Skip to content

Environment variable descriptions (raw)

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

Value Entries Share
ELASTICSEARCH_API_KEY=API key for Elasticsearch or Elastic Cloud authentication (recommended) · ELASTICSEARCH_HOSTS=Comma-separated list of Elasticsearch hosts (e.g., https://localhost:9200) · ELASTICSEARCH_PASSWORD=Password for basic authentication (used with ELASTICSEARCH_USERNAME) · ELASTICSEARCH_USERNAME=Username for basic authentication (alternative to API key) · ELASTICSEARCH_VERIFY_CERTS=Whether to verify SSL certificates (true/false) 1 0.0 %
ELASTICSEARCH_API_KEY=API key for authentication (recommended for production and Elastic Cloud) · ELASTICSEARCH_BEARER_TOKEN=Bearer/service token for authentication (alternative to API key) · ELASTICSEARCH_CLOUD_ID=Elastic Cloud deployment ID (alternative to ELASTICSEARCH_HOSTS for cloud deployments) · ELASTICSEARCH_HOSTS=Comma-separated Elasticsearch hosts. Supports HTTP/HTTPS, local/remote/cloud (e.g., http://localhost:9200, https://es.prod.example.com:9200) · ELASTICSEARCH_PASSWORD=Password for basic authentication (used with ELASTICSEARCH_USERNAME) · ELASTICSEARCH_USERNAME=Username for basic authentication (alternative to API key) · REQUEST_TIMEOUT=Request timeout in seconds (e.g., 60 or 10.5) · VERIFY_CERTS=TLS certificate verification: true (verify CA — production), false (skip — dev/test), or /path/to/ca.crt (custom CA) 1 0.0 %
ELASTICSEARCH_URL=Direct Elasticsearch URL. If unset, ES requests route through the Kibana Console proxy. · KIBANA_API_KEY=Elasticsearch API key (ApiKey base64(id:api_key) format). Takes priority over Basic auth. · KIBANA_PASSWORD=HTTP Basic auth password. · KIBANA_SSL_VERIFY=Verify SSL certificates (true/false). Set to 'false' for self-signed certs. · KIBANA_URL=Kibana base URL (e.g. https://kibana.example.com) · KIBANA_USERNAME=HTTP Basic auth username. Used only when KIBANA_API_KEY is not set. 1 0.0 %
ELECTRICITY_MAPS_API_TOKEN=Optional Electricity Maps API token for live grid data. Without it, annual averages are used. 1 0.0 %
ELECTRICITY_PROVIDER=Provider selector — "mock" (default, offline fixtures) or "vtpass" for live data. · VTPASS_API_KEY=VTpass API key — required when ELECTRICITY_PROVIDER=vtpass. · VTPASS_BASE_URL=Set to https://vtpass.com/api for production (default is the VTpass sandbox). · VTPASS_PUBLIC_KEY=VTpass public key (PK_...) — required when ELECTRICITY_PROVIDER=vtpass. · VTPASS_SECRET_KEY=VTpass secret key (SK_...) — required when ELECTRICITY_PROVIDER=vtpass. 1 0.0 %
ELEMENTOR_MCP_CONFIG_PATH=Alternative: path to a JSON config file. README has the schema. · ELEMENTOR_MCP_DEFAULT_SITE_ID=Optional default site id when a tool is called without site_id. · ELEMENTOR_MCP_SITES=JSON array of site objects. Each: {id, url, username, application_password}. See README. 1 0.0 %
ELEPHIA_DIR=Path to the context store directory (default: nearest .elephia/, else ~/.elephia/store; a legacy CONTEXTGIT_DIR or .contextgit/ store is still honored) 1 0.0 %
ELESYNC_DIR=Vault directory (default: ~/EleSyncVault) 1 0.0 %
ELEVENLABS_API_KEY=ElevenLabs API key (starts with sk_) · MCP_WORKSPACE_PATH=Optional workspace root for sandboxed knowledge-base file uploads 1 0.0 %
ELEVENLABS_API_KEY=ElevenLabs API key (starts with sk_) · MCP_WORKSPACE_PATH=Workspace directory for transcription audio file inputs. Defaults to os.tmpdir() when unset. 1 0.0 %
ELEVENLABS_API_KEY=ElevenLabs API key for high-quality TTS. Optional — falls back to macOS system voice if not set. 1 0.0 %
ELEVENLABS_API_KEY=ElevenLabs key — voiceover · FAL_KEY=fal.ai key — image + video · FIRECRAWL_API_KEY=Firecrawl key — URL extraction · GEMINI_API_KEY=Gemini key — image/video analysis · SCRAPECREATORS_API_KEY=ScrapeCreators key — social research · WAVESPEED_API_KEY=WaveSpeed key — image + video (recommended) 1 0.0 %
ELEVENLABS_API_KEY=Your ElevenLabs API key 1 0.0 %
ELFA_API_KEY=Elfa API key from https://dev.elfa.ai 1 0.0 %
ELISYM_AGENT=Name of an elisym agent identity (reads config from ~/.elisym/<name>/elisym.yaml) · ELISYM_AGENT_NAME=Agent display name for ephemeral mode (default: mcp-agent) · ELISYM_ALLOW_AGENT_SWITCH=Set to '1' to override per-agent security.agent_switch_enabled flag · ELISYM_ALLOW_DELEGATION=Set to '1' to enable the approve_delegation tool (grants a provider a USDC allowance) · ELISYM_ALLOW_WITHDRAWAL=Set to '1' to override per-agent security.withdrawals_enabled flag (CI use) · ELISYM_NETWORK=Network for ephemeral mode. Only 'devnet' is supported (default: devnet) · ELISYM_NOSTR_SECRET=Nostr secret key (hex or nsec) for ephemeral mode. Auto-generates if omitted · ELISYM_PASSPHRASE=Passphrase to decrypt encrypted agent configs (required if config was encrypted) 1 0.0 %
ELIXIUM_API_KEY=Your Elixium API key. Generate one from your workspace card on the Profile tab (Generate Key button). · ELIXIUM_API_URL=Your Elixium workspace API URL (e.g., https://your-tenant.elixium.ai/api). · ELIXIUM_BOARD_SLUG=Board slug to scope operations to a specific board. Optional — auto-detects when the workspace has only one board. · ELIXIUM_USER_EMAIL=Email of the user creating stories. Optional — defaults to the user the API key is bound to. 1 0.0 %
ELMA365_DOMAIN=API key for the service 1 0.0 %
ELSEVIER_API_KEY=Elsevier API key from https://dev.elsevier.com. Required for every tool except subject_classifications; data access depends on your subscription and institutional access. · ELSEVIER_INST_TOKEN=Institutional token supplied by Elsevier, if available for your institution. Used alongside the API key for institutional access. 1 0.0 %
ELSEVIER_API_KEY=Elsevier API key · FULLTEXT_OUTPUT_DIR=Folder for downloaded files (default ./papers) · SEMANTIC_SCHOLAR_API_KEY=Semantic Scholar API key · SPRINGER_API_KEY=Springer Nature API key · UNPAYWALL_EMAIL=Contact email for Unpaywall and Crossref · WILEY_API_KEY=Wiley TDM token 1 0.0 %
ELSTER_CITY=City. · ELSTER_CONFIG_PATH=Path to a config.json that holds all settings below. Recommended. · ELSTER_COUNTRY=ISO country code, default DE. · ELSTER_EST_SKIP_EUR=If 1, skip the EUER pre-hook in ESt sessions. · ELSTER_FIRST_NAME=First name. · ELSTER_HEADLESS=Run Chromium headless (true/false). Default true. · ELSTER_HOUSE_NUMBER=House number. · ELSTER_NAME=Last name / company name. · ELSTER_PASSWORD=Password for the .pfx certificate. · ELSTER_PFX_PATH=Absolute path to your ELSTER certificate (.pfx). · ELSTER_STATE_CODE=Two-digit ELSTER federal-state code of your Finanzamt. · ELSTER_STREET=Street. · ELSTER_TAX_NUMBER=Your Steuernummer in the format issued by your Finanzamt. · ELSTER_ZIP=ZIP code. 1 0.0 %
EMAIL2CHAT_API_KEY=Your API key from the Email2Chat dashboard (starts with em2c_) 1 0.0 %
EMAILENS_API_KEY=API key for screenshots and sharing. Get one free at emailens.dev/settings/api-keys 1 0.0 %
EMAILFINDER_API_KEY=API key from emailfinder.dev/dashboard/settings 1 0.0 %
EMAIL_ACCOUNTS=Inline JSON array of account configs · EMAIL_CONFIG_FILE=Path to account JSON config file 1 0.0 %
EMAIL_CREDENTIALS=Email credentials (format: user@gmail.com:app-password). Multiple accounts: comma-separated. 1 0.0 %
EMAIL_IMAP_EMAIL=Email address · EMAIL_IMAP_IMAP_HOST=Custom IMAP host (for provider=custom) · EMAIL_IMAP_IMAP_PORT=Custom IMAP port · EMAIL_IMAP_MAX_RECIPIENTS=Safety cap: maximum combined To+CC+BCC recipients per email_send call. Defaults to 25; raising bypasses spam-prevention guardrails against prompt-injection-driven mass sends. · EMAIL_IMAP_PASSWORD=App-specific password · EMAIL_IMAP_PROVIDER=Provider — icloud, gmail, yahoo, outlook, or custom (auto-detected from email domain if unset) · EMAIL_IMAP_RATE_LIMIT_PER_HOUR=Safety cap: maximum email_send calls per rolling window. Defaults to 50; protects against runaway sends when injection content escapes the LLM's intent. · EMAIL_IMAP_RATE_LIMIT_WINDOW_MS=Sliding-window length for the rate limit (ms) · EMAIL_IMAP_SMTP_HOST=Custom SMTP host (for provider=custom) · EMAIL_IMAP_SMTP_PORT=Custom SMTP port · MCP_WORKSPACE_PATH=Workspace directory that email_get_attachment downloads into (fresh email-imap-attachment-* staging directories). Defaults to the system temp directory. 1 0.0 %
EMBEDDER_API_KEY=API key for the embedder. Keyless TEI accepts any non-empty value; use 'not-needed' there. · EMBEDDER_BASE_URL=Required: the dense retrieval leg embeds the 40-pattern catalogue during startup warmup and the server refuses to start when the endpoint is unreachable. OpenAI-compatible embeddings endpoint ending in /v1: on the Docker host use http://host.docker.internal:8080/v1 (add --add-host=host.docker.internal:host-gateway on Linux); on a shared Docker network use http://pattern-tei-embed:8080/v1. · EMBEDDER_PROVIDER=Embedding backend for pattern retrieval: tei, openai, ollama, vllm or hosted_vllm. · GENERATOR_API_KEY=API key for the generator LLM (LiteLLM provider). · GENERATOR_BASE_URL=OpenAI-compatible base URL (LiteLLM api_base). · GENERATOR_MODEL=Model name, combined as <provider>/<model> via LiteLLM. · GENERATOR_PROVIDER=LiteLLM provider prefix, e.g. openai, anthropic, openrouter, minimax. · PATTERN_DIRECTORY=Directory with *-pattern.json files. The image bakes the 40-pattern catalogue at /app/pattern. · RERANKER_BASE_URL=Required: pattern retrieval runs a mandatory TEI cross-encoder rerank. On the Docker host use http://host.docker.internal:8080; on a shared Docker network use http://pattern-tei-rerank:8080. 1 0.0 %
EMBEDDER_API_KEY=API key for the embedder. Required for startup even with keyless TEI; use 'not-needed' there. · EMBEDDER_BASE_URL=Embedder endpoint. For TEI sidecars on the host use http://host.docker.internal:8080/v1 (add --add-host=host.docker.internal:host-gateway on Linux). · EMBEDDER_PROVIDER=Embedding backend for pattern retrieval: tei, openai, ollama, vllm or hosted_vllm. · GENERATOR_API_KEY=API key for the generator LLM (LiteLLM provider). · GENERATOR_BASE_URL=OpenAI-compatible base URL (LiteLLM api_base). · GENERATOR_MODEL=Model name, combined as <provider>/<model> via LiteLLM. · GENERATOR_PROVIDER=LiteLLM provider prefix, e.g. openai, anthropic, openrouter, minimax. · PATTERN_DIRECTORY=Directory with *-pattern.json files. The image bakes the 61-pattern catalog at /app/pattern. · RERANKER_BASE_URL=TEI cross-encoder reranker endpoint used during pattern retrieval. 1 0.0 %
EMBEDDER_DIM=Embedding vector dimension · EMBEDDER_MODEL=Embedding model id · EMBEDDER_URL=Optional HTTP embedder (Ollama/TEI/OpenAI-compatible). Unset = in-process embedder. · ORCHESTRATOR_DB_PATH=SQLite path inside container 1 0.0 %
EMBEDDING_BACKEND=DEPRECATED (honored one release): embedding backend override 'local' or 'cloud'. Use EMBEDDING_MODELS instead. · EMBEDDING_MODELS=Embedding models in selection order; the current runtime uses the first provider/model entry; empty = local ONNX · HULL_CHAT_API_KEY=API key for the [models.chat] cell transport (OpenRouter pre-wired default); host-injected, enables LLM summaries when the cell model is set · HULL_EMBED_API_KEY=API key for the [models.embed] cell transport (OpenRouter pre-wired default); host-injected, overrides the cell api_key · LOCAL_EMBEDDING_DIM=Required positive output dimension for an external local embedding ID without a manifest · LOCAL_EMBEDDING_MODEL=Built-in fastretrieval model ID or local directory with fastretrieval-manifest.json · LOCAL_EMBEDDING_MODEL_FILE=ONNX file path inside a manifest-backed local embedding directory · LOCAL_EMBEDDING_NORMALIZE=Explicit L2 normalization for an external local embedding ID without a manifest · LOCAL_EMBEDDING_POOLING=Explicit pooling for an external local embedding ID without a manifest · LOCAL_RERANK_MODEL=Fastretrieval TextCrossEncoder model ID; empty = reranking disabled 1 0.0 %
EMBEDDING_DIMENSIONS=Embedding vector dimensions (defaults per provider; required for lmstudio and litellm) · EMBEDDING_MODEL=Embedding model name (defaults per provider; required for lmstudio and litellm) · EMBEDDING_PROVIDER=Embedding provider to use: ollama (default), openai, google, lmstudio, or litellm · GOOGLE_API_KEY=API key for Google embeddings (required only when EMBEDDING_PROVIDER=google) · LITELLM_API_KEY=LiteLLM master or virtual API key (required when EMBEDDING_PROVIDER=litellm) · LITELLM_SEND_DIMENSIONS=Forward the dimensions parameter through LiteLLM when explicitly enabled · LITELLM_URL=LiteLLM OpenAI-compatible base URL (default: http://localhost:4000/v1) · LMSTUDIO_ALLOW_MISSING_MODEL_LISTING=Allow compatible embedding servers without a models endpoint to be probed directly · LMSTUDIO_API_KEY=Optional API key when LM Studio authentication is enabled · LMSTUDIO_URL=LM Studio OpenAI-compatible base URL (default: http://localhost:1234/v1) · OLLAMA_API_KEY=Optional API key for authenticated Ollama proxies · OLLAMA_MODE=Ollama mode: auto (default), docker, or external · OLLAMA_URL=URL of the Ollama server (default: auto-detected; Docker-managed or http://localhost:11434) · OPENAI_API_KEY=API key for OpenAI embeddings (required only when EMBEDDING_PROVIDER=openai) · QDRANT_API_KEY=API key for remote Qdrant instance. Only needed when QDRANT_MODE=external · QDRANT_MODE=Qdrant mode: managed (default, Docker-managed) or external (user-provided instance) · QDRANT_URL=Full URL for remote/cloud Qdrant (e.g. https://xyz.cloud.qdrant.io:6333). Only needed when QDRANT_MODE=external 1 0.0 %
EMBEDDING_MODEL=Gemini text embedding model · GEMDEX_MODE=Memory backend: embedded local LanceDB or a self-hosted Gemdex Server · GEMDEX_REMOTE_NAME=Human-readable name for the remote server · GEMDEX_REMOTE_TOKEN=Gemdex Server bearer token (required in remote mode) · GEMDEX_REMOTE_URL=Gemdex Server root URL (required in remote mode) · GEMDEX_TRUST_RANKING=Re-rank recall results by recorded worked/failed/stale outcomes · GEMINI_API_KEY=Google AI Studio key for local mode, or the exact value 'local' for on-device MLX text embeddings. Not needed in remote mode. · LANCEDB_PATH=Directory for the embedded LanceDB store 1 0.0 %
EMBEDDING_MODEL=Ollama embedding model (default: nomic-embed-text) · FIREWALL_DATA_DIR=Directory for storing ChromaDB data · OLLAMA_URL=URL for Ollama server (default: http://localhost:11434) · SIMILARITY_THRESHOLD=Block threshold 0-1 (default: 0.85) 1 0.0 %
EMBEDDING_MODEL=Ollama embedding model (default: nomic-embed-text) · OLLAMA_URL=URL for Ollama server (default: http://localhost:11434) 1 0.0 %
EMBEDDING_MODEL=sentence-transformers model for embeddings · GEMINI_API_KEY=Google Gemini API key (free tier). Get one at https://aistudio.google.com/apikey · GEMINI_MODEL=Gemini model for answer generation · LANGFUSE_PUBLIC_KEY=LangFuse public key, paired with LANGFUSE_SECRET_KEY · LANGFUSE_SECRET_KEY=LangFuse secret key for observability (free tier). Get one at https://cloud.langfuse.com · QDRANT_API_KEY=Only needed for a hosted Qdrant Cloud instance; leave unset for local Qdrant · QDRANT_URL=Qdrant vector database URL, e.g. http://localhost:6333 for local Docker, or a Qdrant Cloud cluster URL · SEC_EDGAR_USER_AGENT=Identifying User-Agent for SEC EDGAR requests, e.g. "YourApp you@email.com" 1 0.0 %
EMBEDDING_PROVIDER=Embedding provider: ollama (free), openai, or mock 1 0.0 %
EMBED_API_URL=Embedding API endpoint · EMBED_ENABLED=Enable embedding-based features · EMBED_MODEL=Embedding model name · EMBED_PROVIDER=Embedding provider: openai, gigachat, lmstudio · MODE=Server mode: luca, prizma, or sloi · OBSIDIAN_ROOT=Path to Obsidian vault 1 0.0 %
EMBED_API_URL=Embedding API endpoint · EMBED_ENABLED=Enable embedding-based features · EMBED_MODEL=Embedding model name · EMBED_PROVIDER=Embedding provider: openai-compatible endpoint or ollama · NOUZ_CONFIG=Absolute path to config.yaml; if omitted, server looks in current working directory · NOUZ_DATABASE_NAME=SQLite cache filename inside OBSIDIAN_ROOT · NOUZ_DATABASE_PATH=Full SQLite cache path; takes precedence over NOUZ_DATABASE_NAME · OBSIDIAN_ROOT=Path to Obsidian vault 1 0.0 %
EMBED_MODEL=Embedding model identifier (for retrieval + memory). Default 'text-embedding-3-small'; use 'nomic-embed-text' on Ollama. · ENABLE_FETCH=Set to '0' to skip the trafilatura full-page fetch stage. Default '1'. · ENABLE_RERANK=Set to '1' to enable the BAAI/bge-reranker-v2-m3 cross-encoder rerank stage. First run downloads ~560MB. · LOCAL_CORPUS_PATH=Path to an index directory built via scripts/index_corpus.py. When set, local corpus hits augment web search. · MODEL_PLANNER=Model for the plan / classify / critic / compress / verify nodes. Defaults to 'gpt-5-nano'. · MODEL_SYNTHESIZER=Model identifier used for the synthesize node. Defaults to 'gpt-5-mini'; set to 'gemma3:4b' for Mac-local Ollama. · OPENAI_API_KEY=API key for the endpoint above. Use 'ollama' as a sentinel value when running locally against Ollama. · OPENAI_BASE_URL=Any OpenAI-compatible endpoint. Default: OpenAI cloud. Use http://localhost:11434/v1 for Ollama. · SEARXNG_URL=Base URL of the SearXNG meta-search instance. Default http://localhost:8888. 1 0.0 %
EMBER_AUTH_TOKEN=Credential for a remote inference endpoint · EMBER_SERVER_URL=Inference endpoint; defaults to the local model server at http://127.0.0.1:8765 1 0.0 %
EMEM_BIND=Bind address for the HTTP server. When unset, the entrypoint derives it from PORT, falling back to 0.0.0.0:5051. · EMEM_DATA=Path to the persistent data directory (sled cache + ed25519 identity). Mount a volume here; on managed platforms that mount /data, set EMEM_DATA=/data. · EMEM_PUBLIC_URL=Optional canonical origin for self-referencing URLs in MCP responses (e.g. https://emem.dev). When unset the server falls back to urn:emem. · EMEM_TLS_DOMAINS=Comma-separated hostnames for built-in Let's Encrypt ACME (TLS-ALPN-01). When set, the server binds 0.0.0.0:443 instead of EMEM_BIND. · PORT=PaaS port convention: the container entrypoint binds 0.0.0.0:$PORT when EMEM_BIND is not set explicitly. Falls back to 5051. 1 0.0 %
EMERGENCE_API_KEY=Your Emergence Science API key. Obtain one at https://emergence.science by clicking Connect. 1 0.0 %
EMFIRGE_BASE_URL=Backend URL — override to point at a self-hosted backend · EMFIRGE_PRIVACY=Tokenization mode: strict (default), balanced, or off 1 0.0 %
EMILE_API_KEY=API key generated from the Émile iOS app (Profile → Settings → API Keys). Starts with `emile_live_...`. · EMILE_API_URL=Optional override for the backend URL — only useful for local development against a self-hosted backend. · EMILE_LOG_LEVEL=Logging verbosity. One of: debug, info, warn, error. 1 0.0 %
EMPLYX_API_KEY=Your Emplyx API key (format: emplyx_live_xxx). Get one from Settings > API Keys in Emplyx admin panel. · EMPLYX_API_URL=Optional. Emplyx API endpoint URL. Defaults to https://api.emplyx.com 1 0.0 %
EMPTYINBOX_API_KEY=Existing EmptyInbox API key. Omit to auto-register a free account on the first tool call that needs one; the key is then written to ~/.emptyinbox.json. 1 0.0 %
EMP_API_ENDPOINT=Your Eulerian Marketing Platform MCP Endpoint · EMP_API_TOKEN=Your Eulerian Marketing Platform API key 1 0.0 %
EMULUXE_API_URL=Platform URL. Defaults to https://app.emuluxe.com. · EMULUXE_DEFAULT_NETWORK=Default network profile. Defaults to no-throttle. · EMULUXE_IDE=Which client this runs inside. Detected automatically; set it if detection fails. · EMULUXE_TOKEN=Your Emuluxe token: Dashboard > Integrations > CLI Access Tokens. 1 0.0 %
ENABLED_TOOLGROUPS=Comma-separated list of tool groups to enable (readonly or readwrite). · GCAL_IMPERSONATE_EMAIL=Email address of the user whose calendar to access via domain-wide delegation. · GCAL_SERVICE_ACCOUNT_CLIENT_EMAIL=Service account email address from Google Cloud Console. · GCAL_SERVICE_ACCOUNT_PRIVATE_KEY=Service account private key in PEM format from Google Cloud Console. 1 0.0 %
ENABLED_TOOLGROUPS=Comma-separated list of tool groups to enable (readonly, write). · SLACK_BOT_TOKEN=Slack Bot User OAuth Token starting with xoxb-. 1 0.0 %

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

Sheet 53 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=53