Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Knuckles-Team/jellyfin-mcp --skill jellyfin-kg-ingestiongit clone --depth 1 https://github.com/Knuckles-Team/jellyfin-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/knuckles-team/jellyfin-mcp/jellyfin-kg-ingestion)<a href="https://agentmods.dev/skills/knuckles-team/jellyfin-mcp/jellyfin-kg-ingestion"><img src="https://agentmods.dev/badge/skills/knuckles-team/jellyfin-mcp/jellyfin-kg-ingestion/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/knuckles-team/jellyfin-mcp/jellyfin-kg-ingestion"><img src="https://agentmods.dev/badge/skills/knuckles-team/jellyfin-mcp/jellyfin-kg-ingestion.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00158 | $0.01071 |
| Opus 5 | $0.00079 | $0.00535 |
| Sonnet 5 | $0.00032 | $0.00214 |
| Haiku 4.5 | $0.00016 | $0.00107 |
Grade A, and why
jellyfin-kg-ingestion scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Jellyfin Knowledge-Graph Ingestion
Native "maximum ingestion" of a Jellyfin library into the ONE epistemic-graph knowledge graph. Library items become typed OWL nodes; overviews become semantic-search documents; posters become deduped blobs — all best-effort and engine-guarded (no engine reachable ⇒ clean no-op).
When to use
- Make a Jellyfin catalog queryable in the KG (
jellyfin_ingest_library). - Refresh media nodes after library changes (re-run; ids are stable).
- Persist item artwork as durable blobs (
jellyfin_ingest_posters).
When NOT to use
- Interactive catalog browse/search →
jellyfin-library-catalog. - Streaming / playback control →
jellyfin-media-playback. - Server administration → the
jellyfin_systemtool.
Prerequisites & environment
Connect via the mcp-client skill against the jellyfin-mcp MCP server.
Ingestion additionally requires a reachable epistemic-graph engine (an
agent_utilities KG stack); with none present the tools return
{"ingested": null} and do nothing else.
| Variable | Required | Notes |
|---|---|---|
JELLYFIN_URL |
✅ | Base server URL |
JELLYFIN_API_KEY / JELLYFIN_TOKEN |
✅ | X-Emby-Token API key |
JELLYFIN_USER_ID |
optional | Default user_id for item reads |
Tools & actions
| Tool | Purpose |
|---|---|
jellyfin_ingest_library |
List items (get_items filters via params_json) → typed nodes + documents |
jellyfin_ingest_posters |
For given item_ids, fetch the primary image → :Blob + :MediaAsset |
KG mapping
- Item →
media:MediaAsset:<Id>(:Bookwhen the item Type is a book/audiobook), carryingitemKind,overview,productionYear,communityRating, … Genres[]→media:Genre:<slug>+:hasGenreedge.Artists[]→media:Artist:<slug>+:performedBy(or:Author+:authoredByfor books).- Item
Overview→media:Document:<Id>(:Document, embedded hub-side). - Node ids follow
media:<class>:<externalId>; provenancesource=jellyfin-mcp,domain=media.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 89 lines · 158 tokens per session scan A 755d9dd763c5
jellyfin-kg-ingestion is a skill published in the GitHub repository Knuckles-Team/jellyfin-mcp (3 stars, last pushed 14d ago), licensed MIT. It adds 158 tokens to every session and 1,071 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
archivebox-kg-ingestion
Natively ingest an ArchiveBox archive into the epistemic-graph knowledge graph via the archivebox-api MCP server — push snapshots as typed :Snapshot nodes (with :Tag + :hasTag links and per-snapshot :Document page-text) and archive results as :ArchiveResult nodes, best-effort, with the Wire-First ingest tools. Use…
audio-transcriber-knowledge-graph
Native knowledge-graph ingestion of Whisper transcripts on the audio-transcriber MCP server — transcribe an audio/video file and push it into the epistemic-graph in one call: the raw audio as a shared :MediaAsset blob, the transcript text as a :Document, and each Whisper segment as a :TranscriptSegment node linked…
searxng-kg-ingestion
Persist SearXNG search results into the epistemic-graph knowledge graph via the searxng-mcp MCP server. Use when the agent must turn a web search into durable, semantically-searchable KG memory — each result becomes a :Document (plus :SearchQuery and :SearchEngine typed nodes with :resultOf / :fromEngine links) so…
nextcloud-ingest
Natively ingest Nextcloud files into the epistemic-graph knowledge graph via the nextcloud-agent MCP server — fetch a file over WebDAV and store its raw bytes as a content-addressed :Blob/:AssetOccurrence plus its extracted text (pdf/office/txt or image OCR) as a linked :Document. Use when the agent must make a…
documentdb-collection-admin
Database, collection, and user administration on a DocumentDB (MongoDB-compatible, PostgreSQL-backed) server via the documentdb-mcp MCP server — list/create/drop/rename databases and collections, and manage database users and their roles. Use when the agent must provision or tear down namespaces, enumerate the…
documentdb-document-crud
Document create/read/update/delete operations on a DocumentDB (MongoDB-compatible, PostgreSQL-backed) collection via the documentdb-mcp MCP server — insert one/many, find with filter/sort/skip/limit, update/replace one/many, delete, count, and the atomic find-and-modify variants. Use when the agent must read or mutate…