-
Notifications
You must be signed in to change notification settings - Fork 0
FAQ
Not with the default settings. Embeddings are computed locally on your CPU, and the database is inside
the same container. The only outbound requests a default installation makes are the one-time model
download (which EMBEDDING_OFFLINE=1 removes) and, if you configure them, fetches from your git host or
Notion. Switching to OpenAI embeddings does send document text to OpenAI — that is an explicit choice.
No. It is optional. See Embedding Models.
No. Embedding runs on the CPU.
No. It ships inside the container, listening only on the container's loopback interface.
Markdown (.md), MDX (.mdx) and, if you enable it per source, plain text (.txt). PDFs, Office
documents and images are not indexed.
Yes — that is the point. A local folder, two git repositories, an upload and a Notion workspace can all feed one endpoint. Each source is mounted under its own name, which becomes the first path segment of its documents. See Document Sources.
No, by design. Projects are isolated end to end. If two bodies of documentation belong to the same question, make them two sources of one project instead.
No. All three tools are read-only. Contextator never writes to a local directory or pushes to a repository.
No — it is unauthenticated by design, because MCP clients have no interoperable way to carry
credentials. Keep the port private or put authentication in front of it. ADMIN_TOKEN protects the
dashboard and the API, not /mcp/*. See Security.
Yes. The default model covers 50+ languages including Turkish, and matches across them — a Turkish question can find an English paragraph.
When you ask it to: the dashboard button, the API, or a push webhook. Indexing is incremental, so frequent runs are cheap. Notion has no push webhook, so a scheduled API call is the way there.
No. Files are hashed; unchanged files are skipped. Only Force re-index, or a change of embedding model, rebuilds everything.
There is no hard limit. Search stays fast into the tens of thousands of chunks thanks to the HNSW index; the first index run is the expensive part. Separate unrelated knowledge into separate projects for better retrieval, not for capacity.
Yes, as many as you like. They share one indexing queue — one project is indexed at a time — but serving searches is concurrent.
That source reports its own error and the others still index. A source whose content could not be read keeps the documents it had already contributed; a failure never empties a source.
No — HTTPS with an access token only. See Git Repository Source.
No. The name is the prefix of every document path it contributes. Delete the source and add it again with the new name (which re-indexes it).
Files that Contextator materialised (git checkouts, uploads, Notion pulls) are deleted. Your own
documentation is untouched: /docs is mounted read-only and local sources are scanned in place.
Yes — disable response buffering and set PUBLIC_BASE_URL. See
Installation.
Yes, and anything else that speaks MCP. Both MCP transports are served on the same URL, so old and new clients both work without configuration. See Connecting AI Clients.
Every search result carries a file path and a heading breadcrumb, and the server instructs agents to
cite the file path they used. read_document returns the file so you can check it.
In the contextator-data volume, under the source's directory. For upload sources that is the only
copy — include the volume in your backups. See Backup and Data.
git pull && docker compose up -d --build. The schema updates itself at startup; there is no migration
command. Data lives in volumes and is kept.
GNU Affero General Public License, version 3 or later. The full text ships as LICENSE and every
running instance serves it at /license.txt; the /license page of your own dashboard summarises it.
It was MIT before 2026-09-18. The AGPL was chosen because Contextator is a server: a plain GPL would let someone fork it, host it as a service and never publish their changes. Section 13 of the AGPL closes that gap.
Yes to both, and for most people nothing is required in return:
| What you are doing | What the licence asks |
|---|---|
| Running Contextator as it ships — for yourself, your team, your whole company | Nothing. Internal use is simply use |
| Changing it and keeping the change to yourself | Nothing, as long as nobody outside uses that version over a network |
| Changing it and letting other people reach your version over a network | Offer those users the complete source of what you run, under the AGPL |
| Redistributing it — as a repository, an image, or inside a product | Ship the source of your version, under the AGPL |
| Indexing your own documents with it | Nothing. Your documents are yours; the licence covers Contextator's code, and an agent that queries /mcp/… does not inherit it |
If your organisation forbids AGPL software by policy, or you need to ship it inside something closed, a separate commercial licence can be granted by the copyright holder — ask at tunedness.com.
Contextator · AGPL-3.0-or-later · Self-hosted MCP documentation server
Getting started
Your documentation
Using it
Operations