe('Nombre del API importada. Si se omite y solo hay un spec, lo usa automáticamente'),
    method: z
      .enum(['GET', 'POST', 'PUT', 'PATCH', 'DELETE', 'HEAD', 'OPTIONS'])
      .describe('Método HTTP del endpoint'),
    path: z
      .string()
      .describe('Path exacto del endpoint (ej: "/blog", "/auth/login")'),
  },
  async (params) => {
    try {
      const resolved = await resolveSpecName(params.name, storage)
      if (resolved.error) {
        return {
          content: [{ type: 'text' as const, text: resolved.error }],
          isError: true,
        }
      }

      const resolvedName = resolved.name as string
      const spec = await storage.getSpec(resolvedName)
      if (!spec) {
        return {
          content: [
            {
              type: 'text' as const,
              text: `Error: API '${resolvedName}' no encontrada. Usa api_import para importarla primero.`,
            },
          ],
          isError: true,
        }
      }

      const endpoint = spec.endpoints.find(
        (ep) => ep.method === params.method && ep.path === params.path,
      )

      if (!endpoint) {
        // Try partial match
        const similar = spec.endpoints.filter((ep) =>
          ep.path.includes(params.path) || params.path.includes(ep.path),
        )

        const suggestion = similar.length > 0
          ? `\n\nEndpoints similares:\n${similar.map((ep) => `  ${ep.method} ${ep.path}`).join('\n')}`
          : ''

        return {
          content: [
            {
              type: 'text' as const,
              text: `Error: Endpoint ${params.method} ${params.path} no encontrado.${suggestion}`,
            },
          ],
          isError: true,
        }
      }

      // Build detailed output
      const sections: string[] = []

      // Header
      sections.push(`## ${endpoint.method} ${endpoint.path}`)
      if (endpoint.summary) sections.push(`**${endpoint.summary}**`)
      if (endpoint.description) sections.push(endpoint.description)
      if (endpoint.tags?.length) sections.push(`Tags: ${endpoint.tags.join(', ')}`)

      // Parameters
      if (endpoint.parameters?.length) {
        sections.push('')
        sections.push('### Parámetros')
        for (const param of endpoint.parameters) {
          const required = param.required ? ' (requerido)' : ' (opcional)'
          const type = param.schema?.type ?? 'string'
          const desc = param.description ? ` — ${param.description}` : ''
          sections.push(`- **${param.name}** [${param.in}] ${type}${required}${desc}`)
        }
      }

      // Request body
      if (endpoint.requestBody) {
        sections.push('')
        sections.push('### Body')
        const required = endpoint.requestBody.required ? ' (requerido)' : ' (opcional)'
        sections.push(`Body${required}`)

        if (endpoint.requestBody.content) {
          for (const [contentType, media] of Object.entries(endpoint.requestBody.content)) {
            sections.push(`\nContent-Type: ${contentType}`)
            if (media.schema) {
              sections.push('```json')
              sections.push(formatSchema(media.schema))
              sections.push('```')
            }
          }
        }
      }

      // Responses
      if (endpoint.responses) {
        sections.push('')
        sections.push('### Respuestas')
        for (const [status, resp] of Object.entries(endpoint.responses)) {
          const desc = resp.description ? ` — ${resp.description}` : ''
          sections.push(`\n**${status}**${desc}`)

          if (resp.content) {
            for (const [, media] of Object.entries(resp.content)) {
              if (media.schema) {
                sections.push('```json')
                sections.push(formatSchema(media.schema))
                sections.push('```')
              }
            }
          }
        }
      }

      return {
        content: [
          {
            type: 'text' as const,
            text: sections.join('\n'),
          },
        ],
      }
    } catch (error) {
      const message = error instanceof Error ? error.message : String(error)
      return {
        content: [{ type: 'text' as const, text: `Error: ${message}` }],
        isError: true,
      }
    }
  },
)

src/tools/api-spec.ts:340-464 (handler)

Handler function for api_endpoint_detail: resolves the spec name, finds the endpoint by method+path, builds detailed output with parameters, request body, and responses, and returns formatted text.

async (params) => {
  try {
    const resolved = await resolveSpecName(params.name, storage)
    if (resolved.error) {
      return {
        content: [{ type: 'text' as const, text: resolved.error }],
        isError: true,
      }
    }

    const resolvedName = resolved.name as string
    const spec = await storage.getSpec(resolvedName)
    if (!spec) {
      return {
        content: [
          {
            type: 'text' as const,
            text: `Error: API '${resolvedName}' no encontrada. Usa api_import para importarla primero.`,
          },
        ],
        isError: true,
      }
    }

    const endpoint = spec.endpoints.find(
      (ep) => ep.method === params.method && ep.path === params.path,
    )

    if (!endpoint) {
      // Try partial match
      const similar = spec.endpoints.filter((ep) =>
        ep.path.includes(params.path) || params.path.includes(ep.path),
      )

      const suggestion = similar.length > 0
        ? `\n\nEndpoints similares:\n${similar.map((ep) => `  ${ep.method} ${ep.path}`).join('\n')}`
        : ''

      return {
        content: [
          {
            type: 'text' as const,
            text: `Error: Endpoint ${params.method} ${params.path} no encontrado.${suggestion}`,
          },
        ],
        isError: true,
      }
    }

    // Build detailed output
    const sections: string[] = []

    // Header
    sections.push(`## ${endpoint.method} ${endpoint.path}`)
    if (endpoint.summary) sections.push(`**${endpoint.summary}**`)
    if (endpoint.description) sections.push(endpoint.description)
    if (endpoint.tags?.length) sections.push(`Tags: ${endpoint.tags.join(', ')}`)

    // Parameters
    if (endpoint.parameters?.length) {
      sections.push('')
      sections.push('### Parámetros')
      for (const param of endpoint.parameters) {
        const required = param.required ? ' (requerido)' : ' (opcional)'
        const type = param.schema?.type ?? 'string'
        const desc = param.description ? ` — ${param.description}` : ''
        sections.push(`- **${param.name}** [${param.in}] ${type}${required}${desc}`)
      }
    }

    // Request body
    if (endpoint.requestBody) {
      sections.push('')
      sections.push('### Body')
      const required = endpoint.requestBody.required ? ' (requerido)' : ' (opcional)'
      sections.push(`Body${required}`)

      if (endpoint.requestBody.content) {
        for (const [contentType, media] of Object.entries(endpoint.requestBody.content)) {
          sections.push(`\nContent-Type: ${contentType}`)
          if (media.schema) {
            sections.push('```json')
            sections.push(formatSchema(media.schema))
            sections.push('```')
          }
        }
      }
    }

    // Responses
    if (endpoint.responses) {
      sections.push('')
      sections.push('### Respuestas')
      for (const [status, resp] of Object.entries(endpoint.responses)) {
        const desc = resp.description ? ` — ${resp.description}` : ''
        sections.push(`\n**${status}**${desc}`)

        if (resp.content) {
          for (const [, media] of Object.entries(resp.content)) {
            if (media.schema) {
              sections.push('```json')
              sections.push(formatSchema(media.schema))
              sections.push('```')
            }
          }
        }
      }
    }

    return {
      content: [
        {
          type: 'text' as const,
          text: sections.join('\n'),
        },
      ],
    }
  } catch (error) {
    const message = error instanceof Error ? error.message : String(error)
    return {
      content: [{ type: 'text' as const, text: `Error: ${message}` }],
      isError: true,
    }
  }
},

src/tools/api-spec.ts:328-339 (schema)

Zod schema for api_endpoint_detail inputs: 'name' (optional string), 'method' (enum of HTTP methods), 'path' (string for exact endpoint path).

{
  name: z
    .string()
    .optional()
    .describe('Nombre del API importada. Si se omite y solo hay un spec, lo usa automáticamente'),
  method: z
    .enum(['GET', 'POST', 'PUT', 'PATCH', 'DELETE', 'HEAD', 'OPTIONS'])
    .describe('Método HTTP del endpoint'),
  path: z
    .string()
    .describe('Path exacto del endpoint (ej: "/blog", "/auth/login")'),
},

src/server.ts:65-65 (registration)
Registration call that wires registerApiSpecTools into the server, making api_endpoint_detail available.
```
registerApiSpecTools(server, storage)
```

src/tools/api-spec.ts:468-550 (helper)

formatSchema helper function used by the handler to generate human-readable JSON examples from schema definitions.

/**
 * Formatea un schema como ejemplo JSON legible.
 * Genera un ejemplo basado en los tipos y propiedades del schema.
 */
function formatSchema(schema: { type?: string; properties?: Record<string, unknown>; items?: unknown; required?: string[]; enum?: unknown[]; example?: unknown; format?: string; description?: string }, depth = 0): string {
  if (depth > 5) return '"..."'

  const indent = '  '.repeat(depth)
  const innerIndent = '  '.repeat(depth + 1)

  if (schema.example !== undefined) {
    return JSON.stringify(schema.example, null, 2)
      .split('\n')
      .map((line, i) => (i === 0 ? line : indent + line))
      .join('\n')
  }

  if (schema.enum) {
    return JSON.stringify(schema.enum[0])
  }

  if (schema.type === 'object' && schema.properties) {
    const props = Object.entries(schema.properties as Record<string, Record<string, unknown>>)
    if (props.length === 0) return '{}'

    const requiredFields = new Set(schema.required ?? [])
    const lines: string[] = ['{']

    for (const [key, prop] of props) {
      const isRequired = requiredFields.has(key)
      const comment = []
      if (prop.description) comment.push(prop.description as string)
      if (!isRequired) comment.push('opcional')
      const commentStr = comment.length > 0 ? ` // ${comment.join(' — ')}` : ''

      const value = formatSchema(prop as typeof schema, depth + 1)
      lines.push(`${innerIndent}"${key}": ${value},${commentStr}`)
    }

    lines.push(`${indent}}`)
    return lines.join('\n')
  }

  if (schema.type === 'array' && schema.items) {
    const itemValue = formatSchema(schema.items as typeof schema, depth + 1)
    return `[${itemValue}]`
  }

  // Primitive types
  switch (schema.type) {
    case 'string':
      if (schema.format === 'date-time') return '"2024-01-01T00:00:00Z"'
      if (schema.format === 'email') return '"user@example.com"'
      if (schema.format === 'uri' || schema.format === 'url') return '"https://example.com"'
      return '"string"'
    case 'number':
    case 'integer':
      return '0'
    case 'boolean':
      return 'true'
    default:
      return 'null'
  }
}

Tool Definition Quality

A3.8/5.0

Behavior3/5

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

No annotations are provided, so the description carries the full burden. It discloses that the tool returns parameters, body schema, and responses, which is adequate. However, it does not mention authentication requirements, rate limits, or any side effects beyond this read operation.

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

Conciseness5/5

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

The description is two sentences, each providing essential information without redundancy. It is well-structured and concise.

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 there is no output schema, the description adequately lists the components returned (parameters, body schema, responses). It is complete for a detail-viewing tool, though it could mention the response format or if it returns a JSON object.

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

Parameters3/5

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

Schema coverage is 100% with good descriptions for each parameter. The description adds no additional meaning beyond the schema, so baseline 3 is appropriate.

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 description clearly states that the tool shows complete details of an endpoint, including parameters, body schema, and responses. It is specific about the resource (endpoint) and the verb (show detail). It distinguishes from sibling 'api_endpoints' which likely lists endpoints.

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

Usage Guidelines3/5

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

The description says it's useful for knowing what data to send, implying when to use. However, it does not explicitly state when not to use or provide alternatives among siblings. The usage context is implied but not thoroughly clarified.

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

Install Server

Latest Blog Posts

Lightport: Open-Sourcing Glama's AI Gateway
By punkpeye on April 27, 2026.
open source
OpenAI
Tool Definition Quality Score (TDQS)
By punkpeye on April 3, 2026.
mcp
The Hackers Who Tracked My Sleep Cycle
By punkpeye on March 26, 2026.
security

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/cocaxcode/api-testing-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server