The full upstream README, mirrored here for reference. Install config, tool schemas, adoption signals, and an original overview live on the Qencode listing page.
Model Context Protocol (MCP) server for the Qencode Transcoding API.
Connect any MCP-compatible AI client — Claude, Cursor, ChatGPT, Grok, Gemini — to your Qencode account and let it submit, monitor, and reason about transcoding jobs on your behalf.
Once your client is connected (see Connect a client), ask your agent in plain English:
Transcode
https://example.com/input.mp4as an HLS ladder at 1080/720/540/360. Put it in my R2 bucketvideos/demo/.
The agent picks the hls_abr recipe, fills in the per-rendition encoding params, submits via start_encode2_raw, and polls until the job is done.
There are no API keys to copy into client config — authentication is browser-based OAuth.
The connector uses standard OAuth 2.1 — no API keys in client config. On first use, your client opens a browser, you sign in to your Qencode portal account, pick a project, and approve the requested scopes. The client stores the token; subsequent calls are silent until the token expires.
Scopes the client should request at authorize time (published via Protected Resource Metadata):
| Scope | Purpose |
|---|---|
openid | OIDC identity |
profile | Display name |
email | Account email |
offline_access | Refresh token |
transcoding:read | get_job_status, list_jobs, docs tools |
transcoding:write | transcode_video, start_encode2_raw |
The RS enforces transcoding:read and transcoding:write on access tokens at the transport layer.
Your Qencode API keys never leave the portal. The MCP server derives a short-lived session token per request via an internal portal endpoint.
The same connector is deployed in two environments. Each has its own domains, accounts, projects, and credentials — sign in to the portal that matches the endpoint you connect to.
| Role | Production | QA (testing) |
|---|---|---|
| MCP endpoint (connect here) | https://mcp.qencode.com/mcp | https://mcp-qa.qencode.com/mcp |
| Portal (sign in / projects) | https://portal.qencode.com | https://portal-qa.qencode.com |
| Authorization server | https://auth.qencode.com | https://auth-qa.qencode.com |
| Qencode API | https://api.qencode.com | https://api-qa.qencode.com |
The instructions below use the production endpoint. To test against QA, swap in the QA URL and sign in at the QA portal.
Endpoint: https://mcp.qencode.com/mcp — same for every client below. Sign in to your Qencode account when the browser opens and approve access.
QA (internal testing): use
https://mcp-qa.qencode.com/mcpand sign in at the QA portal instead.
| Client | Where to add it | MCP URL / config |
|---|---|---|
| Claude (chat) | Message box → + → Connectors → Add connector | https://mcp.qencode.com/mcp |
| Claude Code | Terminal | claude mcp add --transport http qencode https://mcp.qencode.com/mcp |
| ChatGPT | Apps → search Qencode → Connect; or Developer Mode → Build app | Connector URL: https://mcp.qencode.com/mcp |
| Gemini | ~/.gemini/settings.json → mcpServers | "httpUrl": "https://mcp.qencode.com/mcp" — then /mcp auth qencode in the CLI |
| Cursor | Settings → Tools & MCP → New MCP Server (or ~/.cursor/mcp.json) | "url": "https://mcp.qencode.com/mcp" — restart Cursor after saving |
Cursor (mcp.json):
Gemini (settings.json):
Tip: sign in to portal.qencode.com in your browser before connecting — OAuth goes smoother.
Transcoding & jobs
| Tool | Description |
|---|---|
transcode_video | Submit a job from a source URL to one or more outputs. Convenience wrapper — auto-injects encoder_version: 2 (or 1 for VMAF) when omitted. |
start_encode2_raw | Escape hatch — submit a job with the full query JSON exactly as the Qencode API expects. |
get_job_status | One-shot status snapshot by task_token. |
get_job_status_detailed | Full, authoritative job status, including per-rendition progress and output details. |
list_jobs | Inline jobs card for the task_tokens of the current conversation — status badges, filters, expandable rows, output URLs. The card refreshes itself while any job is still running. |
fetch_job_result | Read the contents of a result file produced by an analysis job (transcript, VMAF report, metadata, categorization). |
wait_for_job | Deprecated. Returns immediately and points at list_jobs; kept so older conversations do not hit "tool not found". |
search_qencode_docs | Search the built-in knowledge base of recipes and reference docs. |
fetch_qencode_doc | Fetch the full content of a knowledge-base resource by qencode:// URI (tool-based counterpart to resources/read). |
Playback
| Tool | Description |
|---|---|
open_player | Render a playable result inline — progressive MP4/WebM or an HLS/DASH manifest. The server applies the calling host's sandbox policy, so which source origins are allowed depends on the client. |
refresh_jobs | The jobs card's own silent poll. Not meant to be called directly by an agent; it backs the card's auto-refresh and Refresh button. |
Media Storage
Bucket management and ingest for Qencode Media Storage. These ride the same OAuth grant as the transcoding tools — no extra scope and no re-consent.
| Tool | Description |
|---|---|
list_buckets | List the Media Storage buckets available to the account. |
create_bucket | Create a new bucket. Called only on an explicit request — not to satisfy a missing destination. |
list_objects | Browse the contents of a bucket. |
get_download_url | Return a time-limited download URL for an existing object. |
download_url_to_bucket | Server-side copy of a public URL into a bucket (ingest, no transcoding). |
The server ships a knowledge base of recipes and reference docs, exposed as MCP resources so the agent can fetch only what it needs. Notable URIs:
qencode://docs/best-practices — composition defaults the agent applies automaticallyqencode://docs/storage — destination compatibility matrix (Qencode S3, R2, AWS S3, Azure, B2, FTP/SFTP)qencode://docs/error-codes — error code → cause → fixqencode://docs/gotchas — non-obvious API quirksqencode://schema/digest — full attribute reference for start_encode2qencode://recipe/<slug> — one per feature flow: ai_detection, ai_upscaling, audio_outputs, callbacks, clip_trim, codec_av1, codec_lcevc, drm_aes128, drm_buydrm, drm_doverunner, drm_expressplay, drm_fairplay_ezdrm, drm_forensic_watermark, drm_playready_ezdrm, drm_widevine_ezdrm, hdr_to_sdr, hls_abr, incremental_abr, mp4_ladder, per_title_encoding, refresh_abr_playlist, reliability, repack, rotate_deinterlace, smart_crop, smart_thumbnail, speech_to_text, stitching, subtitles, thumbnails, video_intelligence, video_metadata, vmaf_quality, vr_360, vr_mode, watermark_logo, waveformUse search_qencode_docs to discover the right recipe URI for a goal.
In clients that surface MCP prompts, 40 one-shot templates are available. Each tells the agent to read the matching qencode://recipe/... resource and submit via start_encode2_raw.
ABR / packaging: encode_hls_abr, encode_dash_abr, encode_mp4_ladder, encode_incremental_rung, encode_refreshing_playlist, remux_repack
Codecs / quality: encode_av1, encode_lcevc, tune_per_title, check_vmaf, ai_upscale_video, convert_hdr_to_sdr
Audio / images / text: extract_audio, generate_thumbnails, generate_smart_thumbnails, generate_waveform, transcribe, add_subtitles
Editing / framing: trim_clip, rotate_video, deinterlace_video, enable_smart_crop, add_watermark, add_html_overlay
Immersive: enable_vr_mode, inject_360_metadata
Analysis: get_video_metadata, analyze_video, detect_ai_generated
Probe / stitch: stitch_videos
Production hooks: enable_callbacks, enable_reliability
DRM: encode_aes128_hls, encode_widevine_ezdrm, encode_playready_ezdrm, encode_fairplay_ezdrm, encode_drm_buydrm, encode_drm_expressplay, encode_drm_doverunner, encode_forensic_watermark
transcode_video and start_encode2_raw accept source values with schemes https://, http://, s3://, or tus:. FTP/SFTP and private/metadata URLs are rejected at the tool boundary (SSRF defence). See docs/security/THREAT_MODEL.md for limitations.
Authentication is OAuth 2.1 only — there is no static-API-key mode. Your Qencode API keys never leave the portal; the server derives a fresh, short-lived session token per request via an internal portal endpoint. Source URLs are validated at the tool boundary (SSRF defence — see Source URL rules).
Full threat model and adversarial test coverage: docs/security/THREAT_MODEL.md.
Protocol tests run fully offline (mocked Authorization Server, portal, and Qencode API). CI is the Jenkins job mcp_automated_tests (Jenkinsfile.manual): manual checkboxes for any layer, nightly L3 cron, weekly L4 cron.
Clients negotiate a version at initialize. This server targets MCP 2025-11-25 as the primary version. CI also runs conformance tests against 2025-06-18 because JSON-RPC batching behavior differs between earlier revisions. We do not claim support for 2025-03-26 or older wire semantics beyond what the underlying SDK negotiates.
| Version | Support | Notes |
|---|---|---|
| 2025-11-25 | Primary | Streamable HTTP, resumable SSE where used |
| 2025-06-18 | CI matrix | Regression guard for mid-2025 clients |
| 2025-03-26 | Not targeted | Batching semantics differ from 2025-06-18 |
The connector users install is the hosted endpoint above. For
Glama Servers / awesome-mcp-servers
scoring only, this repo also ships qencode-mcp-inspect (stdio, dummy env,
tools/call refused). That is not a supported client transport. See
docs/glama-release.md.
docs/local-development.mddocs/testing.md and tests/README.mdtests/integration/README.mdevals/README.mddocs/release-checklist.mdThe connector follows SemVer applied to the MCP surface — tools, prompts, resources, OAuth scopes, and supported protocol versions. Qencode HTTP API changes are out of scope (they are the API's own concern, not the connector's).
Surface changes are guarded by snapshot tests under tests/protocol/. When you change the surface, regenerate the snapshots (python scripts/regen_tools_snapshot.py) and bump the version in the same PR: pyproject.toml, src/qencode_mcp/__init__.py, server.json, and a new CHANGELOG.md entry must all agree.
CHANGELOG.mddocs/oauth-spec.md