Echosaw runs media intelligence analysis on audio, video, images and documents, returning transcripts, summaries, entities and events.
What you can do
Start analysis jobs from local files (audio, video, image, PDF, DOCX, TXT, Markdown, PPTX)
Start analysis jobs from public media or video platform URLs such as YouTube, Rumble or Vimeo
Check whether a job is queued, processing, completed or failed
Retrieve structured results: summaries, transcripts, detected entities, events and other intelligence outputs
Get a presigned download link for the original media of an already-analyzed job
When to use it
Useful when an assistant needs to turn recordings, videos, images or documents into transcripts and structured intelligence, or to analyze public video links without downloading them first. Suited to research, content review and media monitoring workflows.
Requirements
A remote endpoint at mcp.echosaw.com or the local npm package @echosaw/mcp-server over stdio. OAuth authentication is required, and an Echosaw API key is supplied through the ECHOSAW_API_KEY environment variable; ECHOSAW_API_URL can override the API base URL. Network access is needed to upload files and reach the service.
Before you install
Requires an Echosaw account and API key; keep ECHOSAW_API_KEY private. Uploading local files and submitting URLs sends that media to a third-party service for processing, so avoid confidential material unless permitted. Jobs consume the service's processing resources, and download links are presigned, so treat returned URLs as sensitive.
Connect the required credentials. They are stored privately and never shown on public pages.
Enable the server for the chats that should use its tools.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Use with an agent
Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.
Read https://sourceweft.com/mcp/com.echosaw%2Fmcp-server/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.
Start a NEW Echosaw analysis job by uploading a local audio, video, image, or document (PDF, DOCX, TXT, Markdown, PPTX) file from disk. This is an entry point that creates a job and begins processing — it does not fetch or re-download previously analyzed media (use echosaw_download_media for that). Returns a job ID (mediaId) used to track processing and retrieve results.
ParametersrubricfilePathrequiredmediaTyperequired
echosaw_analyze_media_url
Submit Media URL
Start a NEW Echosaw analysis job from a publicly accessible media URL or video platform URL (YouTube, Rumble, Vimeo, etc.). This is an entry point that creates a job and begins processing — it does not fetch previously analyzed media (use echosaw_download_media for that). Returns a job ID (mediaId) used to track processing and retrieve results.
ParametersurlrequiredrubricmediaTyperequired
echosaw_check_job_status
Check Job Status
Retrieve the current processing state of an Echosaw analysis job, including whether the job is queued, processing, completed, or failed.
ParametersmediaIdrequired
echosaw_get_analysis_results
Get Analysis Results
Retrieve structured analysis results generated by Echosaw for a completed job, including summaries, transcripts, detected entities, events, and other intelligence outputs.
ParametersmediaIdrequiredsection
echosaw_download_media
Download Source Media
Retrieve the original source media file of an already-analyzed job by generating a presigned download URL for it. This only fetches existing media identified by mediaId — it does not upload files or start any analysis (use echosaw_analyze_media or echosaw_analyze_media_url to begin an analysis). The URL is valid for 1 hour.
ParametersmediaIdrequired
Version history
2
v2.2.0LatestNov 4, 2026
v2.1.0Sep 16, 2026
Score
75%
75% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
Reached in the last 30 daysRequired25 pts
Auth declaredRequired10 pts
Tools listed15 pts
DescriptionRequired15 pts
Logo10 pts
Documentation15 pts
Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.
License10 pts
Declare a license in the repository or the registry entry.