Skip to content

Environment variable descriptions (raw)

7,577 distinct values, measured against 42,703 published entries.

Value Entries Share
DATABASE_URL=The database the generated actions reach, in the same form your Prisma datasource takes. 1 0.0 %
DATABASE_URL=URL de conexao PostgreSQL (ex: postgresql://user:pass@localhost/certidao_db) 1 0.0 %
DATABASE_URL=Use an existing Kybase Postgres instead of the embedded one (migrations are left to the app) · EMBEDDING_PROVIDER=Embedding provider for semantic search · GOOGLE_API_KEY=Google API key, when EMBEDDING_PROVIDER=google. Sends note text to Google · KYBASE_DATA_DIR=Where the embedded database and instance secret live. Defaults to ~/.kybase · OLLAMA_MODEL=Ollama embedding model · OLLAMA_URL=Ollama endpoint for local embeddings. Without any provider, full-text search still works · OPENAI_API_KEY=OpenAI API key, when EMBEDDING_PROVIDER=openai. Sends note text to OpenAI 1 0.0 %
DATABASE_URL=Your own PostgreSQL, where this library keeps file ownership, grants and the audit chain. Apply node_modules/@filelayer/core/schema.sql once before starting. · FILELAYER_AS=The ONE subject this server speaks for, in your own id space. Fixed for the life of the process: no tool reads it as an argument and no tool can change it, which is the only reason exposing these tools to an agent is safe. Write it yourself or have your provisioning write it, never derive it from a conversation. Serving several people means starting several servers. · FILELAYER_BASE_URL=The base of the share URLs this instance mints. Without it, share links come back without a URL. · FILELAYER_DATA_DIR=A local directory for the bytes. Needs no bucket and no IAM user. Set this OR the S3_* block: with neither, the server refuses to start rather than falling back to memory, which would work in a demo and lose the first real file. · FILELAYER_MCP_AGENT_LABEL=How this agent names itself in the audit trail, recorded on every event these tools produce. It is what lets the chain separate "the partner opened this document" from "the partner's assistant opened this document". · FILELAYER_MCP_ALLOW_DESTRUCTIVE=Set to exactly `true` to register delete_file. Off by default because deleting is not recoverable and an agent that misreads a sentence deletes the wrong thing silently. · FILELAYER_MCP_EXPOSE_AUDIT=Set to exactly `true` to register file_audit. Off by default for a specific reason: reading the audit trail is the one act this library does not itself record, so an agent could read an organisation's entire history and leave nothing behind. See LIMITATIONS.md entry 16. · FILELAYER_MCP_RETURN_BYTES=Set to exactly `true` to register read_file. Off by default because a document returned by a tool is a document copied into a model's context; file_info plus a share link is usually what was actually needed. · FILELAYER_ORG=The organisation this server is scoped to, in your own id space. · S3_ACCESS_KEY_ID=Access key id for the bucket. · S3_BUCKET=The bucket. It must be private: this library decides who may be GIVEN a URL and has no say in who the object store will answer. `npx -p @filelayer/core filelayer doctor` reports whether yours serves unauthenticated reads. · S3_ENDPOINT=An S3-compatible endpoint, for example https://<account>.r2.cloudflarestorage.com. Setting it makes S3_BUCKET, S3_ACCESS_KEY_ID and S3_SECRET_ACCESS_KEY required. · S3_REGION=Region, or `auto` for Cloudflare R2. · S3_SECRET_ACCESS_KEY=Secret access key for the bucket. 1 0.0 %
DATABASE_URL_READONLY=Postgres connection string for the read-only role. · DATABASE_URL_WRITER=Postgres connection string for the writer role. 1 0.0 %
DATABRICKS_CLIENT_ID=Databricks: OAuth machine-to-machine service-principal client ID (preferred for automated use). Requires DATABRICKS_CLIENT_SECRET as well. · DATABRICKS_CLIENT_SECRET=Databricks: OAuth machine-to-machine service-principal client secret. Requires DATABRICKS_CLIENT_ID as well. · DATABRICKS_HTTP_PATH=Databricks: SQL warehouse HTTP path (from the warehouse's Connection Details tab, e.g. /sql/1.0/warehouses/<warehouse-id>). Required to use the databricks engine. · DATABRICKS_SERVER_HOSTNAME=Databricks: SQL warehouse server hostname (e.g. my-workspace.cloud.databricks.com, no scheme, no trailing slash). Required to use the databricks engine. · DATABRICKS_TOKEN=Databricks: personal access token (simplest auth option). Either this or DATABRICKS_CLIENT_ID + DATABRICKS_CLIENT_SECRET is required to use the databricks engine. · GOOGLE_APPLICATION_CREDENTIALS=BigQuery: path to a service-account key file (Application Default Credentials). Required to use the bigquery engine. · SNOWFLAKE_ACCOUNT=Snowflake: account identifier. Required to use the snowflake engine. · SNOWFLAKE_PASSWORD=Snowflake: password (discouraged; prefer SNOWFLAKE_PRIVATE_KEY_PATH). Either this or SNOWFLAKE_PRIVATE_KEY_PATH is required to use the snowflake engine. · SNOWFLAKE_PRIVATE_KEY_PASSPHRASE=Snowflake: passphrase for an encrypted SNOWFLAKE_PRIVATE_KEY_PATH key file, if the key is encrypted. · SNOWFLAKE_PRIVATE_KEY_PATH=Snowflake: path to an RSA private key file for key-pair auth (preferred over SNOWFLAKE_PASSWORD). Either this or SNOWFLAKE_PASSWORD is required to use the snowflake engine. · SNOWFLAKE_ROLE=Snowflake: role to assume. Required to use the snowflake engine; has no default and must never be ACCOUNTADMIN. · SNOWFLAKE_USER=Snowflake: username. Required to use the snowflake engine. 1 0.0 %
DATABRICKS_HOST=Your Databricks workspace URL (e.g. https://adb-123.azuredatabricks.net) · DATABRICKS_MCP_TOOLS_INCLUDE=Comma-separated list of tool modules to load (e.g. unity_catalog,sql,compute). Leave empty to load all 263 tools. · DATABRICKS_TOKEN=Databricks personal access token or OAuth token 1 0.0 %
DATACITE_CONTACT_EMAIL=Contact email sent in the User-Agent as mailto: (never a URL parameter). Moves requests to DataCite's identified tier (1,000 per 5 minutes per IP instead of 500). · DATACITE_CONTACT_EMAIL=Contact email sent in the User-Agent as mailto: (never a URL parameter). Moves requests to DataCite's identified tier (1,000 per 5 minutes per IP instead of 500). Set it on any hosted deployment. · DATACITE_MAX_REQUESTS_PER_5MIN=Request budget per 5-minute window, 50-1000. Default 800 with a contact email, 400 without; divide it across replicas sharing one egress IP. · MCP_AUTH_MODE=Authentication mode to use: 'none', 'jwt', or 'oauth'. · MCP_HTTP_ENDPOINT_PATH=The endpoint path for the MCP server. · MCP_HTTP_HOST=The hostname for the HTTP server. · MCP_HTTP_PORT=The port to run the HTTP server on. · MCP_LOG_LEVEL=Sets the minimum log level for output (e.g., 'debug', 'info', 'warn'). · MCP_TRANSPORT_TYPE=Selects the HTTP transport. 1 0.0 %
DATACORE_A2A_URL=Base URL của DataCore gateway, ví dụ https://gateway.example.com. Phải là gateway — trỏ thẳng orchestrator sẽ luôn bị từ chối 401. · DATACORE_MANDATE=AP2 mandate token do DataCore cấp. Quyết định skill nào được gọi và hạn mức chi tiêu. · DATACORE_SKILLS=Danh sách skill id cách nhau bằng dấu phẩy để giới hạn tool được expose, hoặc * để lấy tất cả skill mà endpoint trả về. Bỏ trống dùng mặc định. · DATACORE_TIMEOUT=Timeout mỗi request, tính bằng giây. Mặc định 30. 1 0.0 %
DATACRON_VAULT_ROOT=Absolute path to the Markdown vault the server indexes and serves. 1 0.0 %
DATADIFFER_CONFIG=Path to datadiffer.toml holding named connections (run `datadiffer init` to scaffold one). Credentials never pass through tool arguments. 1 0.0 %
DATAFORDELER_API_KEY=Datafordeler API key. Optional for lookups by id until 15 January 2027; required for text search and the GraphQL tools. 1 0.0 %
DATAFORSEO_CACHE_DAYS=TTL for the DataForSEO response cache, in days. Default 7. · DATAFORSEO_PASSWORD=DataForSEO API password (optional). · DATAFORSEO_USERNAME=DataForSEO API username (optional, enables SERP/keyword/domain/market/recon checks). · FIRECRAWL_API_KEY=Firecrawl API key (optional). Lets content recon scrape competitor pages. Get one at https://firecrawl.link/2d1PLD8 · GOOGLE_APPLICATION_CREDENTIALS=Path to the Google service-account JSON key with Search Console access. · MAJESTIC_API_KEY=Majestic API key (optional). Enriches link_intersect with Trust Flow + Topical Trust Flow and re-sorts prospects by real authority. · MAJESTIC_CACHE_DAYS=TTL for the Majestic response cache, in days. Default 30. · SAC_DATA_DIR=Directory for per-property SQLite databases and reports. Defaults to ~/Documents/seo-audit-console. · SUPADATA_API_KEY=Supadata API key (optional). Lets content recon transcribe the ranking videos (YouTube/TikTok/X). 1 0.0 %
DATAFORSEO_PASSWORD=DataForSEO account API password from the dashboard · DATAFORSEO_PROXY_TEST_CHILD=Test suite only, with NODE_ENV=test: path of a fake child to spawn instead of the upstream server. Never set it in normal use · DATAFORSEO_USERNAME=DataForSEO account login (email) from the dashboard 1 0.0 %
DATAGATE_API_KEY=Bearer token from your DataGate account. · DATAGATE_BASE_URL=Full API base URL. Leave blank to use DataGate's production endpoint (api.dgportal.net). · DATAGATE_CLIENT_ID=ClientId GUID from your DataGate account. Required in addition to the Bearer token on every request. · DATAGATE_MCP_HTTP_TOKEN=Required only when running the MCP server with --transport http. Not needed for the default local stdio transport. · DATAGATE_USER_AGENT=Overrides the User-Agent the CLI sends on DataGate requests. · PRINTING_PRESS_CLIENT_PROFILE=Binds this MCP server to one tenant-gated client profile. Leave blank to use the default client profile. 1 0.0 %
DATAGATE_PROJECT_ROOT=Workspace root used to resolve .datagate/datagate.toml, datagate.toml, or user-level config. 1 0.0 %
DATAIKU_API_KEY=Dataiku API key. · DATAIKU_PROJECT_KEY=Optional default Dataiku project key. · DATAIKU_URL=Dataiku DSS instance URL (for example, https://my-dss.app.dataiku.io). 1 0.0 %
DATALIKERS_API_KEY=DataLikers API key — get one at https://datalikers.com/tokens (100 free requests on signup) 1 0.0 %
DATALINK_ANALYTICS_READONLY=Set to 'true' for read-only access. Pattern: DATALINK_<NAME>_READONLY · DATALINK_ANALYTICS_URL=Database connection URL. Pattern: DATALINK_<NAME>_URL where <NAME> identifies the database. Supports postgresql://, mysql://, or file path for SQLite. 1 0.0 %
DATALOUPE_MCP_ROOT=Directory the server is allowed to read data files from (inside the container). Defaults to /data. 1 0.0 %
DATANIKA_ALLOW_WRITE=Set to true to enable write/trigger tools (read-only by default) · DATANIKA_API_KEY=Datanika API key (from Settings -> API Keys) · DATANIKA_URL=Datanika instance URL (defaults to https://app.datanika.io; set this for a self-hosted instance) 1 0.0 %
DATAPRISM_AUDIT_FILE_PATH=Path to the durable, hash-chained audit log; required when DATAPRISM_AUDIT_SINK=hash-chained, refused as MISSING_AUDIT_FILE_PATH if absent for that sink, ignored otherwise · DATAPRISM_AUDIT_SINK=Audit sink implementation: one of approved-sink, slf4j, hash-chained; required, never downgraded to no-op · DATAPRISM_AUDIT_WRITER_ID=Writer/instance identity recorded on every audit entry; required · DATAPRISM_HAZELCAST_CLUSTERNAME=Hazelcast cluster name; required when DATAPRISM_HAZELCAST_TOPOLOGY=embedded, never dev, refused if set with single-node · DATAPRISM_HAZELCAST_JOIN_MEMBERS=Comma-separated member addresses (host or host:port); required when DATAPRISM_HAZELCAST_JOIN_MODE=tcp-ip, otherwise unused · DATAPRISM_HAZELCAST_JOIN_MODE=How cluster members find each other: tcp-ip, kubernetes or none; required when DATAPRISM_HAZELCAST_TOPOLOGY=embedded (none is an explicit single member bound to 127.0.0.1), refused if set with single-node · DATAPRISM_HAZELCAST_MEMBER_PORT=Hazelcast member port, default 5701, never auto-incremented; must differ from the server, management and operator ports. Member traffic is unencrypted, so keep it on a private network. Optional · DATAPRISM_HAZELCAST_TOPOLOGY=Cluster read-budget topology: embedded (shared across members that have joined one cluster; set cluster name and join mode) or single-node (enforced per process); required, never defaulted · DATAPRISM_METRICS_SINK=Metrics sink binding, currently only micrometer; required in production, never the framework no-op · DATAPRISM_OPERATOR_ENABLED=Enables the operator surface; optional, off by default · DATAPRISM_OPERATOR_PORT=Port of the operator listener; required when DATAPRISM_OPERATOR_ENABLED=true, must differ from the server, management (OPERATOR_PORT_SHARED otherwise) and member ports, and has no fixed default (publish it explicitly) · DATAPRISM_OPERATOR_REQUIREDAUDIENCE=JWT audience an operator token must carry; required when DATAPRISM_OPERATOR_ENABLED=true · DATAPRISM_OPERATOR_REQUIREDSCOPE=JWT scope an operator token must carry; required when DATAPRISM_OPERATOR_ENABLED=true · DATAPRISM_PRIVACY_HMAC_KEY_ENVIRONMENT_VARIABLE=Name of the environment variable holding the HMAC key material; exactly one of this or DATAPRISM_PRIVACY_HMAC_KEY_PROVIDER_REFERENCE is required, never both, and never a literal key value · DATAPRISM_PRIVACY_HMAC_KEY_KEY_ID=Identifier of the pinned HMAC key used to derive synthetic identities; required · DATAPRISM_PRIVACY_HMAC_KEY_PROVIDER_REFERENCE=Reference to an approved secret provider holding the HMAC key material; set this instead of DATAPRISM_PRIVACY_HMAC_KEY_ENVIRONMENT_VARIABLE, never both · DATAPRISM_PRIVACY_PROFILE=Name of the reviewed privacy profile implementation to apply; required · DATAPRISM_PRIVACY_SCOPE_LIFETIME=Positive duration (e.g. 8h) a privacy scope's synthetic identities remain valid; required · DATAPRISM_SECURITYPOLICY_ROLES_INVESTIGATOR=Example only — declare DATAPRISM_SECURITYPOLICY_ROLES_<ROLE> per operator-defined role (no underscore between SECURITY and POLICY: Spring Boot's map-key enumeration under a hyphenated dataprism.security-policy.roles.<role> segment only binds the concatenated prefix, verified by binding this property directly against Spring Boot 4.1.1), a comma-separated list of known MCP tool capabilities; at least one role-to-capability mapping is required · DATAPRISM_SECURITY_CALLER_CLAIMS_INVESTIGATION=JWT claim name that carries the trusted investigation/case identifier; required, must differ from the principal and roles claims · DATAPRISM_SECURITY_CALLER_CLAIMS_PRINCIPAL=JWT claim name that carries the caller's principal identifier; required, must differ from the roles and investigation claims · DATAPRISM_SECURITY_CALLER_CLAIMS_ROLES=JWT claim name that carries the caller's roles; required, must differ from the principal and investigation claims · DATAPRISM_SECURITY_JWT_AUDIENCE=Expected JWT audience claim for this deployment; required for every protected deployment · DATAPRISM_SECURITY_JWT_ISSUER=OAuth2/OIDC issuer that mints the caller's JWT; required for every protected deployment · DATAPRISM_SECURITY_JWT_ISSUER_DISCOVERY_URI=Alternative HTTPS OIDC issuer-discovery location; set this instead of DATAPRISM_SECURITY_JWT_JWK_SET_URI, never both · DATAPRISM_SECURITY_JWT_JWK_SET_URI=HTTPS JWKS location used to verify caller JWTs; exactly one of this or DATAPRISM_SECURITY_JWT_ISSUER_DISCOVERY_URI is required, never both · DATAPRISM_SECURITY_POLICY_PURPOSES=Comma-separated list of permitted purposes; at least one is required · DATAPRISM_SOURCES_CUSTOMER_BASE_URL=Example only — declare DATAPRISM_SOURCES_<NAME>_BASE_URL (HTTPS) per configured source; at least one source, each with its own reviewed DataSourceAdapter bean, is required · DATAPRISM_SOURCES_CUSTOMER_TIMEOUT=Example only — declare DATAPRISM_SOURCES_<NAME>_TIMEOUT (positive duration) per configured source; required alongside its base URL · LOADER_PATH=Directory Spring Boot's PropertiesLauncher scans for extension jars; already set to /app/adapters by the image, but startup still fails with MISSING_SOURCE_ADAPTER until you bind-mount a reviewed DataSourceAdapter/IdentityResolver jar there (see the -v arguments above) 1 0.0 %
DATASCOOP_API_KEY=Optional DataScoop API key for Pro (unlimited rows). 1 0.0 %
DATASIEVE_API_URL=API base URL. Default https://api.datasieve.xyz; sandbox https://staging.datasieve.xyz (Base Sepolia, faucet USDC). · DATASIEVE_PRIVATE_KEY_FILE=Path to a file holding a burner wallet key (0x…) with USDC on Base. Optional — free tools work without it. 1 0.0 %
DATASINK_API_KEY=Your DataSinking API key. Free key at https://datasink.ing 1 0.0 %
DATAVERSE_ENVIRONMENTS_PATH=Optional path to the Dataverse environments configuration file. Defaults to ./environments.json. 1 0.0 %
DATAVERSE_ENV_URL=Your Dataverse environment URL · MCP_CONFIG_PATH=Path to a config.json file (overrides all other env vars). Recommended for VS Code / Claude Desktop setups. 1 0.0 %
DATAVILLE_API_BASE_URL=API base URL; defaults to https://api.dataville.com · DATAVILLE_API_KEY=Dataville API key from https://app.dataville.com/api-keys 1 0.0 %
DATAWRAPPER_ACCESS_TOKEN=Datawrapper API Access Token 1 0.0 %
DATA_DIR=Directory for shops.json, stats.db and the encryption key. Defaults to /data; set it to a writable path for a local install, e.g. ~/.ozon-mcp · OZON_API_KEY=Ozon Seller API key · OZON_CLIENT_ID=Ozon Seller API Client-Id from seller.ozon.ru (Settings - API keys) · OZON_PERF_CLIENT_ID=Ozon Performance API Client-Id, needed only for advertising tools · OZON_PERF_CLIENT_SECRET=Ozon Performance API client secret 1 0.0 %
DATA_DIR=Directory for shops.json, stats.db and the encryption key. Defaults to /data; set it to a writable path for a local install, e.g. ~/.wb-mcp · WB_API_TOKEN=Wildberries Seller API token from seller.wildberries.ru (Settings - Access tokens) 1 0.0 %
DATA_DIR=Persistent Event Intelligence state directory. · MCP_WRITE_ENABLED=Set to true to expose persistent trigger mutation tools. Read-only by default. · RUNTIME_WAKE_TARGETS_JSON=Optional operator-configured signed runtime wake targets. · TYPESAFE_API_KEY=Optional TypeSafe Jev API key for explicit semantic Pattern AST nodes. · TYPESAFE_MODEL=Optional TypeSafe Jev model override. Defaults to jev-latest. 1 0.0 %
DATA_DIR=Where to store the SQLite index + embedding cache. Defaults to $XDG_DATA_HOME/obsidian-brain or ~/.local/share/obsidian-brain. · EMBEDDING_MODEL=Power-user override: any transformers.js checkpoint or Ollama model id. Takes precedence over EMBEDDING_PRESET. Switching auto-reindexes. · EMBEDDING_PRESET=Preset name: english (default, bge-small-en-v1.5), english-fast, english-quality, multilingual, multilingual-quality, multilingual-ollama. Ignored when EMBEDDING_MODEL is set. · EMBEDDING_PROVIDER=Embedding backend. 'transformers' (local, default) or 'ollama' (requires a running Ollama server). · OBSIDIAN_BRAIN_COMMUNITY_DEBOUNCE_MS=Graph-wide community-detection (Louvain) debounce for the live watcher, in milliseconds. Louvain is the only expensive op — batching it prevents per-edit CPU spikes. · OBSIDIAN_BRAIN_CONFIG_DIR=Override the per-user config directory where obsidian-brain stores model overrides (`model-overrides.json`) and the user-fetched seed (`seed-models.json`). Default is `$XDG_CONFIG_HOME/obsidian-brain` on macOS/Linux (or `~/.config/obsidian-brain`) and `%APPDATA%/obsidian-brain` on Windows. Both files survive `npm update obsidian-brain` because they live outside the package. · OBSIDIAN_BRAIN_DEBUG=Set to "1" to print a verbose synchronous startup trace to stderr — every preflight, createContext, server.connect, and shutdown step is logged with a monotonic timestamp. The LAST line before any silent failure tells you exactly which step the server reached. No-op when unset (no overhead). Use to diagnose silent-crash failure modes. · OBSIDIAN_BRAIN_LOG_FORMAT=Set to 'ndjson' for one-JSON-object-per-line stderr output (timestamp + level + message + structured fields). Default is human-readable plain text (`obsidian-brain: <message>`). Useful for piping logs into aggregators (Datadog, Loki, Vector, journald) that index structured fields. · OBSIDIAN_BRAIN_MAX_CHUNK_TOKENS=Override the adaptive chunk-size budget (in tokens). When set, this beats the capacity probed from the model's tokenizer or Ollama /api/show. Use for debugging or for models with stale tokenizer configs. · OBSIDIAN_BRAIN_NO_CATCHUP=Set to '1' to skip the startup catchup reindex pass that picks up edits made while the server was down. The live file watcher still starts (via OBSIDIAN_BRAIN_NO_WATCH=1 to disable that separately), and first-time indexing on an empty DB is unaffected — this knob only governs the post-restart `enqueueBackgroundReindex` walk. · OBSIDIAN_BRAIN_NO_WATCH=Set to '1' to disable the live chokidar file watcher. Useful on SMB/NFS vaults where FSEvents/inotify don't fire reliably — fall back to running `obsidian-brain index` on a schedule (launchd/systemd). · OBSIDIAN_BRAIN_OLLAMA_AUTO_PULL=Auto-pull the configured Ollama model when /api/show returns 404 (model not present). Default ON — choosing an Ollama-backed preset is implicit consent to download its model. Streams /api/pull progress to stderr. Set to '0' to disable auto-pull entirely (master kill-switch) and fall back to the actionable error path (`HTTP 404 — try: ollama pull <model>`). · OBSIDIAN_BRAIN_OLLAMA_BYOM_AUTO_PULL=Opt-in to auto-pull for BYOM (custom EMBEDDING_MODEL) Ollama models OUTSIDE Ollama's official `library/` namespace. Default OFF — third-party models (e.g. `user/custom-fork`, `myregistry.com/team/model`) require this env var to be set to `1` before they will auto-pull, to prevent silent downloads of arbitrary user-named artifacts. Preset-known models (via EMBEDDING_PRESET) and bare model ids in the official library (e.g. `qwen3-embedding:0.6b`, `library/llama3:8b`) continue to auto-pull by default per the existing OBSIDIAN_BRAIN_OLLAMA_AUTO_PULL behavior. · OBSIDIAN_BRAIN_TOOL_TIMEOUT_MS=Per-tool-call timeout in milliseconds. Tools exceeding this return an MCP error instead of hanging. · OBSIDIAN_BRAIN_WATCH_DEBOUNCE_MS=Per-file reindex debounce for the live watcher, in milliseconds. · OLLAMA_BASE_URL=Base URL of a local Ollama server. Only used when EMBEDDING_PROVIDER=ollama. · OLLAMA_EMBEDDING_DIM=Override the embedding dimensionality when EMBEDDING_PROVIDER=ollama. If unset, the server probes the model on startup. · OLLAMA_NUM_CTX=Override Ollama's num_ctx for embed requests. Leave UNSET to let obsidian-brain auto-detect via `/api/show`'s `context_length` (e.g. nomic-embed-text=2048, bge-m3=8192, qwen3-embedding:0.6b=32 768). Setting this manually imposes a hard cap and may silently truncate longer inputs — see https://github.com/ollama/ollama/issues/14259. Ollama's own default is 2048 which truncates for any model trained on a larger context. See also https://github.com/ollama/ollama/issues/7008. Fallback when both env is unset AND /api/show is unreachable: 8192. · VAULT_PATH=Absolute path to your Obsidian vault (or any folder of .md files). 1 0.0 %
DATA_GOV_SG_API_KEY=Optional data.gov.sg API key for production limits. · LTA_DATAMALL_API_KEY=Optional LTA DataMall Account Key for dynamic transport APIs. · OLANO_SG_CACHE_DIR=Optional private directory for the persistent public-response cache. · OLANO_SG_PROFILE=Optional aggregate tool profile: all, mobility, property, business, economy, civic, or finance. · ONEMAP_TOKEN=Optional OneMap token for geocoding, routing, themes, and address-based rail lookup. 1 0.0 %
DATA_GO_KR_BASE_URL=서비스 경로를 포함한 전체 base URL 오버라이드 · DATA_GO_KR_DOWNLOAD_DIR=download_attachments 저장 기준 디렉터리. 공고번호별 하위폴더로 저장한다. 미설정 시 ~/Downloads · DATA_GO_KR_DOWNLOAD_MAX_BYTES=download_attachments 파일당 다운로드 크기 상한(바이트, 기본 100MB) · DATA_GO_KR_DOWNLOAD_TIMEOUT_MS=download_attachments 파일 다운로드 타임아웃(밀리초) · DATA_GO_KR_SERVICE_KEY=공공데이터포털 data.go.kr Decoding(원본) 인증키 1 0.0 %
DATA_GO_KR_KEY=Service key from data.go.kr (Korean public data portal). Required for National Fire Agency APIs: fire status, EMS statistics, fire-safety buildings, facilities, and hazardous materials. · LAW_OC=OC identifier from open.law.go.kr (Korean Ministry of Government Legislation). Required for statutes, annexes, precedents, and administrative rules. 1 0.0 %
DATA_GO_KR_SERVICE_KEY=선택. 공공데이터포털 등록원부 API 키(일반 인증키 Decoding). 넣으면 만료일·권리자·연차료를 등록원부 확정값으로 판정합니다. · KIPRIS_CACHE_TTL=선택. 같은 번호 조회를 캐시하는 시간(초). 기본 3600. · KIPRIS_SERVICE_KEY=KIPRIS Plus 서비스 키. plus.kipris.or.kr에서 무료로 발급합니다(공공데이터포털 키가 아닙니다). 1 0.0 %
DATA_ROOT=Root directory for market data files · MCP_SERVER_PORT=Server port (default: 8010) 1 0.0 %
DATRIS_API_KEY=API key for the Datris server (only when USE_API_KEYS=true) · DATRIS_API_URL=URL of the Datris server API (default http://localhost:8080) 1 0.0 %
DATTO_BCDR_BASE_URL=Base URL for the Datto BCDR API. Leave the prefilled default unless your account uses a different regional or self-hosted host. · DATTO_BCDR_MCP_HTTP_TOKEN=Required only when running the MCP server with --transport http. Not needed for the default local stdio transport. · DATTO_BCDR_PUBLIC_KEY=Set the DATTO_BCDR_PUBLIC_KEY credential for the Datto BCDR MCP server. · DATTO_BCDR_SECRET_KEY=Set the DATTO_BCDR_SECRET_KEY credential for the Datto BCDR MCP server. · DATTO_BCDR_USER_AGENT=Overrides the User-Agent the CLI sends on Datto BCDR requests. Leave blank to use the CLI's own built-in User-Agent. · PRINTING_PRESS_CLIENT_PROFILE=Only used when the MCP server is bound to a tenant-gated Printing Press client profile; leave blank otherwise. 1 0.0 %
DATTO_RMM_API_KEY=Set the DATTO_RMM_API_KEY credential for the Datto RMM MCP server. · DATTO_RMM_API_SECRET_KEY=Set the DATTO_RMM_API_SECRET_KEY credential for the Datto RMM MCP server. · DATTO_RMM_BASE_URL=Full API base URL, e.g. https://merlot-api.centrastage.net/api. Overrides the platform shortcut above. Leave blank when you set the platform. · DATTO_RMM_NO_CONFIG_WRITE=Set to 1 to keep credentials off disk. The token cache becomes a no-op, so the connector mints a fresh token each run instead of writing one to config.toml. Leave blank for the default cached behaviour. · DATTO_RMM_PLATFORM=Regional platform shortcut that selects the API host: pinotage, merlot, concord, vidal, zinfandel, or syrah. It is the 'merlot' in merlot.centrastage.net. Leave blank if you set the base URL directly. · DATTO_RMM_TOKEN=Set the DATTO_RMM_TOKEN credential for the Datto RMM MCP server. 1 0.0 %
DATUMA_K=Absolute path to the datuma_k binary. Omit if datuma_k is already on PATH. 1 0.0 %
DATUM_API_URL=Datum API base URL. Defaults to https://datummarket.co. · DATUM_MAX_PRICE_DTM=Safety cap on purchase_data spend, in DTM. Defaults to 1000. · DATUM_RPC_URL=Base JSON-RPC endpoint. Required only for on-chain purchases. · DATUM_SIGNER_KEY=Wallet private key used to sign paid actions and identify the seller. Read-only tools work without it. 1 0.0 %
DAZZLE_API_KEY=API key for headless/CI use. Alternative to interactive login. · DAZZLE_STAGE=Pin to a specific stage name or ID. If omitted, auto-selects when you have one stage. 1 0.0 %
DB2I_DRIVER=Database driver: odbc (default, IBM i Access ODBC driver, no Java), jt400 (install node-jt400 next to the server; needs a JDK at install and a JRE at runtime) or mapepire (install @ibm/mapepire-js and ssh2; Mapepire over SSH, needs Java on the IBM i only) · DB2I_HOSTNAME=IBM i hostname or IPv4 address · DB2I_JDBC_OPTIONS=Extra JT400 JDBC properties, semicolon-separated (jt400 and mapepire drivers) · DB2I_MAPEPIRE_OPTIONS=SSH and Mapepire settings, semicolon-separated, e.g. hostKey=SHA256:...;agent=true;maxJobs=2 (mapepire driver) · DB2I_ODBC_OPTIONS=Extra IBM i Access ODBC connection keywords, semicolon-separated (odbc driver) · DB2I_PASSWORD=IBM i password · DB2I_PROFILES=Path to a YAML file of IBM i systems. When set, it replaces the DB2I_* connection variables · DB2I_SCHEMA=Default schema (library) · DB2I_USERNAME=IBM i user profile · QUERY_ALLOWED_SCHEMAS=Comma-separated schemas the server may read. Empty disables the check. 1 0.0 %
DBGPROBE_BACKEND=Debug probe backend to use (default: jlink). Future: openocd, pyocd. · DBGPROBE_INTERFACE=Debug interface: SWD (default) or JTAG. · DBGPROBE_JLINK_DEVICE=Default target device string (e.g. nRF52840_xxAA). Can be overridden per-session. · DBGPROBE_JLINK_GDBSERVER_PATH=Explicit path to JLinkGDBServerCLExe. Auto-detected if not set. · DBGPROBE_JLINK_PATH=Explicit path to JLinkExe (or JLink.exe on Windows). Auto-detected if not set. · DBGPROBE_MCP_LOG_LEVEL=Log level: DEBUG, INFO, WARNING (default), ERROR. · DBGPROBE_MCP_PLUGINS=Plugin policy: 'all' or comma-separated plugin names. Unset = disabled. · DBGPROBE_MCP_TOOL_SEPARATOR=Tool name separator character (default '.'). Set to '_' for clients that reject dots (e.g. Cursor). · DBGPROBE_SPEED_KHZ=Interface speed in kHz (default: 4000). 1 0.0 %
DBHAWK_BASE_URL=DBHawk base URL, e.g. https://dbhawk.example.com (no trailing /api) · DBHAWK_DEFAULT_DATASOURCE=Datasource used when a request doesn't name one · DBHAWK_TOKEN=MCP-scoped personal token (dbh_...) from DBHawk User Profile > API Token 1 0.0 %
DBRIDGE_CONFIG=Absolute path to a dbridge.config.json with safety settings (row caps, hidden/masked columns, table allow/block lists) 1 0.0 %
DBS=Engines to enable, comma-separated. Only the listed engines get their tools registered. Example: mysql,redis,kafka · DYNAMODB_ACCESS_KEY_ID=AWS access key ID for DynamoDB. · DYNAMODB_REGION=AWS region for DynamoDB. DynamoDB is configured with discrete variables instead of a connection string. · DYNAMODB_SECRET_ACCESS_KEY=AWS secret access key for DynamoDB. · ELASTICSEARCH=Elasticsearch connection string(s), semicolon-separated. Format: elasticsearch://<user>:<password>@<host>:9200?alias=dev, or http(s)://<host>:9200?alias=dev for no auth. alias is required. · KAFKA=Kafka connection string(s), semicolon-separated. Format: kafka://<user>:<password>@<broker1>:9092,<broker2>:9092?alias=dev&mechanism=plain — alias is required. · MONGODB=MongoDB connection string(s), semicolon-separated. Format: mongodb://<user>:<password>@<host>:27017/<database>?alias=dev — alias is required. · MYSQL=MySQL connection string(s), semicolon-separated for multiple instances. Format: mysql://<user>:<password>@<host>:3306/<database>?alias=dev&default=true — alias is required. · POSTGRESQL=PostgreSQL connection string(s), semicolon-separated. Format: postgresql://<user>:<password>@<host>:5432/<database>?alias=dev&ssl=true — alias is required. · READ_ONLY=Set to true to hide every write tool and restrict *_execute_query to SELECT-style statements. Recommended when pointing at production. · REDIS=Redis connection string(s), semicolon-separated. Format: redis://:<password>@<host>:6379/0?alias=dev — leave the password empty for a no-auth instance. alias is required. · REDSHIFT=Redshift connection string(s), semicolon-separated. Format: redshift://<user>:<password>@<host>:5439/<database>?alias=dev&ssl=true — alias is required. 1 0.0 %
DB_CONNECT_TIMEOUT_MS=Connection timeout in milliseconds. Defaults to 10000 · DB_DEFAULT_PROFILE=Which DB_PROFILES entry to start on · DB_LOG=true logs every tool call, its statements and full output to stderr. Off by default · DB_LOG_DIR=Save every tool call as its own JSON file in this folder, on a mounted volume. Implies logging · DB_LOG_DIR=Save every tool call as its own JSON file in this folder, permanently. Implies logging · DB_LOG_FILE=Log every tool call to this file instead, on a mounted volume. Implies DB_LOG · DB_LOG_FILE=Log every tool call to this file instead. Implies DB_LOG · DB_LOG_FORMAT=pretty (default) or json, one object per line · DB_LOG_HISTORY=Entries the viewer keeps in memory when DB_LOG_DIR is not set. Defaults to 500 · DB_LOG_PORT=Serve a live log viewer in the browser on this port. Needs DB_LOG_DIR, DB_LOG or DB_LOG_FILE. No access control · DB_LOG_PORT=Serve a live log viewer on this port (publish it with -p). Needs DB_LOG_DIR, DB_LOG or DB_LOG_FILE. No access control · DB_PASSWORD=Password for DB_URL, so it need not be percent-encoded inside the URL · DB_PROFILES=JSON object of named connections to switch between, each a URL or {"url", "password"} · DB_QUERY_TIMEOUT_MS=Server-side query timeout in milliseconds. Defaults to 30000 · DB_URL=Connection URL to open at startup, e.g. postgres://user@host:5432/db, mongodb://user@host/db, redis://host:6379/0 or sqlite:///data/app.db · DB_URL=Connection URL to open at startup, e.g. postgres://user@host:5432/db, mongodb://user@host/db, redis://host:6379/0 or sqlite:///data/app.db. Use host.docker.internal to reach the host · MYSQL_DATABASE=Legacy MySQL-only form. Prefer DB_URL · MYSQL_HOST=Legacy MySQL-only form, kept for drop-in compatibility. Prefer DB_URL · MYSQL_PASSWORD=Legacy MySQL-only form. Prefer DB_URL with DB_PASSWORD · MYSQL_USER=Legacy MySQL-only form. Prefer DB_URL 1 0.0 %

This sheet lists 50 of 7,577 values; they cover 50 entries.

Sheet 45 of 152, 7,577 values in total.

Counted from the projection, the same table the list filters on. An entry counts once per value.

tracevero · https://tracevero.com/werkzeuge/merkmal/mcp/roh_umgebungsbeschreibungen?seite=45