Stellaris Teacher MCP
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Stellaris Teacher MCP explain how orbital habitats work in Stellaris"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Stellaris Teacher MCP
Personal MCP server by Ibrahim Sabri Örene for offline-first game knowledge retrieval. Zero runtime dependencies; Node.js 18+; stdio transport.
Capabilities
BM25-ranked knowledge search, page and section access, glossary lookup, UI-label mapping, learning paths, ingestion queues and optional timestamped video retrieval. stellaris_explain combines useful context for a teaching assistant.
node server.js
node test/smoke.jsRegister node /absolute/path/to/mcp-stellaris/server.js with your MCP client. Set STELLARIS_KB_DIR to the desired writable knowledge directory. Without it, storage defaults to a sibling .kb directory.
Related MCP server: loci-mcp
Build your own knowledge base
The public repository includes authored term mappings and source code, not a downloaded wiki or video corpus. An empty KB is expected on first run. Use stellaris_queue_add, stellaris_queue_next and stellaris_kb_add_page to ingest material you are permitted to use. Live HTTP access can be blocked by the wiki's browser challenge; the tool reports that limitation.
The original smoke test runs against a throwaway KB with synthetic examples. It does not use your personal corpus.
Stellaris and its wiki are third-party works. This repository is an independent tool and does not redistribute their article bodies or full video transcripts. Retrieved material retains its source rights and attribution. The project package declares MIT; see LICENSE.
Available Tools
16 toolsstellaris_explainA
ONE-CALL answer to "what does X mean?". Searches the knowledge base, returns a digest of the best-matching wiki page(s) plus glossary and related-page hits. Use this first for any Stellaris term, UI label, resource, job, ship part, crisis or mechanic.
Inputs: term (required), pages, maxChars.
stellaris_get_pageA
Fetch the full text of a wiki page from the local KB. Optionally narrow to one section by heading name.
Inputs: title (required), section, maxChars.
stellaris_glossaryA
Look up Stellaris slang and abbreviations (FE, AE, GC, ecum, naval cap, tall/wide, CG...). Explains community shorthand a new player will not know.
Inputs: term.
stellaris_kb_add_pageA
Store a wiki page into the local KB from raw wikitext. Call this right after fetching https://stellaris.paradoxwikis.com/index.php?title=&action=raw with WebFetch. The page becomes searchable instantly and offline.
Inputs: title (required), wikitext (required), aliases.
stellaris_kb_statsA
Knowledge base coverage: how many pages are downloaded, indexed tokens, and how many titles are still queued.
Inputs: no named parameters.
stellaris_learning_pathA
Ordered reading list for a topic. Use when teaching a beginner or when the user asks "where do I start / how do I learn X".
Inputs: path.
stellaris_live_fetchA
Attempt a live download of a wiki page. Usually returns blocked:true because of the site bot challenge; when it does, follow the returned workaround (WebFetch + stellaris_kb_add_page).
Inputs: title (required).
stellaris_outlineA
List the section headings of a page. Cheap way to see what a big page contains before reading it.
Inputs: title (required).
stellaris_queue_addB
Add titles to the download queue, optionally into a priority tier (1 = highest).
Inputs: titles (required), tier.
stellaris_queue_nextB
Get the next batch of wiki page titles that still need to be downloaded. Drives the crawling cron job.
Inputs: limit.
stellaris_readmeA
Read the MCP server README: architecture, the bot-challenge workaround, and the teaching contract for answering player questions.
Inputs: no named parameters.
stellaris_searchA
BM25 full-text search across every downloaded wiki page AND every video transcript chunk. Returns ranked titles with snippets, kind of source, and (for video) a timestamped deep link.
Inputs: query (required), kind, limit.
stellaris_ui_hintA
Map a UI label / tooltip / resource name seen in a screenshot to the wiki page that explains it. Call this when the user pastes a screenshot and you can read text off it.
Inputs: term (required).
stellaris_video_chaptersA
List the chapters of an ingested video with timestamps and deep links. Use to point a player at the right section of a long tutorial.
Inputs: video.
stellaris_video_searchA
Search the Stellaris video transcripts in the KB. Returns the spoken content with a deep link straight to that moment in the video (e.g. &t=6393s). Use when a player would rather watch an explanation, or when the wiki page is too dry.
Inputs: query (required), limit.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 16 tools
Most tools have clearly distinct roles (explain vs search vs glossary vs video_search), and descriptions explicitly steer between them. The main overlap is stellaris_search (which covers video too) versus stellaris_video_search, and stellaris_explain versus stellaris_search, but the descriptions differentiate them reasonably well.
All tools share the stellaris_ prefix and snake_case, which makes the set predictable. There is some mixing of verb-led (explain, search, get_page) and noun-led (glossary, outline, readme, learning_path) names, but the pattern remains readable.
16 tools is slightly on the heavy side but justified by the server's three concerns: KB querying, crawling/ingestion management, and teaching aids. Each tool earns its place, with no obvious filler.
The KB lifecycle is mostly covered: add, search, fetch, outline, related, stats, and queue management. Minor gaps exist around update/delete/re-index of stored pages, which agents can work around by re-adding content.
Related MCP Connectors
Private, multimodal knowledge store for agents: hybrid search with cited, provenance-backed results.
A search engine that learns from your grades. Store text, records, images or embeddings.
Search, read, cite, create, and safely update a user's private KeepFlash knowledge library.
Ingest, manage, and retrieve documents for RAG-powered AI applications
Related MCP Servers
- FlicenseAqualityCmaintenanceEnables LLM agents to search and retrieve a hybrid knowledge base of manuals, videos, PDFs, DOCX files and images through tools for hybrid BM25-plus-vector search with facet and tag filters, full document retrieval, semantically similar document lookup, and timestamped video transcript segments. It ships with an in-memory backend for instant local use and an identical Elasticsearch backend for production deployment over stdio or authenticated HTTP.5-
- FlicenseNot gradedqualityAmaintenanceEnables AI agents and MCP hosts to query locally indexed notes, docs, chat logs, and other files via hybrid vector/BM25 retrieval with section-level citations. Exposes tools, resources, and prompts for searching and asking over the indexed content.-
- FlicenseNot gradedqualityAmaintenanceEnables AI agents and MCP-compatible hosts to search, ask, and retrieve section-level citations from scattered local notes, docs, PDFs, Word files, web pages, org files, and chat logs using hybrid vector and BM25 retrieval.-
- FlicenseNot gradedqualityAmaintenanceEnables AI agents and MCP hosts to search and ask questions across a local hybrid-retrieval index of scattered notes, documents, PDFs, and chat logs, returning section-level citations and agent-usable tools, resources, and prompts.-