Skip to main content
Glama

Azure AI Agent Service MCP Server

swagger.yaml11.9 kB
openapi: 3.0.3 info: title: Azure OpenAI Fine-tuning API version: 2024-02-01 description: | Complete API specification for Azure OpenAI fine-tuning operations. This spec covers all endpoints used in the MCP Foundry fine-tuning tools. contact: name: MCP Foundry Team servers: - url: '{azure_endpoint}' description: Azure OpenAI endpoint variables: azure_endpoint: default: https://your-resource.openai.azure.com description: Your Azure OpenAI resource endpoint security: - apiKey: [] paths: /openai/fine_tuning/jobs: get: operationId: listFineTuningJobs summary: List all fine-tuning jobs description: Retrieves a list of all fine-tuning jobs for your Azure OpenAI resource tags: - Fine-tuning Jobs parameters: - $ref: '#/components/parameters/ApiVersion' responses: '200': description: Successfully retrieved list of fine-tuning jobs content: application/json: schema: type: object properties: data: type: array items: $ref: '#/components/schemas/FineTuningJobSummary' has_more: type: boolean description: Whether there are more jobs to retrieve example: data: - id: "ftjob-abc123" status: "succeeded" created_at: 1234567890 model: "gpt-35-turbo" - id: "ftjob-def456" status: "running" created_at: 1234567891 model: "gpt-35-turbo" '401': $ref: '#/components/responses/UnauthorizedError' '500': $ref: '#/components/responses/InternalServerError' /openai/fine_tuning/jobs/{job_id}: get: operationId: getFineTuningJob summary: Get fine-tuning job details description: Retrieves detailed information about a specific fine-tuning job tags: - Fine-tuning Jobs parameters: - $ref: '#/components/parameters/JobId' - $ref: '#/components/parameters/ApiVersion' responses: '200': description: Successfully retrieved fine-tuning job details content: application/json: schema: $ref: '#/components/schemas/FineTuningJobDetail' example: id: "ftjob-abc123" status: "succeeded" model: "gpt-35-turbo" created_at: 1234567890 finished_at: 1234567900 fine_tuned_model: "gpt-35-turbo-ftjob-abc123" hyperparameters: n_epochs: 3 batch_size: 1 learning_rate_multiplier: 0.1 trained_tokens: 50000 result_files: - "file-result123" training_files: - "file-train123" validation_files: - "file-val123" '404': $ref: '#/components/responses/NotFoundError' '401': $ref: '#/components/responses/UnauthorizedError' /openai/fine_tuning/jobs/{job_id}/events: get: operationId: getFineTuningJobEvents summary: Get fine-tuning job events description: Retrieves all events for a specific fine-tuning job including progress updates and billing details tags: - Fine-tuning Jobs parameters: - $ref: '#/components/parameters/JobId' - $ref: '#/components/parameters/ApiVersion' - name: limit in: query schema: type: integer default: 20 description: Number of events to retrieve - name: after in: query schema: type: string description: Cursor for pagination responses: '200': description: Successfully retrieved job events content: application/json: schema: type: object properties: data: type: array items: $ref: '#/components/schemas/FineTuningEvent' has_more: type: boolean example: data: - created_at: 1234567890 message: "Fine-tuning job started" level: "info" - created_at: 1234567891 message: "Step 100/1000" level: "info" - created_at: 1234567900 message: "Fine-tuning job succeeded" level: "info" '404': $ref: '#/components/responses/NotFoundError' /openai/files/{file_id}/content: get: operationId: getFileContent summary: Get file content description: Downloads the content of a file, including training data or result metrics tags: - Files parameters: - $ref: '#/components/parameters/FileId' - $ref: '#/components/parameters/ApiVersion' responses: '200': description: Successfully retrieved file content content: text/plain: schema: type: string description: File content (JSONL for training files, CSV for result files) example: | {"messages": [{"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": "Hello"}, {"role": "assistant", "content": "Hi there!"}]} {"messages": [{"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": "How are you?"}, {"role": "assistant", "content": "I'm doing well, thank you!"}]} text/csv: schema: type: string description: CSV content for result files example: | step,train_loss,valid_loss,full_valid_loss,train_mean_token_accuracy,valid_mean_token_accuracy,full_valid_mean_token_accuracy 1,2.345,2.456,2.467,0.789,0.778,0.776 2,1.234,1.345,1.356,0.890,0.889,0.887 '404': $ref: '#/components/responses/NotFoundError' components: securitySchemes: apiKey: type: apiKey in: header name: api-key description: Azure OpenAI API key parameters: ApiVersion: name: api-version in: query required: true schema: type: string default: '2024-02-01' enum: - '2024-02-01' - '2023-12-01-preview' - '2023-10-01-preview' description: API version to use JobId: name: job_id in: path required: true schema: type: string pattern: '^ftjob-[a-zA-Z0-9]+$' description: The ID of the fine-tuning job example: ftjob-abc123 FileId: name: file_id in: path required: true schema: type: string pattern: '^file-[a-zA-Z0-9]+$' description: The ID of the file example: file-abc123 schemas: FineTuningJobSummary: type: object properties: id: type: string description: The fine-tuning job ID example: ftjob-abc123 status: type: string enum: - pending - running - succeeded - failed - cancelled description: Current status of the job created_at: type: integer description: Unix timestamp of job creation model: type: string description: Base model being fine-tuned example: gpt-35-turbo FineTuningJobDetail: type: object properties: id: type: string description: The fine-tuning job ID status: type: string enum: - pending - running - succeeded - failed - cancelled model: type: string description: Base model being fine-tuned created_at: type: integer description: Unix timestamp of job creation finished_at: type: integer nullable: true description: Unix timestamp of job completion fine_tuned_model: type: string nullable: true description: Name of the fine-tuned model (available after success) hyperparameters: type: object properties: n_epochs: type: integer description: Number of training epochs batch_size: type: integer description: Training batch size learning_rate_multiplier: type: number description: Learning rate multiplier trained_tokens: type: integer nullable: true description: Total number of tokens trained result_files: type: array items: type: string description: List of result file IDs training_files: type: array items: type: string description: List of training file IDs validation_files: type: array items: type: string description: List of validation file IDs estimated_finish: type: integer nullable: true description: Estimated completion time (Unix timestamp) error: type: object nullable: true properties: code: type: string message: type: string description: Error details if job failed FineTuningEvent: type: object properties: created_at: type: integer description: Unix timestamp of the event message: type: string description: Event message level: type: string enum: - info - warning - error description: Event severity level responses: UnauthorizedError: description: Authentication failed - invalid or missing API key content: application/json: schema: type: object properties: error: type: object properties: code: type: string example: "401" message: type: string example: "Unauthorized. Access token is missing, invalid, or expired." NotFoundError: description: The requested resource was not found content: application/json: schema: type: object properties: error: type: object properties: code: type: string example: "404" message: type: string example: "The requested resource was not found." InternalServerError: description: Internal server error content: application/json: schema: type: object properties: error: type: object properties: code: type: string example: "500" message: type: string example: "An internal server error occurred."

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/azure-ai-foundry/mcp-foundry'

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