Skip to content

Environment variable descriptions (raw)

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

Value Entries Share
LIVEAUTH_API_BASE=Override for self-hosted LiveAuth. Defaults to https://api.liveauth.app. · LIVEAUTH_API_KEY=Your LiveAuth project public key (la_pk_…). · LIVEAUTH_DEMO=Force demo mode even with a key set. Defaults to false. 1 0.0 %
LIVENX_API_KEY=LiveNX API key · LIVENX_PROM_PASSWORD=LiveNX Prometheus password 1 0.0 %
LIVESPACE_API_KEY=Per-user Livespace API key. · LIVESPACE_API_SECRET=Per-user Livespace API secret. · LIVESPACE_MCP_ENABLE_WRITES=Expose write tools. Keep false unless writes are deliberately required. · LIVESPACE_SUBDOMAIN=Bare Livespace workspace subdomain, without protocol or domain suffix. · MCP_AUTH_TOKEN=Random bearer token of at least 32 bytes, also sent by the client. · MCP_PORT=Loopback port used by the local MCP server. · MCP_REQUEST_STATE_KEY=Random HMAC key of at least 32 bytes. Required when writes are enabled. 1 0.0 %
LIVETENNISAPI_KEY=Your Live Tennis API key (twjp_...). Get one free, no card, at https://livetennisapi.com/subscribe/free — the server runs without it but only the status check will work. 1 0.0 %
LIVEVARIANT_API_TOKEN=API token for a self-hosted deployment that sets LV_API_TOKEN. Not needed for the hosted service. · LIVEVARIANT_ASSET_UPLOAD_TOKEN=Asset upload token for a deployment with hosted images enabled. Optional. · LIVEVARIANT_SERVER_URL=Base URL of a self-hosted LiveVariant deployment. Omit to use the hosted service at https://livevariant.com. 1 0.0 %
LLAMAPARSE_API_KEY=Optional fallback backend; only required for llamaparse routing 1 0.0 %
LLMC_API_KEY=LLM Conveyors API key (starts with llmc_). Get one at https://llmconveyors.com 1 0.0 %
LLMGRAPH_API_KEY=API key for the deployment · LLMGRAPH_ENDPOINT=Full deployment endpoint URL from the LLMGraph dashboard, e.g. https://llmgraph.ai/api/<graph_id>/<environment> 1 0.0 %
LLMKIT_API_KEY=LLMKit API key. Optional: local tools work without it. · LLMKIT_PROXY_URL=LLMKit proxy URL (defaults to hosted service) 1 0.0 %
LLMTEST_API_KEY=Your LLMTest API key from https://llmtest.io/dashboard 1 0.0 %
LLMVERIFY_AUDIT_DIR=Audit JSONL directory · LLMVERIFY_AUDIT_HASH_KEY=Enables keyed hmac-sha256 content hashes in audit records · LLMVERIFY_AUDIT_NO_CONTENT_HASH=Set to 1 to disable content hashes in audit records · LLMVERIFY_BASELINE_DIR=Drift baseline directory · LLMVERIFY_HOME=Base directory for engine local state · LLMVERIFY_LOG_DIR=Operational log directory · LLMVERIFY_MCP_MAX_INPUT_CHARS=Max characters accepted in a content/input argument · LLMVERIFY_MCP_MAX_OUTPUT_ITEMS=Cap on any single output array · LLMVERIFY_MCP_MAX_TEXT_FIELD_CHARS=Cap on any single text field in output · LLMVERIFY_MCP_TIMEOUT_MS=Per-tool wall-clock timeout in milliseconds · LLMVERIFY_USAGE_FILE=Usage counter file 1 0.0 %
LLM_API_KEY=API key for an OpenAI-compatible LLM provider, used for entity/relation extraction · LLM_BASE_URL=OpenAI-compatible base URL · LLM_MODEL=Model name for extraction 1 0.0 %
LLM_API_KEY=API key for the LLM provider (not needed for local Ollama) · LLM_API_URL=LLM API endpoint URL (OpenAI-compatible or Anthropic) · LLM_MODEL=Model name/ID to use for optimization 1 0.0 %
LLM_API_KEY=LLM API Key (OpenAI compatible) · LLM_BASE_URL=LLM Base URL (OpenAI compatible) · LLM_MODEL=LLM model name 1 0.0 %
LLM_KEY=OpenRouter API key (sk-or-v1-...). Required for LLM analysis steps. · LLM_MODEL=OpenRouter model ID for analysis steps. · MOVA_API_KEY=MOVA API key. Use test-key-001 to get started without registration. · MOVA_API_URL=Override the MOVA API base URL. 1 0.0 %
LLM_ORACLE_LOCAL_ONLY=Set to any value to skip remote fetch and use bundled catalog only · LLM_ORACLE_URL=Override the remote catalog URL (default https://oracle.weiseer.com/catalog.json) 1 0.0 %
LLW_BASE_URL=Model server URL (Ollama, llama.cpp, LM Studio, vLLM). Default http://localhost:11434 · LLW_MODEL=Model to use; optional if the server has only one · LLW_SEARCH_URL=SearXNG URL for web research (optional) 1 0.0 %
LMCP_REF=Install-source attribution tag (fixed). 1 0.0 %
LMP_API_BASE=Override for self-hosted deployments. Defaults to https://api.letmepost.dev. · LMP_API_KEY=Your letmepost.dev API key (lmp_live_... or lmp_test_...). Create one at https://dashboard.letmepost.dev/api-keys. 1 0.0 %
LM_ACCESS_ID=LMv1 API access ID (required for log/metric ingestion) · LM_ACCESS_KEY=LMv1 API access key (required for log/metric ingestion) · LM_BEARER_TOKEN=LogicMonitor API Bearer token · LM_DISABLED_TOOLS=Comma-separated tool names or glob patterns to disable (e.g., delete_*) · LM_ENABLED_TOOLS=Comma-separated tool names or glob patterns to enable (e.g., get_*,create_device) · LM_ENABLE_WRITE_OPERATIONS=Enable write operations (create, update, delete) · LM_LOG_LEVEL=Logging level for API request debugging (debug, info, warning, error) · LM_PORTAL=LogicMonitor portal hostname (e.g., company.logicmonitor.com) 1 0.0 %
LM_DATA_ROOT=Directory for per-namespace SQLite memory files. Defaults to ~/.lean_memory when unset. 1 0.0 %
LOADBEARING_SOLUTION_PATH=Path to the solution to check when no solution argument is passed. A config generated from this manifest passes none, so this is where a repository the walk-up cannot resolve binds: set it at install time, or the server starts unbound and its session works from the CLI alone, spelled through dnx because launching this way installs no loadbearing command. 1 0.0 %
LOC8N_API_KEY=API key for the loc8n Geographic Data API 1 0.0 %
LOCALGYM_API_BASE=Optional LocalGym API base URL override; defaults to https://localgym.uk. · LOCALGYM_MCP_RATE_LIMIT_MAX=Optional local MCP client-side rate limit per window; defaults to 60. The public API also enforces server-side limits. · LOCALGYM_MCP_RATE_LIMIT_WINDOW_MS=Optional local MCP client-side rate limit window in milliseconds; defaults to 60000. 1 0.0 %
LOCALKEEP_DATA_DIR=Optional directory for the SQLite DB (default: ~/.localkeep) · LOCALKEEP_DB_PATH=Optional full path to localkeep.db 1 0.0 %
LOCAL_API_KEY=Optional bearer token, openai backend only; sent as a header, never logged · LOCAL_BACKEND=Backend to use: ollama, vllm or openai · LOCAL_EMBED_MODEL=Default embedding model · LOCAL_EMBED_PATH=Optional, openai backend only: embedding endpoint path · LOCAL_HOST=Model endpoint URL; must be local or on your own network. Required for the openai backend · LOCAL_SCHEMA_MODE=Optional, openai backend only: auto, response_format or none · LOCAL_TIMEOUT=Read timeout in seconds 1 0.0 %
LOCAL_DEFAULT_BLOG_ID=Default blog ID for multisite · LOCAL_DEFAULT_SITE_ID=Default site ID for multisite · LOCAL_MULTISITE=Enable WordPress multisite mode · LOCAL_SSL_CA_FILEPATH=Path to SSL CA certificate file · LOCAL_SSL_CERT_FILEPATH=Path to SSL certificate file · LOCAL_SSL_ENABLED=Enable SSL for database connection · LOCAL_SSL_KEY_FILEPATH=Path to SSL key file · LOCAL_USERNAME=WordPress username to assume for capability checks · WP_DB_HOST=WordPress database host · WP_DB_NAME=WordPress database name · WP_DB_PASSWORD=WordPress database password · WP_DB_PORT=WordPress database port · WP_DB_USER=WordPress database user 1 0.0 %
LOCAL_DELEGATE_API_KEY=Bearer token for the endpoint, if it requires one. · LOCAL_DELEGATE_BASE_URL=OpenAI-compatible endpoint (llama-swap, Ollama, LM Studio, vLLM). Default http://127.0.0.1:9292/v1 1 0.0 %
LOCAL_EMBEDDING_MODEL=Local embedding model used when no remote embedding API is configured. · OBSIDIAN_IGNORE_PATTERNS=Comma-separated glob patterns to exclude from indexing. · OBSIDIAN_INCLUDE_PATTERNS=Comma-separated patterns to re-include notes ignored only by .gitignore. · OBSIDIAN_PREFIX=Optional prefix for MCP tool names when configuring multiple vaults. · OBSIDIAN_RESPECT_GITIGNORE=Read root and nested .gitignore files when indexing; set to false, 0, or no to disable. · OBSIDIAN_VAULT_PATH=Absolute path to the Obsidian vault to index and search. · OPENAI_API_KEY=Optional API key for OpenAI-compatible remote embeddings; omit to use local embeddings. · OPENAI_BASE_URL=Optional OpenAI-compatible API base URL for OpenRouter, Ollama, LM Studio, or similar providers. · OPENAI_EMBEDDING_MODEL=Remote embedding model name when using an OpenAI-compatible API. · RERANKER_MODEL=Optional ONNX cross-encoder reranker model used when reranking is requested. 1 0.0 %
LOCAL_YDB_MCP_CONTENT_FORMAT=Optional LLM-facing tool response text format. Use toon to prefer TOON for the second text content block, with JSON fallback if TOON cannot round-trip losslessly; omit or set json for pretty JSON. MCP JSON-RPC and structuredContent stay JSON. · LOCAL_YDB_TOOLKIT_CONFIG=Optional path to a local-ydb-toolkit config JSON file. 1 0.0 %
LOCKSTEP_VENDOR=Agent vendor label used for session registration (e.g. claude-code, cursor). Optional; defaults to unknown. 1 0.0 %
LOC_LOG_LEVEL=silent, error, info or debug. Default error. Logs go to stderr. · LOC_MIN_INTERVAL_MS=Minimum milliseconds between requests. Default 6000, floor 3000. · LOC_NEWSPAPER_TIMEOUT_MS=Deadline for one search_newspapers request, in milliseconds. The full-text corpus answers in tens of seconds. Default 90000. · LOC_TIMEOUT_MS=Deadline for one catalogue, record or collection request, in milliseconds. Default 30000. · LOC_USER_AGENT=Identify your own client. The project's own identifier is appended, so the Library can always reach a human. 1 0.0 %
LOC_REQUEST_DELAY_MS=Delay in milliseconds between LOC API requests to stay under the 20 req/min rate limit. · LOC_USER_AGENT=User-Agent header sent with LOC API requests. LOC recommends a descriptive value for polite access. · 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_SESSION_MODE=HTTP session mode: auto, stateful, or stateless. · MCP_TRANSPORT_TYPE=Selects the HTTP transport. 1 0.0 %
LODD_API_KEY=Lodd API key. Get one at https://lodd.dev 1 0.0 %
LOG10X_API_KEY=Log10x API key. Without it the server boots read-only against the public demo dataset. 1 0.0 %
LOGCLAW_API_KEY=Your LogClaw project API key (starts with lc_proj_) · LOGCLAW_ENDPOINT=LogClaw auth proxy endpoint (default: https://ticket.logclaw.ai) 1 0.0 %
LOGGLY_SUBDOMAIN=Loggly account subdomain or full Loggly URL (e.g. your-subdomain or https://your-subdomain.loggly.com). · LOGGLY_TOKEN=Loggly API token (read access). 1 0.0 %
LOGICNODES_API_KEY=Optional prepay API key. Not required — x402 pay-per-call is the default. 1 0.0 %
LOGISHEETS_MCP_TOOLS=Tool surface: 'core' (default, 32 tools) or 'full', which adds formatting, comments, links, undo/redo and raw structure operations. 1 0.0 %
LOGI_AGENT_PRIVATE_KEY=Ed25519 private key PEM for signed mode (recommended). · LOGI_AGENT_PUBLIC_ID=Public agent id (agt_...). · LOGI_AGENT_TOKEN=Bearer token issued at agent registration (start.1pass.dev developer console). · LOGI_API_URL=logi API base URL. Defaults to https://api.1pass.dev. 1 0.0 %
LOGI_API_KEY=Personal API Key (logi_pak_...). Issue one at https://start.1pass.dev -> Settings -> API Keys, or via `logi login` CLI. Docs tools work without it. · LOGI_API_URL=logi API base URL. Defaults to https://start.1pass.dev. 1 0.0 %
LOGLY_API_KEY=Your Logly API key — create one in Settings → API keys. 1 0.0 %
LOGSLOOM_API_KEY=Project API key (lb_live_…). Required for stdio. · LOGSLOOM_API_URL=LogsLoom HTTP API origin. 1 0.0 %
LOGS_DIR=Directory for file-based logs (Node only; ignored on Workers). · 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_REQUEST_STATE_KEY=Recommended for HTTP. Key (>= 32 bytes, the same on every instance) that seals the requestState carrying the consent-record id of a confirmation prompt, bound to the caller for 900 s; a forged, tampered, or expired state is rejected before the handler runs. · MCP_SESSION_MODE=HTTP session model: 'auto', 'stateful', or 'stateless'. This server requires 'stateful' over HTTP — the consent prompt on destructive and outbound calls is a multi-round-trip request that a 2025-era HTTP client can only complete over a live session — so an HTTP start with 'stateless' is refused. 'auto' resolves to 'stateful'; stdio ignores the setting. · MCP_TRANSPORT_TYPE=Selects the HTTP transport. · NTFY_AUTH_PASSWORD=Basic-auth password for the single-server shorthand — must be set together with NTFY_AUTH_USERNAME. · NTFY_AUTH_TOKEN=Bearer access token (`tk_…`) for the single-server shorthand. Mutually exclusive with NTFY_AUTH_USERNAME / NTFY_AUTH_PASSWORD. · NTFY_AUTH_USERNAME=Basic-auth username for the single-server shorthand — must be set together with NTFY_AUTH_PASSWORD. · NTFY_BASE_URL=Single-server shorthand — base URL of the ntfy server (no trailing slash). Used when NTFY_SERVERS is unset. · NTFY_BLOCK_PRIVATE_HOSTS=When true, a per-call `base_url` override must resolve to a public address and its redirects are not followed. Servers registered under NTFY_SERVERS / NTFY_BASE_URL are exempt. Turn it on where callers you do not control can reach the server. · NTFY_DEFAULT_TOPIC=Topic used when a tool call omits `topic`. Treat the topic name as a secret — anyone who knows it can publish or subscribe. · NTFY_MAX_RETRIES=Max retry attempts for transient upstream failures (5xx, network, 429). · NTFY_REQUEST_TIMEOUT_MS=Per-request HTTP timeout in milliseconds. · NTFY_SERVERS=JSON array of `{ baseUrl, authToken? | authUsername?+authPassword? }` entries — one per ntfy server. First entry is the default base. Auth is scoped to the entry's `baseUrl`; per-call `base_url` overrides that match a registered base forward that server's auth. Takes precedence over the single-server NTFY_BASE_URL / NTFY_AUTH_* shorthand. · OTEL_ENABLED=Enable OpenTelemetry instrumentation (spans, metrics, completion logs). 1 0.0 %
LOG_DIR=Directory for audit logs (default: ./logs) · OBSIDIAN_API_KEY=API Key generated by Obsidian's Local REST API plugin (Settings -> Local REST API -> API Key) · OBSIDIAN_HOST=Host of the Local REST API (default: http://127.0.0.1) · OBSIDIAN_PORT=Port of the Local REST API (default: 27123) 1 0.0 %
LOG_LEVEL=Log level - error, info, or debug (optional, defaults to error) · MAKE_API_KEY=Make.com API key for scenario deployment (optional - only needed for create_scenario tool) · MAKE_API_URL=Make.com API URL - defaults to https://eu1.make.com/api/v2 (optional) · MAKE_TEAM_ID=Make.com Team ID for scenario deployment (optional) 1 0.0 %
LOG_LEVEL=Log level. Logs go to stderr. · MCP_ADDITIONAL_PATH_PREFIXES=Extra content roots to allow besides /Game, /Engine, /Script, /Temp and /Niagara, comma-separated. Example: /MyPluginContent/ · MCP_AUTOMATION_ALLOW_NON_LOOPBACK=SECURITY: allow a non-loopback MCP_AUTOMATION_HOST. Enable only on a trusted network. · MCP_AUTOMATION_CAPABILITY_TOKEN=Capability token to present to the editor. Only needed when the server cannot read the project folder, for example over LAN. · MCP_AUTOMATION_HOST=Editor host to connect to. A LAN address also needs MCP_AUTOMATION_ALLOW_NON_LOOPBACK=true and Allow Non Loopback in the plugin settings. · MCP_AUTOMATION_MAX_MESSAGES_PER_MINUTE=Inbound messages per minute from the editor before the server disconnects. · MCP_AUTOMATION_PORT=Editor WebSocket port. Default: the first Listen Ports entry in the project settings, else 8090. · MCP_AUTOMATION_USE_TLS=Connect with wss:// instead of ws://. · MCP_CONNECTION_TIMEOUT_MS=How long to wait for the editor connection, in milliseconds. · MCP_REQUEST_TIMEOUT_MS=Overrides every per-capability request timeout, in milliseconds. Leave unset: each capability gets a budget that fits its cost. · UE_PROJECT_PATH=Your Unreal project folder or its .uproject file. The server reads the capability token from <project>/Saved/MCP/capability-token and the WebSocket port from the project settings. 1 0.0 %
LOG_LEVEL=Log verbosity; all logs go to stderr. · PEXELS_API_KEY=Your Pexels API key (sent as the Authorization header, no prefix). 1 0.0 %
LOG_LEVEL=Log verbosity; all logs go to stderr. · PIXABAY_API_KEY=Your Pixabay API key (sent as the `key` query parameter — Pixabay has no header option). 1 0.0 %
LOG_LEVEL=Log verbosity; all logs go to stderr. · UNSPLASH_ACCESS_KEY=Your Unsplash API access key (sent as Authorization: Client-ID). · UNSPLASH_APP_NAME=Registered Unsplash app name, used as the attribution utm_source. 1 0.0 %

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

Sheet 86 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=86