MCP server for Botverse — video transcoding ($0.25/job) and document conversion
MCP server for Botverse — video transcoding ($0.25/job) and document conversion ($0.05/file) for AI agents. No AWS. npx -y botverse-mcp
active Production-safe Score 94/100 http no auth
At a glance
| Endpoint | https://botverse.cloud/mcp?token=bv_sess_ |
|---|---|
| Source | https://github.com/MkTurner74/botverse-mcp |
| Transport | http |
| Tools | 21 |
| Auth | none |
| First seen | 2026-07-08 19:03:22 |
| Last checked | 2026-11-17 21:55:54 |
Observed reliability
| 7-day uptime | 100% |
|---|---|
| 24-hour uptime | 100% |
| Handshake success | 100% |
| Latency p50 / p95 | 380 / 635 ms |
| Last successful check | 2026-11-17 21:55:54 |
Measured by Arclan's validator via repeated live MCP handshakes. How this is computed →
Tools (21)
get_upload_url— Get a presigned upload form for any file — video, audio, or document (markdown, HTML, DOCX, etc.). It expires in 15 minutes. This is a presitranscode_from_url— Offload a video or audio transcode to Botverse using a public URL — no upload step needed. Accepts a direct HTTPS download URL, or a share ltranscode_video— Offload a video transcode to Botverse — encoding runs server-side so you can continue with other tasks. Returns a job_id immediately. Sourcetranscode_content— Offload a video transcode by passing the file bytes inline as base64 — no upload step. Best in sandboxed agent environments that can't makeassemble_sequence— Assemble an ordered sequence of image frames (PNG/JPG) into a video — the 'render frames → movie' step. Give the frames as public HTTPS URLsconform_from_url— Mux a separate video file and audio file (both public HTTPS URLs) into one fresh-encoded output — the video/audio 'conform' step: combine twconform_media— Mux an already-uploaded video and audio file (both from get_upload_url) into one fresh-encoded output. Same conform methods and options as cconform_splice_from_url— Concatenate an ordered list of video and/or still-image segments (all public HTTPS URLs) into one continuous, fresh-encoded output — the vidconform_splice_media— Concatenate an ordered list of already-uploaded video and/or still-image segments (all from get_upload_url) into one continuous, fresh-encodget_job_status— Poll the status of a transcode or convert job. Call every 5 seconds until status is 'complete' or 'failed'. Status 'queued' or 'processing'get_download_url— Get a presigned HTTPS URL to download the completed output file. Call after get_job_status returns 'complete'. URL expires in 24 hours. NOTEget_output_content— Return the finished output of a completed job INLINE as base64 — no separate download. Use this in sandboxed agent environments (claude.ai,get_wallet_balance— Check the current prepaid wallet balance for this Botverse account. Use before large batch jobs to confirm sufficient funds. Submitting a joconvert_from_url— Offload a document conversion to Botverse — runs server-side in seconds, returns a download link, and frees you to continue with other tasksconvert_file— Offload a document conversion to Botverse using an already-uploaded file. Workflow: (1) call get_upload_url to get a presigned upload form,submit_workflow— Submit a multi-step workflow to the Botverse workflow engine. Steps execute in dependency order; parallel branches (multiple steps with theget_workflow_status— Get the current status of a workflow and all its steps. Each call may advance the workflow by dispatching steps whose dependencies have compcancel_workflow— Cancel an in-progress workflow. All queued and dispatched steps are marked CANCELLED. Completed steps are not reversed. You are only billedconvert_content— Convert a document inline — pass the content directly as a string (or base64 for binary inputs like .docx). PREFERRED route for documents, atranscribe_from_url— Transcribe a video or audio file from a public HTTPS URL into a speaker-labelled transcript — ONE call does everything. Source can be a diretranscribe_media— Transcribe an already-uploaded video/audio file (from get_upload_url) into a speaker-labelled transcript. Same one-call pipeline and options
Validation history
| Checked | Reachable | Handshake | Latency | Score | State |
|---|---|---|---|---|---|
| 2026-11-17 21:55:54 | ✓ | ✓ | 305 ms | 90 | active |
| 2026-11-17 21:40:40 | ✓ | ✓ | 227 ms | 94 | active |
| 2026-11-17 21:25:27 | ✓ | ✓ | 254 ms | 94 | active |
| 2026-11-17 21:10:18 | ✓ | ✓ | 407 ms | 90 | active |
| 2026-11-17 20:55:15 | ✓ | ✓ | 244 ms | 94 | active |
| 2026-11-17 20:40:11 | ✓ | ✓ | 300 ms | 90 | active |
| 2026-11-17 20:25:10 | ✓ | ✓ | 372 ms | 90 | active |
| 2026-11-17 20:09:55 | ✓ | ✓ | 259 ms | 94 | active |
| 2026-11-17 19:54:09 | ✓ | ✓ | 456 ms | 90 | active |
| 2026-11-17 19:39:06 | ✓ | ✓ | 252 ms | 94 | active |
| 2026-11-17 19:23:45 | ✓ | ✓ | 383 ms | 90 | active |
| 2026-11-17 19:08:37 | ✓ | ✓ | 396 ms | 90 | active |
| 2026-11-17 18:53:20 | ✓ | ✓ | 481 ms | 90 | active |
| 2026-11-17 18:38:18 | ✓ | ✓ | 407 ms | 90 | active |
| 2026-11-17 18:23:13 | ✓ | ✓ | 331 ms | 90 | active |
Query this programmatically
Agents can pull this record live over the MCP protocol or REST:
get_server("https://botverse.cloud/mcp?token=bv_sess_") # via the Arclan MCP endpoint https://arclan.ai/mcp
GET https://arclan.ai/api/registry/botverse-cloud-mcp-token-bv-sess # JSON