Aws Transcribe MCP server

Connect Aws Transcribe to Claude, ChatGPT, Cursor, Claude Code, Codex, Gemini, GitHub Copilot and any other MCP client, for your whole team. Metorial adds security, governance, and tracing, and gives everyone one Magic MCP URL to connect.

Deploy Aws TranscribeBook a demo

What you can do with the Aws Transcribe MCP server

Ask your agent in plain language. Each of these maps to a real tool on the server.

  • Use the get medical transcription job tool in Aws Transcribe
  • Use the delete transcription job tool in Aws Transcribe
  • Use the manage vocabulary tool in Aws Transcribe
  • Use the manage vocabulary filter tool in Aws Transcribe
  • Use the list call analytics jobs tool in Aws Transcribe
  • Use the start transcription job tool in Aws Transcribe

Supported Tools

get_medical_transcription_job

Get Medical Transcription Job

Retrieve status and details for a medical transcription job, including transcript URI, specialty, type, and failure details.

delete_transcription_job

Delete Transcription Job

Delete a transcription job and its associated metadata. The job must be in a terminal state (COMPLETED or FAILED) to be deleted. This does not delete the transcript output from S3.

manage_vocabulary

Manage Vocabulary

Create, update, get, delete, or list custom vocabularies. Custom vocabularies improve transcription accuracy for domain-specific words like product names, technical terms, or proper nouns. Provide terms as a list of phrases or via an S3 file.

manage_vocabulary_filter

Manage Vocabulary Filter

Create, update, get, delete, or list vocabulary filters. Vocabulary filters specify words to remove, mask, or tag in transcripts — commonly used for removing profanity or unwanted words. Provide filter words as a list or via an S3 file.

list_call_analytics_jobs

List Call Analytics Jobs

List Call Analytics jobs in your AWS account. Filter by job status or job name and paginate through results.

start_transcription_job

Start Transcription Job

Start a batch transcription job to convert speech from an audio or video file stored in Amazon S3 to text. Supports features like speaker diarization, channel identification, custom vocabularies, PII redaction, subtitle generation, and toxicity detection. The job runs asynchronously; use **Get Transcription Job** to check status and retrieve results.

delete_medical_transcription_job

Delete Medical Transcription Job

Delete a medical transcription job and its metadata. This does not delete transcript output stored in S3.

list_language_models

List Language Models

List custom language models in your AWS account. Filter by status or name to find specific models. Custom language models improve transcription accuracy for specific domains by training on your text data.

delete_call_analytics_job

Delete Call Analytics Job

Delete a Call Analytics job and its metadata. This does not delete transcript output stored in S3.

start_medical_transcription_job

Start Medical Transcription Job

Start a medical transcription job to convert medical speech to text. Incorporates medical terminology for use cases like transcribing doctor-patient dialogue, physician notes, and dictation. Supports speaker diarization and channel identification for multi-party conversations.

list_transcription_jobs

List Transcription Jobs

List transcription jobs in your AWS account. Filter by status or job name to find specific jobs. Returns summaries with job names, statuses, creation times, and language codes. Supports pagination for large result sets.

manage_medical_vocabulary

Manage Medical Vocabulary

Create, update, get, delete, or list custom medical vocabularies for Amazon Transcribe Medical. Medical vocabularies use a vocabulary table file stored in S3 or an accessible URI.

get_transcription_job

Get Transcription Job

Retrieve the status and details of a transcription job including its transcript output URI, language, settings, and completion time. Use this to check if a job has completed and to get the transcript location.

start_call_analytics_job

Start Call Analytics Job

Start a Call Analytics transcription job that processes call center audio to extract insights like sentiment, call categories, characteristics, and AI-powered summaries. Designed for two-channel audio where agent and customer are on separate channels. Can also redact PII from both transcripts and source audio.

manage_call_analytics_category

Manage Call Analytics Category

Create, update, get, delete, or list Call Analytics categories. Categories define rule-based labels that AWS applies to Call Analytics jobs created after the category exists.

list_medical_transcription_jobs

List Medical Transcription Jobs

List medical transcription jobs in your AWS account. Filter by status or job name and paginate through results.

get_call_analytics_job

Get Call Analytics Job

Retrieve the status and details of a Call Analytics job including transcript URIs, channel definitions, completion time, and failure reason. Use this to check if a call analytics job has completed and to get the results location.

Connect Aws Transcribe to your AI client

Every client uses the same Magic MCP URL, and so does any other MCP client. Add it once and sign in with SSO.

  1. Enable Aws Transcribe in Metorial. In your Metorial portal, enable the Aws Transcribe MCP server and sign in with the account that owns the data. Access stays governed by your team policies.
  2. Add a custom connector. Open Customize, then Connectors. Select Add, then Custom, then Web.
  3. Paste your Metorial MCP URL. Name it Metorial, paste your Magic MCP URL (<your-magic-mcp-url>) and continue.
  4. Sign in. Select Add and sign in to load Aws Transcribe tools.

Run Aws Transcribe through the Metorial gateway

One governed layer for every app your agents reach, not a separate connector per tool.

  • Give Aws Transcribe and every other app to your whole team through one MCP gateway, behind your SSO.
  • Scope which teams and agents can use Aws Transcribe tools with role-based access control, and trace every call.
  • Prefer to run it yourself? Metorial is open source and self-hostable.

More integrations teams use with Aws Transcribe

GitHub

Manage repositories, issues, and pull requests. Create and configure branches, star repositories, review code, and merge changes. Automate CI/CD workflows with GitHub Actions, manage workflow runs, secrets, and artifacts. Track issues with labels, milestones, and assignees. Search across code, repositories, issues, and users. Manage organizations, teams, and memberships. Create and manage projects, gists, packages, deployments, and environments. Access security alerts including code scanning, secret scanning, and Dependabot alerts. Read and write file contents in repositories. Manage webhooks, notifications, and codespaces.

Salesforce

Manage CRM data including Accounts, Contacts, Leads, Opportunities, Cases, and custom objects. Create, read, update, and delete records. Query data using SOQL and search across objects using SOSL. Perform bulk data operations for large-scale imports, exports, and migrations. Execute composite requests to batch multiple operations in a single API call. Access analytics, reports, and dashboards. Manage files and attachments associated with records. Interact with Chatter feeds, posts, and groups for social collaboration. Manage org metadata including custom objects, fields, layouts, and workflows. Query data using GraphQL for precise data retrieval across related objects.

Sharepoint

Manage SharePoint sites, document libraries, lists, and files. Create, read, update, and delete lists and list items with custom columns. Resolve site users to numeric Person/Group LookupId values. Upload, download, move, copy, and version files in document libraries. Search across sites, files, folders, lists, and list items using Microsoft Search. Manage permissions at site, list, and item levels with granular access control. Define and manage content types and site columns. Retrieve site properties and search for sites across Microsoft 365.

Airtable

Create, read, update, and delete records in Airtable bases and tables. Manage base schemas including creating tables and fields. Filter records using formulas, sort by fields, and scope queries to specific views. Upsert records to find, create, or update in a single call. Upload attachments to records, read and write record comments, list accessible bases, and receive real-time base change events through webhooks.

Sentry

Track, manage, and resolve application errors and performance issues. List, query, and bulk-update issues and error events with filters like status, assignment, and tags. Create and manage releases, associate commits, and upload source maps. Configure issue alert rules and metric alert rules with notification actions. Set up cron monitors to detect missed or failed scheduled jobs. Build custom dashboards with configurable widgets. Run ad-hoc Discover queries across errors and transactions for performance analysis. Manage organizations, teams, projects, and members. Provision users via SCIM. Access session replay data.

Bitbucket

Manage Git repositories, pull requests, and CI/CD pipelines on Bitbucket Cloud. Create, fork, and configure repositories within workspaces and projects. Create, review, approve, merge, and decline pull requests with inline code comments. Browse source code, list commits, and manage branches and tags. Trigger, monitor, and manage Bitbucket Pipelines. List workspace members, configure repository default reviewers and branch restrictions, create and manage repository webhooks, and search code across repositories.

Technical notes for Aws Transcribe

Transcribe speech to text from audio and video files or real-time audio streams. Perform batch transcription of media files stored in S3 and streaming transcription of live audio. Automatically identify languages, apply custom vocabularies and language models, filter unwanted words, identify speakers (diarization), and transcribe multi-channel audio. Redact personally identifiable information (PII) from transcripts. Generate subtitles in WebVTT and SRT formats. Detect toxic speech content. Analyze call center audio to extract sentiment, call categories, and AI-powered summaries. Transcribe medical dictation and patient-clinician conversations. Generate clinical notes from healthcare conversations using AWS HealthScribe. Monitor transcription job state changes, language identification events, and vocabulary updates via EventBridge.

Frequently asked questions

Common questions about connecting Aws Transcribe to AI agents with Metorial.

  1. How many tools does the Aws Transcribe MCP server have?
    The Aws Transcribe MCP server exposes 17 tools, including Get Medical Transcription Job, Delete Transcription Job, Manage Vocabulary. Each one is governed and traced through Metorial.
  2. Aws Transcribe exposes tools your agents call on demand; it does not publish event triggers yet. Everything still runs through one governed MCP URL.
  3. Any MCP client, including VS Code, Windsurf, Zed, OpenCode and Grok. Each one reaches the Aws Transcribe MCP server through the same Metorial URL.
  4. Use role-based access control to decide which teams, users, and agents can use Aws Transcribe and which of its tools they can call.
  5. Yes. Metorial is open source, so you can run the Aws Transcribe MCP server yourself or use the hosted gateway.

Connect Aws Transcribe to production AI agents

See how Metorial gives your team governed access to Aws Transcribe, with tracing and security controls built in.

Book a demoDeploy Aws Transcribe