Contextator
Officialby Tunedness
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| HOST | No | The host interface to bind the server to. | 0.0.0.0 |
| PORT | No | The port to bind the server to. | 3444 |
| DATA_DIR | No | Writable directory holding the materialised sources (git checkouts, uploads, Notion pulls). /data inside the container. | .data |
| SECRET_KEY | No | At least 32 characters (e.g. openssl rand -hex 32). Encrypts git/Notion tokens at rest (AES-256-GCM). Needed only once such a source exists; changing it invalidates stored tokens. | |
| SETUP_CODE | No | One-time code required by /setup to create the first account. If unset, the server generates one and prints it at every start until an account exists. Case, dashes and punctuation are ignored when checked. | |
| ADMIN_TOKEN | No | Machine access token for /api/*, acting with root permissions. Treat like a root password; do not use in a browser. | |
| DATABASE_URL | No | Local development database connection string. The container ignores it and talks to its embedded PostgreSQL via PG* variables set by the entrypoint. | postgres://contextator:contextator@localhost:5432/contextator |
| IGNORE_GLOBS | No | Comma-separated glob patterns to ignore, e.g. '**/CHANGELOG.md,drafts/**'. Applies to every source. | |
| RESET_VECTORS | No | Set to '1' to drop all existing vectors and re-type the vector column (used when changing embedding dimension). | 0 |
| DOCS_HOST_PATH | No | Host folder mounted read-only at /docs (docker-compose only). | ./docs |
| OPENAI_API_KEY | No | OpenAI API key, used when EMBEDDING_PROVIDER is 'openai'. | |
| ALLOWED_ORIGINS | No | Extra browser origins allowed on /mcp/* (non-browser clients are always allowed). | |
| EMBEDDING_DTYPE | No | Data type for the local embedding model. 'fp32' or 'q8' (q8 downloads a ~4× smaller quantized model). | fp32 |
| EMBEDDING_MODEL | No | Embedding model to use. Any transformers.js feature-extraction model. English-only & faster: Xenova/all-MiniLM-L6-v2 (also 384-d). | Xenova/paraphrase-multilingual-MiniLM-L12-v2 |
| MODEL_CACHE_DIR | No | Model download directory; /app/.cache/models inside the container. | .cache/models |
| PUBLIC_BASE_URL | No | Public base URL, e.g. https://docs.example.com, used for URLs shown in the dashboard. | |
| CHUNK_MAX_TOKENS | No | Maximum tokens per document chunk. | 400 |
| ALLOWED_DOC_ROOTS | No | Comma-separated list of directories that project document roots must reside in. Path-escape protection. On Windows dev, e.g. C:/path/to/docs. | /docs |
| EMBEDDING_OFFLINE | No | Set to '1' to prevent the embedding model from downloading at startup (for air-gapped hosts). | 0 |
| POSTGRES_PASSWORD | No | Password of the embedded PostgreSQL (loopback only), applied when the cluster is first created. | contextator |
| AUTH_COOKIE_SECURE | No | Cookie Secure flag: 'auto' sets Secure when the request arrives over HTTPS. Force with '1', use '0' for plain-HTTP LAN installs. | auto |
| EMBEDDING_PROVIDER | No | Embedding provider: 'local' or 'openai'. | local |
| ARCHIVE_MAX_ENTRIES | No | Zip-bomb guard: maximum number of entries in an archive (applied while extracting). | 20000 |
| PASSWORD_MIN_LENGTH | No | Minimum password length for all passwords, including temporary ones. No composition rules. | 12 |
| SESSION_IDLE_TTL_MS | No | Idle Streamable HTTP sessions are closed after this many milliseconds. | 1800000 |
| AUTH_SESSION_IDLE_MS | No | Dashboard session idle timeout in milliseconds. A session unused for this long must sign in again. | 43200000 |
| CHUNK_OVERLAP_TOKENS | No | Token overlap between consecutive chunks. | 50 |
| EMBEDDING_DIMENSIONS | No | Dimension of the embedding vectors. Must match the model. 1536 for text-embedding-3-small. | 384 |
| AUTH_LOGIN_WINDOW_MIN | No | The IP window (in minutes) and the first lockout step (doubles, capped at an hour). | 15 |
| AUTH_SESSION_TTL_DAYS | No | Hard maximum lifetime of a dashboard session in days, however actively used. | 30 |
| UPLOAD_MAX_FILE_BYTES | No | Maximum size per uploaded file. | 52428800 |
| OPENAI_EMBEDDING_MODEL | No | OpenAI embedding model to use when EMBEDDING_PROVIDER is 'openai'. | text-embedding-3-small |
| ARCHIVE_MAX_TOTAL_BYTES | No | Zip-bomb guard: maximum total uncompressed size of an archive (applied while extracting). | 1073741824 |
| AUTH_LOGIN_MAX_ATTEMPTS | No | Maximum failed sign-in attempts per account and per IP before lockout or 429. | 10 |
| CONTEXTATOR_MODELS_PATH | No | Absolute host directory used for embedding models instead of the volume (docker-compose only). | |
| CONTEXTATOR_PGDATA_PATH | No | Absolute host directory used for PostgreSQL data instead of the volume (docker-compose only). | |
| UPLOAD_MAX_ARCHIVE_BYTES | No | Maximum size per uploaded archive. | 268435456 |
| CONTEXTATOR_MODELS_VOLUME | No | Docker volume name for embedding models (docker-compose only). | contextator-models |
| CONTEXTATOR_PGDATA_VOLUME | No | Docker volume name for PostgreSQL data (docker-compose only). | contextator-pgdata |
| UPLOAD_MAX_FILES_PER_REQUEST | No | Maximum number of files per upload request. | 500 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
This server cannot be deployed
Maintenance
ActivityMaintained
ResponsivenessNo issues