Zum Inhalt springen

Beschreibungen der Umgebungsvariablen (Rohangabe)

7.577 verschiedene Werte, gemessen an 42.703 ausgelieferten Einträgen.

Wert Einträge Anteil
ANTHROPIC_API_KEY=Anthropic API key for AI-powered risk scoring 1 0.0 %
ANTHROPIC_API_KEY=Anthropic API key for AI-powered suggestions (optional — free heuristic scoring works without it) 1 0.0 %
ANTHROPIC_API_KEY=Anthropic API key for AI-powered tender scoring 1 0.0 %
ANTHROPIC_API_KEY=Anthropic API key for AI-powered tools · CSVBOX_API_KEY=CSVBox API key · CSVBOX_API_SECRET=CSVBox API secret · OPENAI_API_KEY=OpenAI API key for AI-powered tools 1 0.0 %
ANTHROPIC_API_KEY=Anthropic API key for Claude AI models · CLAUDE_FLOW_MAX_AGENTS=Maximum number of concurrent agents · CLAUDE_FLOW_MEMORY_PATH=Path for persistent memory storage · CLAUDE_FLOW_MODE=Operation mode: development, production, or test · CLAUDE_FLOW_PORT=MCP server port · FLOW_NEXUS_API_KEY=Flow Nexus cloud platform API key · GITHUB_TOKEN=GitHub personal access token for repository operations 1 0.0 %
ANTHROPIC_API_KEY=Anthropic API key for Claude Code workers. Set this or CLAUDE_CODE_OAUTH_TOKEN. · CHARGEHAND_PROFILE=A profile/v1 file for budgets, prices, memory or a pinned runtime version. · CHARGEHAND_RUNTIME=Worker runtime, when both or neither of claude and opencode are on PATH. · CLAUDE_CODE_OAUTH_TOKEN=Claude Code subscription token from claude setup-token. Set this or ANTHROPIC_API_KEY. 1 0.0 %
ANTHROPIC_API_KEY=Anthropic API key for Claude integration · E2B_API_KEY=E2B API key for sandbox creation · FLOW_NEXUS_API_KEY=API key for Flow Nexus authentication · FLOW_NEXUS_BASE_URL=Base URL for Flow Nexus API 1 0.0 %
ANTHROPIC_API_KEY=Anthropic API key for Claude model access · GITHUB_TOKEN=GitHub token for repository access · SUGAR_DEFAULT_REPO=Default repository in owner/repo format 1 0.0 %
ANTHROPIC_API_KEY=Anthropic API key for Claude models (optional - at least one provider required) · DEFAULT_MODEL=Default model to use (defaults to gpt-5-mini) · DEFAULT_MODEL_LIST=Default models for multi-model comparison (comma-separated, defaults to gpt-5-mini,gemini-3-flash) · GEMINI_API_KEY=Google API key for Gemini models (optional - at least one provider required) · OPENAI_API_KEY=OpenAI API key for GPT models (optional - at least one provider required) · OPENROUTER_API_KEY=OpenRouter API key for additional models (optional) 1 0.0 %
ANTHROPIC_API_KEY=Anthropic API key for Claude models · LITELLM_API_BASE=LiteLLM Proxy base URL (optional) · LITELLM_API_KEY=LiteLLM Proxy API key (optional) · OPENAI_API_KEY=OpenAI API key for GPT models 1 0.0 %
ANTHROPIC_API_KEY=Anthropic API key for Claude models · OPENAI_API_KEY=OpenAI API key for GPT models 1 0.0 %
ANTHROPIC_API_KEY=Anthropic API key for Claude recommendations · GEMINI_API_KEY=Google API key for Gemini recommendations 1 0.0 %
ANTHROPIC_API_KEY=Anthropic API key for Claude routing analysis 1 0.0 %
ANTHROPIC_API_KEY=Anthropic API key for Claude-based features · AZURE_OPENAI_API_KEY=Azure OpenAI API key (alternative to OpenAI) · BIOGRID_API_KEY=BioGRID API key for protein-protein interaction queries. Register free at https://webservice.thebiogrid.org/ · BRENDA_EMAIL=BRENDA enzyme database login email. Register at https://www.brenda-enzymes.org/ · BRENDA_PASSWORD=BRENDA enzyme database login password · DISGENET_API_KEY=DisGeNET API key for gene-disease association data. Register free at https://www.disgenet.org/ · GEMINI_API_KEY=Google Gemini API key for Gemini-based features · HF_TOKEN=HuggingFace token for accessing models and datasets · NCBI_API_KEY=NCBI/PubMed API key for higher rate limits (10 req/sec vs 3 req/sec). Register at https://www.ncbi.nlm.nih.gov/account/ · NVIDIA_API_KEY=NVIDIA NIM API key for AlphaFold2 structure prediction, molecular docking, and genomics tools. Get key at https://build.nvidia.com · OMIM_API_KEY=OMIM API key for Mendelian disease data. Register at https://omim.org/api · ONCOKB_API_TOKEN=OncoKB API token for precision oncology annotations. Register at https://www.oncokb.org/apiAccess · OPENAI_API_KEY=OpenAI API key for LLM-based tool finding and embedding features · OPENROUTER_API_KEY=OpenRouter API key for accessing 100+ LLM models · SEMANTIC_SCHOLAR_API_KEY=Semantic Scholar API key for higher rate limits (100 req/sec vs 1 req/sec). Register at https://www.semanticscholar.org/product/api · UMLS_API_KEY=UMLS API key for medical terminology and concept mapping. Register at https://uts.nlm.nih.gov/uts/ · USPTO_API_KEY=USPTO API key for patent data access. Register at https://developer.uspto.gov/ 1 0.0 %
ANTHROPIC_API_KEY=Anthropic API key for LLM answer generation · DARWIN_BASE_DIR=Override the base data directory · GEMINI_API_KEY=Google Gemini API key · OPENAI_API_KEY=OpenAI API key for LLM answer generation 1 0.0 %
ANTHROPIC_API_KEY=Anthropic API key for LLM-based memory processing (optional) · GENESYS_EMBEDDER=Embedding provider: 'openai' or 'local' (default: openai) · OPENAI_API_KEY=OpenAI API key for embedding generation (optional — use GENESYS_EMBEDDER=local for no API key) 1 0.0 %
ANTHROPIC_API_KEY=Anthropic API key for LLM-based risk assessment (alternative to OpenAI) · CACHE_TTL=Cache time-to-live in seconds for vulnerability data (default: 900) · GITHUB_TOKEN=GitHub token for Advisory Database access (increases rate limit to 5000 requests per hour) · MCP_PORT=Port for MCP HTTP server (default: 3000) · NVD_API_KEY=API key for NIST National Vulnerability Database (increases rate limit from 5 to 50 requests per 30 seconds) · OPENAI_API_KEY=OpenAI API key for LLM-based risk assessment in MCP passthrough operations · VULNICHECK_HTTP_ONLY=Enable HTTP-only mode with MCP client delegation (true/false, default: auto-detect) 1 0.0 %
ANTHROPIC_API_KEY=Anthropic API key for LLM-powered semantic analysis · DATARAUM_HOME=Root directory for workspaces, sessions, and exports 1 0.0 %
ANTHROPIC_API_KEY=Anthropic API key for LLM-powered tools (generate_machine, generate_multi_machine, refine_machine, generate_actions with use_llm). Not required for parse_machine, verify_machine, compile_machine, or server_status. · ORCA_MODEL=Model name to use for LLM tools. Defaults to claude-sonnet-4-6 for Anthropic. · ORCA_PROVIDER=LLM provider to use: anthropic (default), openai, grok, or ollama. 1 0.0 %
ANTHROPIC_API_KEY=Anthropic API key for Premium grammar checking; optional when api_key is supplied per call. · GEMINI_API_KEY=Google Gemini API key for grammar checking; optional when api_key is supplied per call. · OPENAI_API_KEY=OpenAI API key for Premium grammar checking; optional when api_key is supplied per call. 1 0.0 %
ANTHROPIC_API_KEY=Anthropic API key for classifying and scoring signals. · GITHUB_PAT=GitHub Personal Access Token for scanning repos and issues. 1 0.0 %
ANTHROPIC_API_KEY=Anthropic API key for live LLM extraction/reasoning. Without it the server runs in a heuristic-only fallback mode. 1 0.0 %
ANTHROPIC_API_KEY=Anthropic API key for local, unlimited analysis (or use `vaspera-pm connect` for managed usage). · VASPERA_API_KEY=VasperaPM Cloud key for managed usage tracking and team features. 1 0.0 %
ANTHROPIC_API_KEY=Anthropic API key for optional LLM-assisted selector repair. · CHROME_PATH=Absolute path to the Chrome binary. Auto-detected on Windows/macOS/Linux when omitted. · GITHUB_TOKEN=Optional token that raises GitHub API limits for repository inspection. · ORCAROUTER_API_KEY=OrcaRouter API key for optional LLM-assisted selector repair. · SEARCH_API=SearchApi API key. Required only for SearchApi primary or fallback modes. · SURF_ALLOW_PRIVATE=Set to 'true' to allow extract on private/loopback addresses (localhost, 10.x, 192.168.x, 169.254.x, etc). Default blocks them as an SSRF guard. · SURF_BROWSER_ENGINE=Browser engine: auto, native, or playwright. Auto uses one hidden native Chrome broker shared across local MCP sessions. · SURF_HEADLESS=Controls Playwright extraction, compatibility, and recovery paths. Native search hides normal system Chrome and shows it only for CAPTCHA recovery. · SURF_IDLE_CLOSE_MS=Idle ms before closing the sequential ctx and pool. 0 disables idle auto-close. Defaults to 30000. · SURF_LLM_HEAL=Enable the optional workflow-only LLM selector repair path. Defaults to false. · SURF_LLM_MODEL=Optional model override. OrcaRouter defaults to orcarouter/auto. · SURF_LLM_PROVIDER=LLM selector repair provider: anthropic or orcarouter. Defaults to anthropic. · SURF_LOCALE=Browser locale, e.g. en-US. · SURF_PROFILE_ROOT=Directory for the warm Chrome profile. Defaults to ~/.google-surf-mcp. · SURF_RESEARCH=Enable local project memory and hybrid retrieval. Defaults to true. · SURF_RESEARCH_BROKER_IDLE_MS=Shared research broker idle lifetime in milliseconds. Defaults to 60000. · SURF_RESEARCH_QUERY_TIMEOUT_MS=Timeout per embedded SurrealDB query in milliseconds. Defaults to 120000; timed-out retrieval lanes are reported as partial. · SURF_RESEARCH_READ_CONCURRENCY=Maximum concurrent research broker reads. Defaults to 4. · SURF_RESEARCH_REPO_AUTO=Sparse-index at most one eligible small GitHub repository per search call. Defaults to true. · SURF_RESEARCH_REPO_AUTO_MAX_FILES=Maximum repository source file count for automatic indexing. Defaults to 2000. · SURF_RESEARCH_REPO_AUTO_MAX_MB=Maximum searchable repository source-text size in MB. Assets are excluded. Defaults to 20. · SURF_RESEARCH_ROOT=Embedded SurrealDB data directory. Defaults to <profile>/research. · SURF_RESEARCH_VECTOR_LOW_MEMORY=Disable ONNX CPU memory arena and memory pattern. Defaults to true. · SURF_RESEARCH_VECTOR_MODEL=Local model for HNSW retrieval and shared reranking. Defaults to Xenova/multilingual-e5-small; use off to disable. · SURF_RESEARCH_VECTOR_THREADS=ONNX intra-op thread count from 1 to 16. Defaults to 4. · SURF_RETRIEVAL_MODE=Shared route for search and search_parallel: live or hybrid. Defaults to hybrid. · SURF_SCHOLAR_PROVIDER=Provider for scholar_search: browser, searchapi, or fallback. Defaults to browser. · SURF_SEARCH_PROVIDER=Provider for search and search_parallel: browser, searchapi, or fallback. Defaults to browser. · SURF_TZ=IANA timezone, e.g. America/New_York. Defaults to system timezone. 1 0.0 %
ANTHROPIC_API_KEY=Anthropic API key for running churn analysis (required for analyze_churn, analyze_stripe_churn, and analyze_sql_churn; get_example_analysis works without it). · MYSQL_URL=MySQL connection string for analyze_sql_churn when dialect='mysql'. Format: mysql://user:pass@host:3306/db?ssl=true. Use a READ-ONLY user — see retentioncheck.com/integrations for the exact GRANT SQL. Optional — only required for the analyze_sql_churn tool with mysql dialect. · POSTGRES_URL=Postgres connection string for analyze_sql_churn when dialect='postgres'. Format: postgres://user:pass@host:5432/db?sslmode=require. Use a READ-ONLY user — see retentioncheck.com/integrations for the exact GRANT SQL. Optional — only required for the analyze_sql_churn tool with postgres dialect. · RETENTIONCHECK_TELEMETRY=Set to 0 to opt out of anonymous usage telemetry. Telemetry tracks tool invocations and aggregate counts — never the feedback text, financial values, or any PII. · STRIPE_SECRET_KEY=Stripe API key for analyze_stripe_churn. Use a RESTRICTED (read-only) key with these permissions: Subscriptions Read, Customers Read, Prices Read. Create one at https://dashboard.stripe.com/apikeys/create. Optional — only required for the analyze_stripe_churn tool. 1 0.0 %
ANTHROPIC_API_KEY=Anthropic API key for session summarization and rule extraction. Not required for search, list, show, or rules tools. · OPENAI_API_KEY=OpenAI API key (alternative to Anthropic) for summarization. 1 0.0 %
ANTHROPIC_API_KEY=Anthropic API key for summary generation · AZURE_OPENAI_API_KEY=Azure OpenAI API key · AZURE_OPENAI_API_VERSION=Azure OpenAI API version (default: 2024-02-01) · AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAME=Azure OpenAI embedding deployment name · AZURE_OPENAI_ENDPOINT=Azure OpenAI endpoint URL · CHUNK_AGGREGATION=Chunk score aggregation method: max (only 'max' supported in current version) · CHUNK_DEDUP_OVERFETCH=Multiplier for over-fetching chunks before deduplication (default: 5) · CHUNK_OVERLAP=Overlap between chunks in characters (default: 150) · CHUNK_SIZE=Target chunk size in characters (default: 1500) · CIRCUIT_BREAKER_FAILURE_THRESHOLD=Circuit breaker failure threshold before opening · CIRCUIT_BREAKER_HALF_OPEN_MAX_CALLS=Maximum calls allowed in circuit breaker half-open state · CIRCUIT_BREAKER_RECOVERY_TIMEOUT_S=Circuit breaker recovery timeout in seconds · DB_PATH=Custom database file location path · DISABLED_TOOLS=Comma-separated list of tools to disable (e.g., delete_context,update_context) · EMBEDDING_DIM=Embedding vector dimensions · EMBEDDING_MAX_CONCURRENT=Maximum concurrent embedding generation operations (default: 3, range: 1-20) · EMBEDDING_MODEL=Embedding model name for semantic search · EMBEDDING_OLLAMA_NUM_CTX=Ollama embedding context window size in tokens (default: 4096, range: 512-2097152) · EMBEDDING_OLLAMA_TRUNCATE=Ollama embedding truncation mode: false (default) returns error when context exceeded, true enables silent truncation · EMBEDDING_PROVIDER=Embedding provider: ollama (default), openai, azure, huggingface, or voyage · EMBEDDING_RETRY_BASE_DELAY_S=Base delay in seconds between retry attempts (with exponential backoff) · EMBEDDING_RETRY_MAX_ATTEMPTS=Maximum number of retry attempts for embedding generation · EMBEDDING_TIMEOUT_S=Timeout in seconds for embedding generation API calls · ENABLE_CHUNKING=Enable text chunking for embedding generation (default: true) · ENABLE_EMBEDDING_GENERATION=Enable embedding generation for stored context. Default true - server fails if dependencies not met. Set false to disable embeddings. · ENABLE_FTS=Enable full-text search functionality · ENABLE_HYBRID_SEARCH=Enable hybrid search combining FTS and semantic search with RRF fusion · ENABLE_RERANKING=Enable cross-encoder reranking of search results (default: true) · ENABLE_SEMANTIC_SEARCH=Enable semantic search functionality · ENABLE_SUMMARY_GENERATION=Enable summary generation for stored context. Default true - server fails if dependencies not met. Set false to disable summaries. · FASTMCP_HOST=HTTP bind address (use 0.0.0.0 for Docker) · FASTMCP_PORT=HTTP port number · FASTMCP_STATELESS_HTTP=Enable stateless HTTP mode for horizontal scaling. Enabled by default as the server has no stateful MCP features. Set to false only if you need server-side MCP session tracking. · FTS_LANGUAGE=Language for FTS stemming (e.g., english, german, french) · FTS_RERANK_GAP_MERGE=Merge FTS match regions within this character distance (default: 100) · FTS_RERANK_WINDOW_SIZE=Characters of context around each FTS match for reranking passage extraction (default: 750) · HUGGINGFACEHUB_API_TOKEN=HuggingFace Hub API token for HuggingFace embedding provider · HYBRID_FTS_OR_THRESHOLD=Minimum significant query terms to switch hybrid FTS from AND to OR logic (default: 4) · HYBRID_RRF_K=RRF smoothing constant for hybrid search (default 60) · HYBRID_RRF_OVERFETCH=Multiplier for over-fetching results before RRF fusion (default: 2) · LANGSMITH_API_KEY=LangSmith API key · LANGSMITH_ENDPOINT=LangSmith API endpoint URL · LANGSMITH_PROJECT=LangSmith project name · LANGSMITH_TRACING=Enable LangSmith tracing · LOG_LEVEL=Log level · MAX_IMAGE_SIZE_MB=Maximum individual image size in megabytes · MAX_TOTAL_SIZE_MB=Maximum total request size in megabytes · MCP_AUTH_CLIENT_ID=Client ID to assign to authenticated requests · MCP_AUTH_PROVIDER=Authentication provider: none (default), simple_token · MCP_AUTH_TOKEN=Bearer token for HTTP authentication (required when using SimpleTokenVerifier) · MCP_SERVER_INSTRUCTIONS=Custom server instructions text. Overrides built-in default. Set to empty string to disable. · MCP_TRANSPORT=Transport mode: stdio for local, http for Docker/remote · METADATA_INDEXED_FIELDS=Comma-separated list of metadata fields to index (field:type format) · METADATA_INDEX_SYNC_MODE=Index sync mode: strict (fail), auto (sync), warn (log), additive (default, add missing only) · OLLAMA_AUTO_PULL=Automatically pull missing Ollama models on startup (default: true) · OLLAMA_HOST=Ollama API host URL for embedding generation · OLLAMA_PULL_TIMEOUT_S=Timeout in seconds for pulling Ollama models (default: 900, range: 30-3600) · OPENAI_API_BASE=Custom base URL for OpenAI-compatible APIs · OPENAI_API_KEY=OpenAI API key for OpenAI embedding provider · OPENAI_ORGANIZATION=OpenAI organization ID · POOL_CONNECTION_TIMEOUT_S=Connection timeout in seconds · POOL_HEALTH_CHECK_INTERVAL_S=Connection health check interval in seconds · POOL_IDLE_TIMEOUT_S=Idle connection timeout in seconds · POOL_MAX_READERS=Maximum number of concurrent read connections in the pool · POOL_MAX_WRITERS=Maximum number of concurrent write connections in the pool · POSTGRESQL_COMMAND_TIMEOUT_S=PostgreSQL command execution timeout in seconds · POSTGRESQL_CONNECTION_STRING=Complete PostgreSQL connection string (overrides individual settings if provided) · POSTGRESQL_DATABASE=PostgreSQL database name · POSTGRESQL_HOST=PostgreSQL server host address · POSTGRESQL_MAX_CACHEABLE_STATEMENT_SIZE=Maximum size of statement to cache in bytes (default: 15360). Has no effect when statement_cache_size=0 · POSTGRESQL_MAX_CACHED_STATEMENT_LIFETIME_S=Maximum lifetime of cached prepared statements in seconds (default: 300). Has no effect when statement_cache_size=0 · POSTGRESQL_MAX_INACTIVE_LIFETIME_S=Close idle PostgreSQL connections after this many seconds (0 to disable, default: 300) · POSTGRESQL_MAX_QUERIES=Recycle PostgreSQL connections after this many queries (0 to disable, default: 10000) · POSTGRESQL_MIGRATION_TIMEOUT_S=Timeout in seconds for PostgreSQL migration operations (default: 300) · POSTGRESQL_PASSWORD=PostgreSQL database password · POSTGRESQL_POOL_MAX=PostgreSQL connection pool maximum size · POSTGRESQL_POOL_MIN=PostgreSQL connection pool minimum size · POSTGRESQL_POOL_TIMEOUT_S=PostgreSQL connection pool timeout in seconds · POSTGRESQL_PORT=PostgreSQL server port number · POSTGRESQL_SCHEMA=PostgreSQL schema name for table and index operations (default: public) · POSTGRESQL_SSL_MODE=PostgreSQL SSL mode (disable, allow, prefer, require, verify-ca, verify-full) · POSTGRESQL_STATEMENT_CACHE_SIZE=asyncpg prepared statement cache size. Set to 0 for external pooler compatibility (PgBouncer transaction mode, Pgpool-II, etc.). Default: 100 · POSTGRESQL_TCP_KEEPALIVES_COUNT=Number of failed TCP keepalive probes before connection is considered dead (0 to disable, default: 3) · POSTGRESQL_TCP_KEEPALIVES_IDLE_S=Seconds of idle time before sending first TCP keepalive probe (0 to disable, default: 15) · POSTGRESQL_TCP_KEEPALIVES_INTERVAL_S=Seconds between subsequent TCP keepalive probes (0 to disable, default: 5) · POSTGRESQL_USER=PostgreSQL database username · QUEUE_TIMEOUT_S=Queue operation timeout in seconds · QUEUE_TIMEOUT_TEST_S=Test mode queue timeout in seconds · RERANKING_BATCH_SIZE=Maximum passages per ONNX Runtime inference batch during reranking (default: 32) · RERANKING_CACHE_DIR=Directory for caching reranking models · RERANKING_CHARS_PER_TOKEN=Estimated characters per token for passage size validation (default: 4.0, range: 2.0-8.0) · RERANKING_CPU_MEM_ARENA=Enable ONNX Runtime CPU memory arena for reranking (default: false) · RERANKING_INTRA_OP_THREADS=ONNX Runtime intra-operation parallelism threads for reranking (default: 0 = auto-detect) · RERANKING_MAX_LENGTH=Maximum input length for reranking in tokens (default: 512) · RERANKING_MODEL=Reranking model name (default: ms-marco-MiniLM-L-12-v2) · RERANKING_OVERFETCH=Multiplier for over-fetching results before reranking (default: 4) · RERANKING_PROVIDER=Reranking provider (default: flashrank) · RETRY_BACKOFF_FACTOR=Exponential backoff multiplication factor for retries · RETRY_BASE_DELAY_S=Base delay in seconds between retry attempts · RETRY_JITTER=Enable random jitter in retry delays · RETRY_MAX_DELAY_S=Maximum delay in seconds between retry attempts · RETRY_MAX_RETRIES=Maximum number of retry attempts for failed operations · SEARCH_DEFAULT_SORT_BY=Default sort order for search results: relevance (only 'relevance' supported in current version) · SEARCH_TRUNCATION_LENGTH=Maximum character length for truncated text_content in search results (default: 300, range: 50-1000) · SHUTDOWN_TIMEOUT_S=Server shutdown timeout in seconds · SHUTDOWN_TIMEOUT_TEST_S=Test mode shutdown timeout in seconds · SQLITE_BUSY_TIMEOUT_MS=SQLite busy timeout in milliseconds · SQLITE_CACHE_SIZE=SQLite cache size (negative value for KB, positive for pages) · SQLITE_FOREIGN_KEYS=Enable SQLite foreign key constraints · SQLITE_JOURNAL_MODE=SQLite journal mode (e.g., WAL, DELETE) · SQLITE_MMAP_SIZE=SQLite memory-mapped I/O size in bytes · SQLITE_PAGE_SIZE=SQLite page size in bytes · SQLITE_SYNCHRONOUS=SQLite synchronous mode (e.g., NORMAL, FULL, OFF) · SQLITE_TEMP_STORE=SQLite temporary storage location (e.g., MEMORY, FILE) · SQLITE_WAL_AUTOCHECKPOINT=SQLite WAL autocheckpoint threshold in pages · SQLITE_WAL_CHECKPOINT=SQLite WAL checkpoint mode (e.g., PASSIVE, FULL, RESTART) · STORAGE_BACKEND=Storage backend type: sqlite (default) or postgresql · SUMMARY_ANTHROPIC_EFFORT=Effort level for Anthropic Claude models (default: none). Valid values: max, high, medium, low. Controls inference effort (adaptive thinking) · SUMMARY_MAX_CONCURRENT=Maximum concurrent summary generation operations (default: 3, range: 1-20) · SUMMARY_MAX_TOKENS=Maximum output tokens for summary generation (default: 4000, range: 50-16384). Increase if summaries are truncated by reasoning models · SUMMARY_MIN_CONTENT_LENGTH=Minimum text content length in characters to trigger summary generation (default: 500, range: 0-10000). Set to 0 to always generate. · SUMMARY_MODEL=Summary generation model name (default: qwen3:0.6b) · SUMMARY_OLLAMA_NUM_CTX=Ollama summary context window size in tokens (default: 32768, range: 512-2097152) · SUMMARY_OLLAMA_TRUNCATE=Ollama summary truncation mode: false (default) returns error when context exceeded, true enables silent truncation · SUMMARY_OPENAI_REASONING_EFFORT=Reasoning effort level for OpenAI reasoning models (default: low). Valid values vary by generation: gpt-5: low, medium, high; gpt-5.1+: none, low, medium, high, xhigh. Default low is universally valid across all generations · SUMMARY_PROMPT=Custom summarization prompt. Overrides the built-in default. Used as system message for the LLM. · SUMMARY_PROVIDER=Summary provider: ollama (default), openai, or anthropic · SUMMARY_RETRY_BASE_DELAY_S=Base delay in seconds between retry attempts (with exponential backoff) · SUMMARY_RETRY_MAX_ATTEMPTS=Maximum number of retry attempts for summary generation · SUMMARY_TIMEOUT_S=Timeout in seconds for summary generation API calls · VOYAGE_API_KEY=Voyage AI API key for Voyage embedding provider · VOYAGE_BATCH_SIZE=Voyage AI batch size for embedding requests · VOYAGE_TRUNCATION=Voyage AI truncation mode: false (default) returns error when context exceeded, true enables silent truncation 1 0.0 %
ANTHROPIC_API_KEY=Anthropic API key for the Claude engine · GOOGLE_API_KEY=Google API key for the Gemini engine · OPENAI_API_KEY=OpenAI API key for the ChatGPT engine · PERPLEXITY_API_KEY=Perplexity API key for the Perplexity engine 1 0.0 %
ANTHROPIC_API_KEY=Anthropic API key for the agent. Required because the default OpenEye agent uses Claude. Swap providers via src/models.ts if you want OPENAI/GROQ/GEMINI/etc. · OPENEYE_CONTEXT_API_KEY=Context API key. Only needed if OPENEYE_CONTEXT_OPTIN is true. · OPENEYE_CONTEXT_OPTIN=Set true to opt in to sharing trajectory data with Context's training pipeline. Default off. Loud opt-in by design — read docs/context-data.md before flipping. 1 0.0 %
ANTHROPIC_API_KEY=Anthropic API key for vision-LLM review. Optional — the deterministic audit needs no key, and Ollama, OpenAI or Google can be used instead. · GOOGLE_API_KEY=Google API key for vision-LLM review. Optional. · OPENAI_API_KEY=OpenAI API key for vision-LLM review. Optional. · OPENAI_BASE_URL=Override the OpenAI base URL to target an OpenAI-compatible endpoint. Optional. 1 0.0 %
ANTHROPIC_API_KEY=Anthropic API key used by Claude Haiku for hook synthesis and verification. · GITHUB_TOKEN=Optional. Personal access token used to enumerate the user's public and private GitHub repos during catalog sync. · GRAD_AGENT_HOME=Optional. Override the default ~/.grad-agent/ location for profile, programs, secrets, and data. · HF_TOKEN=Optional. HuggingFace token used to enumerate the user's published models and datasets during catalog sync. · LOR_LETTERHEAD_PATH=Optional. Absolute path to a letterhead / company logo image (.png / .jpg / .pdf) embedded at the top of Letters of Recommendation during LaTeX compile. Leave unset for a plain top block. Can also be set at runtime via the `set_letterhead` MCP tool. · LOR_LETTERHEAD_WIDTH=Optional. LaTeX length for the letterhead image width (e.g. '2.5in'). Used only when LOR_LETTERHEAD_PATH is set. · SMTP_FROM=Envelope From address for drafts emailed to the user's review inbox. · SMTP_PASSWORD=SMTP password. Gmail App Password recommended. · SMTP_PORT=SMTP port. · SMTP_SERVER=SMTP host for the review mailer. · SMTP_USERNAME=SMTP username; used as From address by default. 1 0.0 %
ANTHROPIC_API_KEY=Anthropic API key used to run the engine locally · MOTIF_RUNS_DIR=Directory for run logs (every prompt, response, iteration). Defaults to ~/.motif/runs. 1 0.0 %
ANTHROPIC_API_KEY=Anthropic API key when KOMA_PROVIDER=anthropic · DEEPSEEK_API_KEY=DeepSeek API key when KOMA_PROVIDER=deepseek · GEMINI_API_KEY=Google Gemini API key (used by the default provider) · KOMA_MODEL=Optional model override for the selected provider · KOMA_PROVIDER=LLM provider: openai, anthropic, google, deepseek, or ollama (default: google) · OPENAI_API_KEY=OpenAI API key when KOMA_PROVIDER=openai 1 0.0 %
ANTHROPIC_API_KEY=Anthropic API key · GEMINI_API_KEY=Gemini API key (recommended free tier) · GROQ_API_KEY=Groq API key · LOG_LEVEL=Log level (DEBUG, INFO, WARNING, ERROR) · OLLAMA_HOST=Ollama host URL · OPENAI_API_KEY=OpenAI API key · REDIS_URL=Redis URL for state persistence · TIMPS_AUTH=Enable API key authentication · TIMPS_MAX_AGENT_WORKERS=Max concurrent agent workers · TIMPS_MODEL_PATH=TIMPS model path for Ollama 1 0.0 %
ANTHROPIC_API_KEY=Anthropic API key · STRIPE_SECRET_KEY=Stripe secret key for billing 1 0.0 %
ANTHROPIC_API_KEY=Anthropic API key — auto-detected from shell env; override only · DEEPSEEK_API_KEY=DeepSeek API key — auto-detected from shell env; override only · GEMINI_API_KEY=Gemini API key — auto-detected from shell env; override only · OPENAI_API_KEY=OpenAI API key — auto-detected from shell env; override only · ORCHEX_API_URL=Override cloud API URL (optional, defaults to https://orchex.dev) 1 0.0 %
ANTHROPIC_API_KEY=Anthropic API key — enables vision features (describe_elements). Optional. 1 0.0 %
ANTHROPIC_API_KEY=Anthropic API key — required for RAG queries and LLM-based metric extraction · EMBEDDING_DIMENSIONS=Embedding vector dimension size (default: 1024) · EMBEDDING_MODEL=Sentence-transformer model name for embedding generation (default: Snowflake/snowflake-arctic-embed-l-v2.0) · MONGODB_URI=MongoDB connection string for PDF binary storage via GridFS (e.g. mongodb://localhost:27017) · POSTGRES_DSN=PostgreSQL connection string with pgvector extension (e.g. postgresql://esg:esg@localhost/esg_platform) 1 0.0 %
ANTHROPIC_API_KEY=Anthropic API key — required only for data-room ingestion (PDF→YAML). Optional for build/qc/lineage tools. 1 0.0 %
ANTHROPIC_API_KEY=Anthropic API key, only needed for the AI-assisted multi-target sweep tool · HIBP_API_KEY=Have I Been Pwned API key, enables breach and paste lookups · IPINFO_TOKEN=ipinfo.io token, enables IP geolocation and exposure reports · SHODAN_API_KEY=Shodan API key, enables internet-exposed device lookups · VIRUSTOTAL_API_KEY=VirusTotal API key, enables reputation checks on IPs, domains, URLs and file hashes 1 0.0 %
ANTHROPIC_API_KEY=Anthropic API key, used for the semantic analysis pass 1 0.0 %
ANTHROPIC_API_KEY=Anthropic API key, used only by compare_studies for live papers. compare_example and list_examples run offline without it. · NCBI_EMAIL=Contact email sent with PubMed/PMC E-utilities requests (NCBI asks callers to identify themselves). Optional. 1 0.0 %
ANTHROPIC_API_KEY=Anthropic API key. Only needed if you use extract_listing_improvements (which uses Claude Opus 4.7 for structured listing rewrites). · VOC_API_KEY=Shulex VOC OpenAPI key. Get a free one (100 calls/month, no credit card) at https://apps.voc.ai/openapi 1 0.0 %
ANTHROPIC_API_KEY=Anthropic API key. Optional — without it, Anthropic models are read from the public models.dev / LiteLLM catalogs instead of the live API. · GOOGLE_API_KEY=Google AI Studio / Gemini API key. Optional. · KOSHA_CACHE_TTL_HOURS=Override the discovery cache TTL. Defaults to 24 hours. · OPENAI_API_KEY=OpenAI API key. Optional — falls back to the public catalogs when absent. · OPENROUTER_API_KEY=OpenRouter key. Optional for discovery (unauthenticated requests are rate-limited), required to execute through OpenRouter. · TYPESAFE_API_KEY=TypeSafe System One (Jev) API key. Optional. · XAI_API_KEY=xAI (Grok) API key. Optional. 1 0.0 %
ANTHROPIC_API_KEY=Anthropic API key. Optional: without it BrowserBash auto-resolves a free local Ollama model. 1 0.0 %
ANTHROPIC_API_KEY=Anthropic API key. Required for LLM-backed primitives (judge, extract-with-schema) and the audit_url / explore_url presets. Meta tools (list_personas, list_scenarios, get_last_report) work without it. 1 0.0 %
ANTHROPIC_API_KEY=Anthropic API key. Required for the tools that call a model — `query` composes a cited natural-language answer, and the semantic half of `lint` reasons over claim pairs. The accessors that only read the store (`particle_show`, `particles_list`, `subjects_*`, `events_*`, `graph_view`, `quality_report`) work without it. · DATABASE_URL=SQLAlchemy URL of the belief store to serve. Defaults to `sqlite+aiosqlite:///./particles.db` in the working directory. · PARTICLES_CONFIG=Path to a `config.yaml` holding the rest of the engine's settings — additional stores, model selection per purpose, and the `mcp.write.enabled_stores` allowlist that turns the write tools on. 1 0.0 %
ANTHROPIC_API_KEY=Anthropic API key. Required only for grade_visual_quality, generate_component, and Tier-2 validate_copy. Optional for all other tools. · BRAND_API_KEY=Your Variel project API key (bsk_…) to connect an existing brand. Get it from your Variel dashboard, or run `variel-mcp login` to provision one via browser sign-in (no copy-paste). You can also start keyless and generate a brand with generate_brand_kickoff. · VARIEL_API_URL=Override the Variel API base URL. Defaults to https://variel.ai. Optional — for self-hosted or staging. 1 0.0 %
ANTHROPIC_API_KEY=Anthropic API key. · ANTHROPIC_CONTEXT=Shared context-window tokens. · ANTHROPIC_COST_IN=Shared USD per 1k input tokens. · ANTHROPIC_COST_OUT=Shared USD per 1k output tokens. · ANTHROPIC_MAX_OUTPUT=Shared maximum output tokens. · ANTHROPIC_MODELS=Comma-separated Anthropic wire model ids. · ANTHROPIC_NAMES=Optional comma-separated canonical model ids. · ANTHROPIC_STRENGTHS=Shared comma-separated routing strengths. · ANTHROPIC_TIER=Shared capability tier from 1 to 4. · ANTHROPIC_TOOLS=Declare tool-call support (1 or 0). · CLAUDE_CODE_ENABLED=Set to 1 to enable the logged-in Claude Code CLI. · CLAUDE_CODE_MAX_OUTPUT=Shared maximum output tokens. · CLAUDE_CODE_MODELS=Comma-separated Claude Code model ids. · CLAUDE_CODE_SYSTEM_PROMPT_MODE=System-prompt mode: replace or append. · CLAUDE_CODE_TIER=Shared capability tier from 1 to 4. · CLAUDE_CODE_TIMEOUT=Per-call timeout in seconds. · CODEX_CONTEXT=Shared context-window tokens. · CODEX_COST_IN=Shared API-equivalent input valuation. · CODEX_COST_OUT=Shared API-equivalent output valuation. · CODEX_ENABLED=Set to 1 to enable the logged-in Codex CLI. · CODEX_MAX_OUTPUT=Shared maximum output tokens. · CODEX_MODELS=Comma-separated Codex model ids. · CODEX_TIER=Required capability tier from 1 to 4 when enabled. · CODEX_TIMEOUT=Per-call timeout in seconds. · MOONSHOT_API_KEY=Moonshot API key. · MOONSHOT_BASE_URL=Moonshot OpenAI-compatible base URL. · MOONSHOT_CONTEXT=Shared context-window tokens. · MOONSHOT_COST_IN=Shared USD per 1k input tokens. · MOONSHOT_COST_OUT=Shared USD per 1k output tokens. · MOONSHOT_MAX_OUTPUT=Shared maximum output tokens. · MOONSHOT_MODELS=Comma-separated Moonshot wire model ids. · MOONSHOT_NAMES=Optional comma-separated canonical model ids. · MOONSHOT_STRENGTHS=Shared comma-separated routing strengths. · MOONSHOT_TIER=Shared capability tier from 1 to 4. · MOONSHOT_TOOLS=Declare tool-call support (1 or 0). · OLLAMA_API_KEY=Optional credential for the Ollama endpoint. · OLLAMA_BASE_URL=Local Ollama OpenAI-compatible base URL. · OLLAMA_CONTEXT=Shared context-window tokens. · OLLAMA_COST_IN=Shared USD per 1k input tokens. · OLLAMA_COST_OUT=Shared USD per 1k output tokens. · OLLAMA_MAX_OUTPUT=Shared maximum output tokens. · OLLAMA_MODELS=Comma-separated Ollama wire model ids. · OLLAMA_NAMES=Optional comma-separated canonical model ids. · OLLAMA_STRENGTHS=Shared comma-separated routing strengths. · OLLAMA_TIER=Shared capability tier from 1 to 4. · OLLAMA_TOOLS=Declare tool-call support (1 or 0). · OPENAI_COMPAT_2_BASE_URL=Compatible slot 2 base URL. · OPENAI_COMPAT_2_CONTEXT=Compatible slot 2 context-window tokens. · OPENAI_COMPAT_2_COST_IN=Compatible slot 2 input cost. · OPENAI_COMPAT_2_COST_OUT=Compatible slot 2 output cost. · OPENAI_COMPAT_2_KEY=Compatible slot 2 API key. · OPENAI_COMPAT_2_MAX_OUTPUT=Compatible slot 2 maximum output tokens. · OPENAI_COMPAT_2_MODEL=Compatible slot 2 wire model id. · OPENAI_COMPAT_2_NAME=Compatible slot 2 canonical model id. · OPENAI_COMPAT_2_STRENGTHS=Compatible slot 2 comma-separated strengths. · OPENAI_COMPAT_2_TIER=Compatible slot 2 capability tier. · OPENAI_COMPAT_2_TOOLS=Compatible slot 2 tool-call support (1 or 0). · OPENAI_COMPAT_3_BASE_URL=Compatible slot 3 base URL. · OPENAI_COMPAT_3_CONTEXT=Compatible slot 3 context-window tokens. · OPENAI_COMPAT_3_COST_IN=Compatible slot 3 input cost. · OPENAI_COMPAT_3_COST_OUT=Compatible slot 3 output cost. · OPENAI_COMPAT_3_KEY=Compatible slot 3 API key. · OPENAI_COMPAT_3_MAX_OUTPUT=Compatible slot 3 maximum output tokens. · OPENAI_COMPAT_3_MODEL=Compatible slot 3 wire model id. · OPENAI_COMPAT_3_NAME=Compatible slot 3 canonical model id. · OPENAI_COMPAT_3_STRENGTHS=Compatible slot 3 comma-separated strengths. · OPENAI_COMPAT_3_TIER=Compatible slot 3 capability tier. · OPENAI_COMPAT_3_TOOLS=Compatible slot 3 tool-call support (1 or 0). · OPENAI_COMPAT_BASE_URL=Compatible slot 1 base URL. · OPENAI_COMPAT_CONTEXT=Compatible slot 1 context-window tokens. · OPENAI_COMPAT_COST_IN=Compatible slot 1 input cost. · OPENAI_COMPAT_COST_OUT=Compatible slot 1 output cost. · OPENAI_COMPAT_KEY=Compatible slot 1 API key. · OPENAI_COMPAT_MAX_OUTPUT=Compatible slot 1 maximum output tokens. · OPENAI_COMPAT_MODEL=Compatible slot 1 wire model id. · OPENAI_COMPAT_NAME=Compatible slot 1 canonical model id. · OPENAI_COMPAT_STRENGTHS=Compatible slot 1 comma-separated strengths. · OPENAI_COMPAT_TIER=Compatible slot 1 capability tier. · OPENAI_COMPAT_TOOLS=Compatible slot 1 tool-call support (1 or 0). · VOLANTE_FETCH_ALLOWLIST=Comma-separated domains that enable fetch_url. · VOLANTE_MAX_SUBSCRIPTION_CALLS=Physical subscription calls allowed per run. · VOLANTE_MODEL_OVERRIDES_FILE=Local strict-JSON per-model metadata override file. · VOLANTE_QUALITY_PROFILES_FILE=Local strict-JSON quality-evidence file. · VOLANTE_READ_ROOT=Root directory that enables confined read_file. · VOLANTE_SANDBOX=Agentic execution sandbox. Unset auto-selects docker when available and otherwise disables code execution; subprocess opts in to unisolated execution. 1 0.0 %
ANTHROPIC_API_KEY=Anthropic API key; required only for subtitle translation 1 0.0 %

Auf diesem Blatt stehen 50 von 7.577 Werten; sie decken 50 Einträge ab.

Blatt 16 von 152, 7.577 Werte insgesamt.

Gezählt wird die Projektion, dieselbe Tabelle, aus der die Liste filtert. Ein Eintrag zählt je Wert einmal.

tracevero · https://tracevero.de/werkzeuge/merkmal/mcp/roh_umgebungsbeschreibungen?seite=16