Zum Inhalt springen

Beschreibungen der Umgebungsvariablen (Rohangabe)

7.577 verschiedene Werte, gemessen an 42.703 ausgelieferten Einträgen.

Wert Einträge Anteil
MANAGED_AGENTS_API_KEY=API key when the connected Harness runtime requires authentication. · MANAGED_AGENTS_URL=URL of the SandBase Harness runtime API. 1 0.0 %
MANAGER_API_KEY=Access token from Manager Settings (sent as X-API-KEY) · MANAGER_API_URL=Manager API base URL (include /api2 when required) · MANAGER_MCP_DELETE_SCOPES=Comma-separated delete scopes (never implied by write scopes) · MANAGER_MCP_HTTP_AUTH_TOKEN=Bearer token required of every HTTP request when set. HTTP transport has no authentication at all when this is unset -- see README's Transports section. · MANAGER_MCP_HTTP_HOST=Bind host for HTTP transport. Defaults to loopback (127.0.0.1) when unset. · MANAGER_MCP_HTTP_PORT=Bind port for HTTP transport. Defaults to 8000 when unset. · MANAGER_MCP_TRANSPORT=stdio (default) or http. This package entry always launches over stdio via uvx; set http only when running the server yourself as a standalone process, not via this registry launch. · MANAGER_MCP_WRITE_SCOPES=Comma-separated write scopes: quotes,orders,parties,items,sales,purchases,banking,payroll,ledger,raw. Recommended: banking,sales,parties 1 0.0 %
MANAGER_API_KEY=Access token from Manager Settings (sent as X-API-KEY) · MANAGER_API_URL=Manager API base URL (include /api2 when required) · MANAGER_MCP_DELETE_SCOPES=Comma-separated delete scopes (never implied by write scopes) · MANAGER_MCP_WRITE_SCOPES=Comma-separated write scopes: quotes,orders,parties,items,sales,purchases,banking,payroll,ledger,raw. Recommended: banking,sales,parties 1 0.0 %
MANDARE_GATEWAY_URL=Running gateway base URL — enables the gateway health tool · MANDARE_LEDGER_DB=Path to the Mandare ledger database this MCP server verifies and kills against · MANDARE_MCP_ALLOW_REINSTATE=Set to 1 to expose the reinstate tool (off by default; kills only close doors) · MANDARE_MCP_HOME=Directory where issued artifacts (mandates, credentials, token grant files) are written (default ~/.mandare/mcp) · MANDARE_WITNESS_PUBLIC_KEY=The witness's Ed25519 public key (64 hex chars), obtained out-of-band · MANDARE_WITNESS_URL=Witness server URL — enables truncation/rewrite checks and certificate export 1 0.0 %
MANIFOLD_API_KEY=Manifold Markets API key from your account settings 1 0.0 %
MANNA_ALLOWED_HOSTS=Comma-separated hostnames the server may fetch. Unset means any public host. · MANNA_ARCHIVES=Comma-separated archive short_names to activate (e.g. 'datalab,alma'). Unset means all. · MANNA_INLINE_ROW_LIMIT=Max rows returned inline before a result is promoted to an async job or truncated. · MANNA_LOG_LEVEL=Logging verbosity. 1 0.0 %
MANTIS_API_KEY=MantisBT API key (Profile → API Tokens in MantisBT) · MANTIS_BASE_URL=Base URL of the MantisBT REST API, e.g. https://your-mantis.example.com/api/rest · MANTIS_CACHE_DIR=Directory for the metadata cache. Defaults to ~/.cache/mantisbt-mcp · MANTIS_CACHE_TTL=Metadata cache TTL in seconds. Default: 3600 (1 hour) · MANTIS_SEARCH_BACKEND=Vector store backend for semantic search. 'vectra' (default, pure JS) or 'sqlite-vec' (faster for >10k issues) · MANTIS_SEARCH_DIR=Directory for the semantic search index. Defaults to ~/.cache/mantisbt-mcp/search · MANTIS_SEARCH_ENABLED=Enable offline semantic search (requires ~80 MB model download on first use) · MANTIS_SEARCH_MODEL=Hugging Face model for embeddings. Default: Xenova/paraphrase-multilingual-MiniLM-L12-v2 · MANTIS_SEARCH_THREADS=ONNX inference threads for the embedding model. Default: 1 · MANTIS_UPLOAD_DIR=If set, restricts file uploads to this directory (path traversal protection) · MANTIS_USE_INDEX_PHP=Use /api/rest/index.php/ for MantisBT installations without URL rewriting. Detected automatically when MANTIS_BASE_URL ends with /api/rest/index.php · MCP_HTTP_HOST=Bind address when TRANSPORT=http. Default: 127.0.0.1 (local only). Use 0.0.0.0 for Docker/remote. · MCP_HTTP_TOKEN=Optional Bearer token to protect the /mcp endpoint when TRANSPORT=http · PORT=HTTP port when TRANSPORT=http. Default: 3000 · TRANSPORT=Transport mode. 'stdio' for local use (default), 'http' for remote/team deployments 1 0.0 %
MANTIS_API_URL=Base URL of Mantis API (e.g., https://api.mantisxr.com) · MANTIS_AUTH_TOKEN=Bearer token for authenticated Mantis API requests 1 0.0 %
MANUAL_WEBHOOK_URL=Webhook URL for the manual backend to send task notifications · MTURK_ACCESS_KEY_ID=AWS access key ID for the Amazon Mechanical Turk backend · MTURK_SANDBOX=Set to "false" to use MTurk production environment (defaults to sandbox mode) · MTURK_SECRET_ACCESS_KEY=AWS secret access key for the Amazon Mechanical Turk backend · RENTAHUMAN_API_KEY=API key for the RentAHuman.ai backend 1 0.0 %
MANYLIVES_MAX_USD_PER_CALL=Refuse calls priced above this (default 0.05) · MANYLIVES_MAX_USD_PER_DAY=Stop paying after this much per day (default 1) · MANYLIVES_WALLET_KEY=Optional key of a small dedicated Base wallet with USDC; without it tools use the free trial (3 calls a day) 1 0.0 %
MAPBOX_ACCESS_TOKEN=Mapbox token for natural-language location search (e.g. 'San Francisco') · MAX_H3_CELLS=Safety cap for H3 grid generation (default: 50000) · OVERPASS_API_URL=Custom Overpass API endpoint URL (defaults rotate between public instances) 1 0.0 %
MAPBOX_ACCESS_TOKEN=Your Mapbox access token 1 0.0 %
MAPBOX_ACCESS_TOKEN=Your Mapbox access token. See docs for required scopes. 1 0.0 %
MAPI_KEY=ALTR management API key · MAPI_SECRET=ALTR management API secret · ORG_ID=ALTR organization ID 1 0.0 %
MAPLESTORY_API_KEY=API key from Nexon OpenAPI (https://open.api.nexon.com) 1 0.0 %
MAPLE_PUMF_CACHE_DIR=Folder for downloaded PUMF microdata (default: system temp). · MAPLE_TOOL_TIMEOUT_SECONDS=Longest a tool call may run before it fails (default 120). 1 0.0 %
MAPLIBRE_MCP_TOOLSETS=The toolsets to turn on, comma separated, like style,gl-js,martin. Defaults to style,gl-js, and all turns on every toolset. · MARTIN_URL=The Martin server that the martin toolset reads and renders with. Defaults to http://localhost:3000. 1 0.0 %
MAPNOSTICS_API_KEY=Personal API key from mapnostics.com -> your repo -> Settings -> API keys. Starts with mns_. · MAPNOSTICS_URL=Override the MCP endpoint. Defaults to https://www.mapnostics.com/api/mcp. 1 0.0 %
MAPPLS_API_KEY=Mappls API key — get one free at https://apis.mappls.com · MAPPLS_CLIENT_ID=Mappls OAuth client ID (alternative to API key) · MAPPLS_CLIENT_SECRET=Mappls OAuth client secret (used with CLIENT_ID) 1 0.0 %
MAPPLS_API_KEY=Your Mappls static API key — get it at https://maps.mappls.com/api 1 0.0 %
MAPSI_API_KEY=Your Mapsi API key from mapsi.dev 1 0.0 %
MAPSMITH_WORKSPACE=Confine all reads/writes to this directory (path jail + sandboxed SQL engine) 1 0.0 %
MARBOBA_API_TOKEN=MarBoba Personal Access Token (mb_pat_*). Create one in Settings -> API Tokens. · MARBOBA_ENDPOINT=API endpoint override; defaults to https://api.marboba.com. Use https://api-dev.marboba.com etc. for non-prod. 1 0.0 %
MARCHWARD_API_KEY=Your Marchward API key (mw_...) · MARCHWARD_API_URL=Marchward API base URL 1 0.0 %
MARIADB_DATABASE=Database name · MARIADB_HOST=Database host · MARIADB_PASSWORD=Database password (or use MARIADB_PASSWORD_FILE) · MARIADB_USER=Database user (a read-only user is recommended) 1 0.0 %
MARKAESTRO_API_KEY=Workspace API key (mk_live_ or mk_test_) from Settings, API Access. Covers one brand or all brands in the workspace. · MARKAESTRO_READ_ONLY=Set to 1 to register only the reading tools. 1 0.0 %
MARKDOWN_SOURCE=Optional directory for one-way markdown import. · MEMORY_DB_PATH=SQLite database path inside the container. · MEMORY_PORT=SSE server port. Default: 8085. 1 0.0 %
MARKDOWN_VAULT_MCP_APP_DOMAIN=MCP Apps iframe domain, used for CSP sandboxing. Overrides the host derived from `base_url`. · MARKDOWN_VAULT_MCP_ATTACHMENT_EXTENSIONS=Comma-separated allowed attachment extensions (e.g. pdf,png,jpg); case and a leading dot are ignored, so PDF and .pdf name the same type. Use * to allow every non-markdown file. Unset selects the built-in allowlist. A link whose target has a listed extension is not part of the link graph; changing the list rebuilds the index once. · MARKDOWN_VAULT_MCP_AUTH_MODE=Explicit auth-mode override, accepting `remote` or `oidc-proxy` (case- and whitespace-insensitive). When unset the mode is auto-detected from which auth variables are set; the override exists because having all four OIDC variables set is ambiguous between those two modes. Other values are ignored with a warning. · MARKDOWN_VAULT_MCP_BASE_URL=Public base URL of the deployed server, for example `https://mcp.example.com`. Required for OIDC. Also the fallback source of the MCP Apps domain when `app_domain` is unset. · MARKDOWN_VAULT_MCP_BEARER_DEFAULT_SUBJECT=Subject assigned to the single-token bearer mode; ignored when `bearer_tokens_file` is set, since mapped mode carries per-token subjects. · MARKDOWN_VAULT_MCP_BEARER_TOKEN=Single shared bearer token; enables bearer auth unless `bearer_tokens_file` is set, which takes precedence. · MARKDOWN_VAULT_MCP_BEARER_TOKENS_FILE=Path to a TOML file mapping bearer tokens to subjects; overrides the single-token `bearer_token` mode. · MARKDOWN_VAULT_MCP_BOOT_REINDEX=Reconcile offline changes at startup by reindexing once the initial build completes. Set false on a large vault to start without paying a full filesystem scan per server start; changes made while no server was running are then invisible until a reindex runs (the reindex tool, or 'markdown-vault-mcp reindex'). Note that `index_stale` reports writer idleness, not agreement with disk, so it reads false while the index may still differ from the vault. · MARKDOWN_VAULT_MCP_BUILD_TIMEOUT_S=Maximum seconds an index-backed tool or resource waits for the FTS index to become queryable during a cold-start background build before raising IndexUnavailableError(reason="timeout"). Increase for large vaults. · MARKDOWN_VAULT_MCP_CHUNKS_PER_FILE=Maximum chunks returned per document in search results. · MARKDOWN_VAULT_MCP_CHUNK_OVERLAP_WORDS=Words of overlap between adjacent budget-split fragments of the same heading section (0 disables). A reindex applies a new value. · MARKDOWN_VAULT_MCP_CONVENTIONS_FILE=Filename of the per-folder conventions files surfaced to clients at write time (bare .md filename without glob characters). Set to none to disable folder conventions. · MARKDOWN_VAULT_MCP_DEFAULT_SEARCH_MODE=Mode used when a search call omits 'mode': auto, keyword, semantic, or hybrid. The default 'auto' picks hybrid when embeddings are configured and keyword when they are not. Pin 'keyword' to keep unqualified searches off the embedding provider (each hybrid or semantic search embeds the query, which costs an API call on a metered provider). A configured semantic/hybrid default also degrades to keyword without embeddings, so no setting can make a vault unsearchable; an explicit mode= argument is never downgraded. · MARKDOWN_VAULT_MCP_DISABLE_APPS_UI=Hide the MCP Apps UI tools (browse_vault, show_context) from the tool listing for clients that do not render MCP Apps panels. · MARKDOWN_VAULT_MCP_DRAIN_TIMEOUT_S=Maximum seconds an index-querying read tool waits for the IndexWriter to drain when called with wait_for_pending_writes=true. On timeout the tool answers from the current index and reports index_stale=true in the response _meta. · MARKDOWN_VAULT_MCP_EMBEDDINGS_PATH=Base path for the embeddings files. Defaults beside INDEX_PATH (index-db-embeddings.npy and .json beside index.db); without INDEX_PATH the vectors are kept in memory and rebuilt at each start. Setting it also lets the provider be auto-detected. · MARKDOWN_VAULT_MCP_EMBEDDING_BATCH_SIZE=Number of chunks sent per embedding request. Smaller batches shorten each request (useful under a tight timeout on slow models) at the cost of more round-trips. · MARKDOWN_VAULT_MCP_EMBEDDING_PROVIDER=Embedding provider: openai, voyage, ollama, or fastembed; setting it turns on search by meaning. Unset auto-detects from the environment (never voyage), but only when EMBEDDINGS_PATH is set. Any OpenAI-compatible endpoint works with openai plus OPENAI_BASE_URL; see the embeddings guide. · MARKDOWN_VAULT_MCP_EMBED_CONTEXT=Enrich embedding input with the note title, chunk heading, and (first chunk) searchable-field values. Flipping it re-embeds the whole vault once on next startup. · MARKDOWN_VAULT_MCP_EMBED_TIMEOUT_S=Per-request wall-clock budget in seconds for a single embedding HTTP call (OpenAI/Ollama). The local FastEmbed backend runs in-process with no network call and ignores this. CPU-only or large-model workloads may need 60-120 s; raise this if batches time out. · MARKDOWN_VAULT_MCP_EXCLUDE=Comma-separated glob patterns excluded from scanning, e.g. .obsidian/**,.trash/**. · MARKDOWN_VAULT_MCP_FASTEMBED_CACHE_DIR=FastEmbed model cache directory (in Docker, stored under /data/state/fastembed). · MARKDOWN_VAULT_MCP_FASTEMBED_MODEL=FastEmbed model name. · MARKDOWN_VAULT_MCP_FILE_WATCHER=Watch the vault for external filesystem changes; auto-disabled when git pull is active or a webhook can deliver (HTTP/SSE transports only). Requires the file-watcher extra. · MARKDOWN_VAULT_MCP_FILE_WATCHER_DEBOUNCE_S=Seconds of quiet after the last filesystem event before reindexing. · MARKDOWN_VAULT_MCP_FILE_WATCHER_ROOT_FLOOR=Keep the non-recursive watch on the vault root; set false to register zero source-dir-rooted FSEvents streams (avoids repeated macOS access prompts on a home-rooted vault) at the cost of root-level files relying on scans. · MARKDOWN_VAULT_MCP_FOLDER_WEIGHTS=Folder-prefix score multipliers (`prefix:weight` pairs, comma-separated, weights > 0) applied to all search modes; the deepest matching prefix wins (sessions:0.5 demotes sessions/**). · MARKDOWN_VAULT_MCP_FTS_WEIGHTS=Per-column BM25 weights (`column:weight` pairs, comma-separated, weights >= 0) for keyword ranking. Columns: path, title, folder, heading, content, summary. · MARKDOWN_VAULT_MCP_GITHUB_WEBHOOK_SECRET=Shared secret for the GitHub push-event webhook; when set, mounts POST /github-webhook on HTTP/SSE transports to trigger an immediate pull + reindex on push events. · MARKDOWN_VAULT_MCP_GITLAB_WEBHOOK_SECRET_TOKEN=Secret token for the GitLab push-event webhook, GitLab's plain-text form and the only one below 19.0; also mounts POST /gitlab-webhook. It proves nothing about the body and cannot expire, so prefer the signing token where the GitLab version offers it. Setting both accepts either, which is how an existing webhook migrates. · MARKDOWN_VAULT_MCP_GITLAB_WEBHOOK_SIGNING_TOKEN=Signing token for the GitLab push-event webhook (GitLab 19.0+); when set, mounts POST /gitlab-webhook on HTTP/SSE transports to trigger an immediate pull + reindex on push events. GitLab generates this value; copy the `whsec_` token it shows under Generate signing token rather than inventing one. Deliveries are authenticated by HMAC-SHA256 over the webhook id, timestamp and body, and a delivery older than 5 minutes is rejected. · MARKDOWN_VAULT_MCP_GIT_COMMIT_EMAIL=Git committer email for auto-commits, and the author email too unless an OIDC claim supplies one. · MARKDOWN_VAULT_MCP_GIT_COMMIT_EMAIL_CLAIM=OIDC claim key used as the commit author email (e.g. email) when an OIDC token is present; the committer stays GIT_COMMIT_EMAIL. Resolved and carried the same way as the name claim. · MARKDOWN_VAULT_MCP_GIT_COMMIT_NAME=Git committer name for auto-commits, and the author name too unless an OIDC claim supplies one; set this in Docker where git config user.name is empty. · MARKDOWN_VAULT_MCP_GIT_COMMIT_NAME_CLAIM=OIDC claim key used as the commit author name (e.g. name) when an OIDC token is present; the committer stays GIT_COMMIT_NAME. The claim is resolved when the tool call arrives and carried to the background commit, so it applies on every write. A configured claim the token does not carry is reported once at WARNING and the static identity is used. · MARKDOWN_VAULT_MCP_GIT_LFS=Run git lfs pull on startup to fetch LFS-tracked attachments; set to false for repos without LFS. · MARKDOWN_VAULT_MCP_GIT_PULL_INTERVAL_S=Seconds between git fetch + fast-forward update attempts; 0 disables periodic pull. · MARKDOWN_VAULT_MCP_GIT_PUSH_DELAY_S=Seconds of write-idle time before pushing; 0 pushes only on shutdown. · MARKDOWN_VAULT_MCP_GIT_REPO_URL=HTTPS remote URL for managed git mode: the server clones into an empty SOURCE_DIR on startup (or validates an existing origin) and enables the pull loop, auto-commit, and deferred push. · MARKDOWN_VAULT_MCP_GIT_TOKEN=Token/password for HTTPS git auth; remotes must be HTTPS when set. · MARKDOWN_VAULT_MCP_GIT_USERNAME=Username for HTTPS git auth prompts (x-access-token for GitHub, oauth2 for GitLab, the account name for Bitbucket). · MARKDOWN_VAULT_MCP_HEALTH_DETAIL=How much the unauthenticated /health and /health/ready bodies say: status, standard (adds name, version and per-check verdicts), or full (adds redacted reasons; trusted networks only). · MARKDOWN_VAULT_MCP_HTTP_PATH=Mount path for the MCP endpoint; the health routes derive their prefix from it. · MARKDOWN_VAULT_MCP_INDEXED_FIELDS=Comma-separated frontmatter fields promoted to the tag index for structured filtering. Changing it cold-rebuilds the index once on next startup; SEARCHABLE_FIELDS inherits this value when unset. · MARKDOWN_VAULT_MCP_INDEX_PATH=Path to the SQLite FTS5 index file; unset keeps the index in memory. Set it for persistence across restarts. · MARKDOWN_VAULT_MCP_INSTANCE_DESCRIPTION=Concise routing context that distinguishes this deployment's material or responsibility. · MARKDOWN_VAULT_MCP_INSTRUCTIONS=Legacy: replaces all generated MCP instructions (deprecated; use _INSTANCE_DESCRIPTION for routing and _INSTRUCTIONS_EXTRA for policy). · MARKDOWN_VAULT_MCP_INSTRUCTIONS_EXTRA=Deployment-specific behavioral policy added to the generated MCP instructions. · MARKDOWN_VAULT_MCP_JOBS_MAX_PER_SUBJECT=Maximum live background jobs per calling subject; further promotions are rejected until older records expire. · MARKDOWN_VAULT_MCP_JOBS_RESULT_TTL_S=Seconds a background-job record (working or finished) is retained for polling before it expires from the store. · MARKDOWN_VAULT_MCP_JOBS_SOFT_DEADLINE_S=Seconds a long-running tool call may run in the foreground before it is promoted to a background job and a job handle is returned instead. · MARKDOWN_VAULT_MCP_KV_STORE_URL=Persistent-state backend URL shared by every pvl-core subsystem that needs state. `memory://` is in-process and lost on restart; `file:///path` persists on one server; `redis://`, `dynamodb://` and `mongodb://` each need their matching extra. When unset, defaults to `file:///data/state` (the volume family Docker images mount), or to `memory://` (with a warning) on a host where that directory is not usable. · MARKDOWN_VAULT_MCP_LENGTH_DOWNWEIGHT_ALPHA=Down-weights longer chunks in ranking: score / (1 + alpha * log(chunk_count)). · MARKDOWN_VAULT_MCP_LOG_FORMAT=Log rendering. rich is one colour event key=value line per record, for a terminal; json is one JSON object per record, for a collector. Unset picks rich when stderr is a terminal and json everywhere else, so a container or journald gets JSON with no configuration. · MARKDOWN_VAULT_MCP_LOG_LEVEL=Log level for every logger in the process, FastMCP's included (DEBUG / INFO / WARNING / ERROR / CRITICAL). The -v CLI flag overrides to DEBUG. The unprefixed FASTMCP_LOG_LEVEL still works for one major version and logs a deprecation warning. · MARKDOWN_VAULT_MCP_MAX_ATTACHMENT_SIZE_MB=Maximum attachment size in MB returned by read / accepted by write; 0 disables the limit. · MARKDOWN_VAULT_MCP_MAX_CHUNK_CHARS=Character cap enforced alongside MAX_CHUNK_WORDS to bound token-dense chunks. Unset derives min(1500, model context * 2.8). Set a positive value for an exact cap, or -1 to scale with the model's full context (can exhaust memory on long-context models). A reindex applies a new value. · MARKDOWN_VAULT_MCP_MAX_CHUNK_WORDS=Word cap per chunk; the adaptive chunker splits at deeper heading levels, then paragraph/word boundaries, to respect it. Match it to the embedding model's context. A reindex applies a new value. · MARKDOWN_VAULT_MCP_MAX_NOTE_READ_BYTES=Maximum bytes returned by a full-document read of a note; use `read(path, section=…)` for partial reads. 0 disables the limit. · MARKDOWN_VAULT_MCP_OIDC_ADVERTISED_SCOPES=Scopes advertised to MCP clients in protected-resource metadata, space- or comma-separated. Overrides the default `openid offline_access`; `oidc_required_scopes` is always added on top. Set this when the registered client is not permitted `offline_access`, or to have clients request extra claim scopes (such as `groups`) without also requiring them in every token. · MARKDOWN_VAULT_MCP_OIDC_AUDIENCE=Expected `aud` claim; tokens issued for another audience are rejected. · MARKDOWN_VAULT_MCP_OIDC_CLIENT_ID=OIDC client identifier registered with the provider. · MARKDOWN_VAULT_MCP_OIDC_CLIENT_SECRET=OIDC client secret registered with the provider. · MARKDOWN_VAULT_MCP_OIDC_CONFIG_URL=OIDC discovery document URL, for example `https://auth.example.com/.well-known/openid-configuration`. · MARKDOWN_VAULT_MCP_OIDC_JWT_SIGNING_KEY=Signing key for issued tokens; used in oidc-proxy mode only. When unset, the key is derived deterministically from `oidc_client_secret`, so tokens survive a restart. Rotating that secret then invalidates every issued token. Set this explicitly to decouple token validity from secret rotation. Generate with `openssl rand -hex 32`. · MARKDOWN_VAULT_MCP_OIDC_REQUIRED_SCOPES=Scopes a caller must present, space- or comma-separated. Defaults to `openid` in oidc-proxy mode. · MARKDOWN_VAULT_MCP_OIDC_VERIFY_ACCESS_TOKEN=Validate the access token instead of the id token. · MARKDOWN_VAULT_MCP_OKF_MODE=OKF (Open Knowledge Format) read semantics. With auto (the default), read annotations switch on when the vault declares an OKF version in its root index.md. Use off to disable OKF semantics entirely, or on to force them for an undeclared vault. Annotations are read-only; write behavior is never affected. · MARKDOWN_VAULT_MCP_OKF_VERIFY=How the okf_verify tool attributes a human review. This applies only when OKF_WRITE is on, which gates the tool. With elicit (the default), okf_verify asks the human to confirm the review through an MCP elicitation, then records the attestation only on an affirmative reply. It fails closed when the client cannot elicit or the human declines, so a model holding the human's token cannot self-attest. Set trust-auth instead to attribute to a token's sub claim with no confirmation; it rejects static bearer credentials and other client-ID-only identities. This is safe only when the sole caller is a human-driven UI. Set off to hide the tool, leaving attestation to external tooling. A non-default value with OKF_WRITE off is a config error. · MARKDOWN_VAULT_MCP_OKF_WRITE=OKF (Open Knowledge Format) enforced write layer. When true on an OKF-active vault, the server stamps generated provenance on each write and clears any verified attestation when a note's content changes. It also keeps each written folder's log.md and index.md current, and exposes the okf_verify tool. Requires OKF_MODE to be auto or on (a true value with OKF_MODE=off is a config error). Off by default. · MARKDOWN_VAULT_MCP_OLLAMA_CPU_ONLY=Force Ollama to embed on CPU only. · MARKDOWN_VAULT_MCP_OLLAMA_MODEL=Ollama embedding model name. · MARKDOWN_VAULT_MCP_OPENAI_BASE_URL=OpenAI-compatible API base URL for embeddings; the bare OPENAI_BASE_URL is honoured as a fallback. · MARKDOWN_VAULT_MCP_OPENAI_EMBEDDING_MODEL=OpenAI-compatible embedding model name; the bare OPENAI_EMBEDDING_MODEL is honoured as a fallback. · MARKDOWN_VAULT_MCP_PROMPTS_FOLDER=Directory of .md prompt files that extend or override built-in prompts; a relative path is resolved against SOURCE_DIR. · MARKDOWN_VAULT_MCP_READ_ONLY=Set to true to hide the write tools (write, edit, append, delete, rename, move_folder, fetch, git_sync, the okf_* tools, create_upload_link) and serve a search-only vault. · MARKDOWN_VAULT_MCP_REPORT_UNRESOLVED_LINKS=Set to true to have write, edit and append list, under unresolved_links, the target of each link the call added that get_broken_links reports. Links the note already held are left out. Off by default, leaving those responses unchanged. · MARKDOWN_VAULT_MCP_REQUIRED_FIELDS=Comma-separated frontmatter fields required on every document; documents missing any are excluded from the index. · MARKDOWN_VAULT_MCP_SEARCHABLE_FIELDS=Comma-separated frontmatter fields whose text values become keyword-searchable and enrich first-chunk embeddings. Inherits INDEXED_FIELDS when unset; the sentinel none means filterable but not searchable. Changing it cold-rebuilds the index and re-embeds once on next startup. · MARKDOWN_VAULT_MCP_SERVER_NAME=Rename this server instance; defaults to the project name. · MARKDOWN_VAULT_MCP_SHUTDOWN_GRACE_S=Seconds SIGTERM may spend draining in-flight requests before the HTTP server exits. Keep it at or below the termination grace period the orchestrator allows. `0` drops in-flight requests immediately. · MARKDOWN_VAULT_MCP_SNIPPET_WORDS=Width of the snippet window (words) in search results; 0 returns full chunk content. · MARKDOWN_VAULT_MCP_SOURCE_DIR=Path to the markdown vault directory. When it does not exist, or the server cannot access it, the server starts but every tool fails with a message saying which until it is fixed (managed git mode clones into it). Symbolic links inside the vault are followed on Python 3.13+. · MARKDOWN_VAULT_MCP_STATE_PATH=Path to the change-tracking state file. Defaults to INDEX_PATH plus .state.json (index.db.state.json beside index.db); without INDEX_PATH the state is kept in memory. Never written into the vault by default. · MARKDOWN_VAULT_MCP_SUMMARIZE_MAX_INPUT_CHARS=Aggregate cap on note characters sent to the model in one call; excess is truncated with a flag on the result. · MARKDOWN_VAULT_MCP_SUMMARIZE_MAX_NOTES=Cap on the number of notes summarised in one call (subtree expansion truncates to this many). · MARKDOWN_VAULT_MCP_SUMMARIZE_MAX_TOKENS=Upper bound on generated tokens per summarize call; on reasoning models this budget also covers internal reasoning tokens. · MARKDOWN_VAULT_MCP_SUMMARIZE_OPENAI_API_KEY=API key for the OpenAI-compatible summarize endpoint; the bare OPENAI_API_KEY is honoured as a fallback. Unset works for keyless local endpoints (Ollama). · MARKDOWN_VAULT_MCP_SUMMARIZE_OPENAI_BASE_URL=OpenAI-compatible endpoint base URL for the summarize tool; setting it enables the tool even without an API key. The bare OPENAI_BASE_URL routes traffic only when a key already enables the feature. · MARKDOWN_VAULT_MCP_SUMMARIZE_OPENAI_MODEL=Chat model id used for summaries. · MARKDOWN_VAULT_MCP_SUMMARIZE_PROVIDER=Summarization backend (only openai is recognised). Unset auto-detects: the backend activates when credentials or an explicit endpoint are present. · MARKDOWN_VAULT_MCP_SUMMARIZE_TIMEOUT=Per-request wall-clock budget in seconds for a single summarize backend call; keep it below the MCP client's request timeout so the server-side error wins the race. · MARKDOWN_VAULT_MCP_TEMPLATES_FOLDER=Relative folder where note templates live (used by the create_from_template prompt). · MARKDOWN_VAULT_MCP_TITLE_FIELD=Frontmatter field used as the document title (falls back to title, the first H1, then the filename). Changing it cold-rebuilds the index once on next startup. · MARKDOWN_VAULT_MCP_TOOLS_ALLOW=Comma-separated explicit tool names this instance exposes; every other tool is hidden from listings and cannot be invoked. Names matching no registered tool are inert. Mutually exclusive with `tools_deny`. Takes effect through `apply_tool_visibility`. · MARKDOWN_VAULT_MCP_TOOLS_DENY=Comma-separated explicit tool names hidden from this instance (absent from listings, cannot be invoked). Names matching no registered tool are inert. Mutually exclusive with `tools_allow`. Takes effect through `apply_tool_visibility`. · MARKDOWN_VAULT_MCP_TRANSFER_GRACE_TTL_S=Post-success grace window in seconds: a served token's TTL shrinks to this so a stalled transfer can retry within it. · MARKDOWN_VAULT_MCP_TRANSFER_LEASE_S=Crashed-handler reclaim window in seconds for an in-flight reservation. · MARKDOWN_VAULT_MCP_TRANSFER_MAX_UPLOAD_BYTES=Maximum size in bytes of a single upload. · MARKDOWN_VAULT_MCP_TRANSFER_TTL_DEFAULT_S=Link lifetime in seconds when the caller requests no explicit TTL. · MARKDOWN_VAULT_MCP_TRANSFER_TTL_MAX_S=Ceiling in seconds a caller-requested link TTL is clamped to. · MARKDOWN_VAULT_MCP_VOYAGE_MODEL=Voyage AI embedding model name. · MARKDOWN_VAULT_MCP_WRITE_PROTECT_EXISTING=Refuse a write that would overwrite an existing file when no if_match etag is supplied. Deliberate replacement still works: read the file first, then pass if_match. Unaffected: edit, append, delete, rename. Set to false to allow blind overwrites. · OLLAMA_HOST=Ollama server URL for the ollama embedding provider. Bare (not MARKDOWN_VAULT_MCP_-prefixed), matching the Ollama ecosystem convention. · OPENAI_API_KEY=OpenAI API key for the openai embedding provider, and the fallback key for the summarize tool when MARKDOWN_VAULT_MCP_SUMMARIZE_OPENAI_API_KEY is unset. Bare (not MARKDOWN_VAULT_MCP_-prefixed), matching the OpenAI ecosystem convention. · OPENAI_BASE_URL=Bare fallback for MARKDOWN_VAULT_MCP_OPENAI_BASE_URL (embeddings). For the summarize tool it only routes traffic when an API key already enables the feature; it never enables summarize by itself. · OPENAI_EMBEDDING_MODEL=Bare fallback for MARKDOWN_VAULT_MCP_OPENAI_EMBEDDING_MODEL. · PGID=Run the server process as this GID; pair with PUID to match the owner of a mounted volume. · PUID=Run the server process as this UID; the container entrypoint reassigns ownership of writable paths to match. · VOYAGE_API_KEY=Voyage AI API key for the voyage embedding provider. Bare (not MARKDOWN_VAULT_MCP_-prefixed), matching the OPENAI_API_KEY / OLLAMA_HOST convention. Setting it never auto-selects the provider; choose it explicitly with MARKDOWN_VAULT_MCP_EMBEDDING_PROVIDER=voyage. 1 0.0 %
MARKETINTELL_API_KEY=API key for the underlying MarketIntell account. Required for tool calls; optional for capability discovery. 1 0.0 %
MARKETMASTER_API_KEY=API key from https://marketmaster.live/dashboard (looks like mmk_live_...). Free tier available. 1 0.0 %
MARKETO_BASE_URL=Marketo REST endpoint base URL (e.g. https://xxx-xxx-xxx.mktorest.com — find under Admin → Integration → Web Services) · MARKETO_CLIENT_ID=Marketo LaunchPoint REST API client ID · MARKETO_CLIENT_SECRET=Marketo LaunchPoint REST API client secret 1 0.0 %
MARKET_API_URL=CLI Market API base URL · MCP_TOOL_PROFILE=MCP tool profile: default (curated) or legacy (all tools) 1 0.0 %
MARKET_FIYATI_DISTANCE=Default radius in km (>0..50). Set together with latitude and longitude; no implicit radius. · MARKET_FIYATI_ENABLE_EXPERIMENTAL=Enables experimental endpoints, including nearby branch discovery. Set true on first setup when branch IDs are unknown; restart after changing it. · MARKET_FIYATI_LATITUDE=Default latitude (-90..90). Optional as a group with LONGITUDE and DISTANCE; calls may override the coordinate pair. · MARKET_FIYATI_LONGITUDE=Default longitude (-180..180). Set together with MARKET_FIYATI_LATITUDE and MARKET_FIYATI_DISTANCE. · MARKET_FIYATI_MODE=Live price requests by default. Select offline for development and tests to block remote requests. 1 0.0 %
MARKET_PULSE_API_KEY=Optional Market Pulse API key (starts with mpk_). Raises the daily pull budget and shows new job listings sooner. Without it the free tier applies. · MARKET_PULSE_TIMEOUT_MS=How long a single call may take before it fails rather than hanging the client. 1 0.0 %
MARKITUP_API_BASE=Override the API base URL. Default: https://markitup.app/api/v1 · MARKITUP_API_KEY=API key minted at https://markitup.app/dashboard/. Required. 1 0.0 %
MARKLAYER_AGENT=Name shown to the humans in the room for this agent. Defaults to claude-code. · MARKLAYER_API_BASE=Override the MarkLayer worker base URL. Defaults to https://marklayer.app; useful against a local dev worker. · MARKLAYER_ROOM=Same as --room: the share URL or room id to join at startup. 1 0.0 %
MARKLY_API_KEY=Your Markly API key (optional - works without for free tier with branding) 1 0.0 %
MARKOVO_API_KEY=Create a key at https://markovo.net/app#developer. Store it in the MCP host secret store; do not paste it into prompts. · MARKOVO_MCP_ROOT=Dedicated existing directory that bounds all MCP file reads and writes. File tools fail closed when it is missing. 1 0.0 %
MARKTPLAATS_COOKIE=Optional. Your marktplaats.nl session Cookie header for the account tools; prefer running 'marktplaats-mcp login' instead. · MARKTPLAATS_READ_ONLY=Set to 1 to disable sending messages, bidding and changing favorites. · TWEEDEHANDS_COOKIE=Optional. Your 2dehands.be session Cookie header for the account tools. 1 0.0 %
MARMITON_LOG_LEVEL=silent, error, info or debug. Default error. · MARMITON_MIN_INTERVAL_MS=Minimum milliseconds between requests. Default 1000, floor 500. · MARMITON_USER_AGENT=Override the User-Agent sent to Marmiton. 1 0.0 %
MARRIAGE_ASTRO_API_KEY=API Key for MarriageAstro 1 0.0 %
MARROW_API_KEY=Marrow API key used by the local compatibility adapter. 1 0.0 %
MARROW_DATA=Directory holding the SQLite mirror and the two generated tokens. Defaults to ./data. 1 0.0 %
MARVIN_API_TOKEN=Amazing Marvin API token (Settings -> API). Enough for reading and creating tasks. · MARVIN_FULL_ACCESS_TOKEN=Amazing Marvin Full Access token (optional but recommended - required by update/delete tools, category creation, time blocks, habit listing, reminders). · MARVIN_TIMEZONE=IANA timezone matching your Marvin account (e.g. Europe/Stockholm). Defaults to the system timezone. 1 0.0 %
MARZBAN_BASE_URL=URL of the Marzban panel. · MARZBAN_PASSWORD=Marzban administrator password. · MARZBAN_USERNAME=Marzban administrator username. 1 0.0 %
MASKBREAK_API_KEY=Maskbreak API key for your plan's lookup allowance (100,000 a month on the Free plan). Without it, lookups use the rate-limited keyless endpoint. The older SENTINEL_API_KEY name is still read. · SENTINEL_BASE_URL=API base URL override, for testing. 1 0.0 %
MASSDRIVER_API_KEY=Massdriver API key · MASSDRIVER_ORGANIZATION_ID=Massdriver organization ID · MASSDRIVER_URL=Massdriver API URL. Only needed for self-hosted Massdriver instances. 1 0.0 %
MASSED_COMPUTE_API_KEY=Your Massed Compute API key (Bearer token). Generate at https://vm.massedcompute.com/settings/api. Optional — `massed-compute-mcp init` provides an interactive first-run flow that prompts for the key, validates it, and stores it locally with 0600 permissions. 1 0.0 %
MASTERKALA_MCP_PROXY=Optional HTTP proxy URL for requests to masterkala.com; system proxy settings are ignored. 1 0.0 %
MASTR_TOKEN=MaStR web service token (~540 chars) for SOAP API access. Enables 14 additional SOAP tools. · MASTR_USER=MaStR Marktakteur number (SOM/SEM...) for SOAP API access. Without credentials, only 7 public tools are available. 1 0.0 %

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

Blatt 89 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=89