Skip to main content
Glama
614,719 tools. Updated 2026-09-26 23:22

"filesystem" matching MCP tools:

  • Read one source-free operating packet: active version metadata, the latest explicitly selected observed project input, review attention, artifact index, work queue, and current activity cursor. Imported input is immutable evidence, not an AI proposal or live filesystem sync; private 2ools skills, prompts, routing, governance text, and generated version source are not returned.
    ConnectorNo auth
  • Generate Jest/Vitest tests for the exported functions and React components in a TypeScript source file. Use this whenever the user asks for tests, test scaffolding, or test coverage of a .ts or .tsx file. Returns the generated test (and any companion .3tg.md / __mocks__) file contents, with paths already translated to the user's `.3tg/` mirror convention. Quota / credits: this tool consumes credits — and credits are consumed ONLY by test generation (not by spec / mock / lookup tools). The accounting is exactly **1 credit per generated test case** (i.e. per `test(...)` / `it(...)` block 3TG emits inside the returned `.test.ts` / `.test.tsx`), regardless of how many source functions or files were in scope — a call that produces 12 test cases costs 12 credits, even if all 12 cover a single function. Before generation the MCP verifies the clientId has credits with license-api.coding-creed.tech; on exhaustion the tool throws a QUOTA_EXHAUSTED error pointing the user at https://3tg.dev. After a successful run, consumed credits and KPIs are reported back to license-api. Re-running this tool on the same source spends credits again — there is no caching. When the previous call returned `enrichment.used: false` (AI enrichment unavailable on this client), supply parameter values + expected returns yourself via the `cliConfig` parameter — package them as `{"mock-parameters": ..., "function-returns": ...}` (same shape AI enrichment would produce) and pass them on a retry call. **Do NOT autonomously write `.3tg/config.3tg.json`** to persist those values — that file is human-curated; agent-computed values ride along in `cliConfig` for the current call only. (Explicit user requests to edit the file are fine — handle those normally.) See the cliConfig parameter description below for the full pattern. CRITICAL POST-CALL ACTION — write returned files to disk: The MCP server does NOT touch the user's filesystem. It returns the generated file CONTENTS in the response's `files` array. After this tool returns, you MUST iterate over `files` and write each entry's `content` verbatim to its `path` using your native file-write capability (e.g. Write / edit_file / create_file — whatever your client exposes). Create parent directories as needed. Returned paths are project-root-relative and already translated to the `.3tg/` mirror convention where applicable (e.g. specs land under `.3tg/<source-path>.3tg.md`; tests / mocks travel through unchanged). Write each path verbatim. Do NOT claim "Generated test file: <path>" unless you have actually written the file. The user will assume the MCP wrote it and waste time looking for a non-existent file. If you can't write for some reason (permission denied, no write capability in this client), return the contents inline in your message so the user can copy-paste them. Never report success silently when the write didn't happen.
    ConnectorNo auth
  • Run a read-only shell-like query against a virtualized, in-memory filesystem rooted at `/` that contains ONLY the Political Comms documentation pages and OpenAPI specs. This is NOT a shell on any real machine — nothing runs on the user's computer, the server host, or any network. The filesystem is a sandbox backed by documentation chunks. This is how you read documentation pages: there is no separate "get page" tool. To read a page, pass its `.mdx` path to `head` or `cat` — a page at the URL path `/some/page` lives at `/some/page.mdx`. To search the docs with exact keyword or regex matches, use `rg`. To understand the docs structure, use `tree` or `ls`. **Paths are specific to this site — never guess them.** Discover real paths with `tree / -L 2`, `ls /`, or the search tool before reading. If a path does not exist, that only means the guess was wrong; it does NOT mean the topic is undocumented — use `rg -il "keyword" /` to find where it is covered. **Workflow:** Start with the search tool for broad or conceptual queries like "how to authenticate" or "rate limiting". Use this tool when you need exact keyword/regex matching, structural exploration, or to read the full content of a specific page by path. Supported commands: rg (ripgrep), grep, find, tree, ls, cat, head, tail, stat, wc, sort, uniq, cut, sed, awk, jq, plus basic text utilities. No writes, no network, no process control. Run `--help` on any command for usage. Each call is STATELESS: the working directory always resets to `/` and no shell variables, aliases, or history carry over between calls. If you need to operate in a subdirectory, chain commands in one call with `&&` or pass absolute paths (e.g., `cd /some-directory && ls` or `ls /some-directory`). Do NOT assume that `cd` in one call affects the next call. Examples (replace the placeholder paths with real ones from `tree` or search): - `tree / -L 2` — see the top-level directory layout - `rg -il "rate limit" /` — find all files mentioning "rate limit" - `rg -C 3 "apiKey" /some-directory/` — show matches with 3 lines of context around each hit - `head -80 /some/page.mdx` — read the top 80 lines of a specific page - `head -80 /page-one.mdx /page-two.mdx /section/page-three.mdx` — read multiple pages in one call - `cat /some/page.mdx` — read a full page when you need everything - `cat /openapi/api-reference/openapi.json | jq '.paths | keys'` — list OpenAPI endpoints OpenAPI specs for this site are mounted at: `/openapi/api-reference/openapi.json`. Use them to answer questions about endpoints, request/response schemas, parameters, and authentication. Output is truncated to 30KB per call. Prefer targeted `rg -C` or `head -N` over broad `cat` on large files. To read only the relevant sections of a large file, use `rg -C 3 "pattern" /path/file.mdx`. Batch multiple file reads into a single `head` or `cat` call whenever possible. When referencing pages in your response to the user, convert filesystem paths to URL paths by removing the `.mdx` extension. For example, `/some/page.mdx` becomes `/some/page`.
    ConnectorNo auth
  • Create a new volumeset in a GVC with explicit performance class, filesystem type, initial capacity, snapshot policy, and (optional) autoscaling. Performance class and filesystem type are IMMUTABLE — choose carefully. xfs/ext4 support snapshots; shared is read-write-many but cannot be snapshotted. Snapshot defaults injected when omitted: createFinalSnapshot=true, retentionDuration "7d". customEncryption (customer-managed KMS keys) cannot be set here — apply a full manifest with the CLI (`cpln apply`), calling get_resource_schema (kind=volumeset) first. Mount separately via mount_volumeset_to_workload (ext4/xfs need a stateful or vm workload; shared mounts on any workload type). Recommended reading before first use: get_cpln_skill("stateful-storage") — the runbook for this tool family (read once per session).
    ConnectorOAuth
  • Run forensic windows analysis (AACE RP 29R-03 §3.3, MIP 3.3 Observational / Dynamic / Contemporaneous As-Is) across multiple Primavera P6 XER snapshots and return the full analysis dict. This is the headline forensic tool — it computes per-window completion shifts, per-window slip registers (per-activity slip with critical/non-critical flag), per-window duration growth on critical-path activities, per-window per-party attribution (Owner / Contractor / Concurrent / Force Majeure / Unattributed), and cumulative project drift from baseline. The attribution math satisfies the CPP conservation check, per the AACE 29R-03 §3.3.E.13 requirement that the summed per-period net impacts equal the difference between the first schedule update and the last schedule update used in the evaluation (per-party day buckets sum to project drift within ±1 day, no cascade-double- counting). Use this tool for the full multi-window forensic claim. If you already have a windows result and only want the per-window × per-party grid view, call ``concurrent_delay_matrix`` instead. Args: schedules: list of dicts in chronological order. Minimum 2 entries (baseline + at least one update). Each dict must contain ``label`` (str) and EXACTLY ONE of: - ``xer_path`` — server-side filesystem path, OR - ``xer_content`` — full XER text content. Use ``xer_content`` when calling a hosted MCP server from a remote client whose XER lives locally. project_name: optional override; auto-picked from XER if "". baseline_idx: which entry in ``schedules`` is the contract baseline (default 0 = first one). entitlement_milestone: optional task_code (e.g. "Ready for Takeover") — recorded on the result, not used for math. output_dir: optional dir for HTML dashboard / DOCX report. If "", a tempdir is used and dropped after — the dashboard / report paths in the response will point to the temp location (caller responsible for moving them). Returns: { "analysis": full dict from run_windows() with keys: "windows", "cumulative", "baseline_label", "data_dates", "attribution_summary", "mcpm_attribution", ..., "dashboard": path to HTML dashboard (server-side), "report": path to DOCX executive report (server-side), "baseline_stability": {"worst_severity", "has_block", ...} } On failure: {"error": "..."} with no schedules processed.
    ConnectorNo auth
  • Parse a Primavera P6 XER file and return a TABLE SUMMARY (not the full row-level data — XER row dumps explode the MCP context window). For each table in the XER, returns the table name, field list, and record count. Per-row data is intentionally omitted — for forensic / DCMA / windows analysis use the dedicated tools (``forensic_windows_analysis``, ``critical_path_validator``, etc.) which consume the parsed XER internally and return analytical summaries, not raw rows. Use this tool to confirm an XER is parseable, list its tables, see the data date / project name from PROJECT, or count activities in TASK before deciding which deeper tool to run. Args: xer_path: server-side filesystem path to the XER file. xer_content: full text of the XER file (alternative for hosted/remote use). Supply EXACTLY ONE of path/content. Returns: { "filepath": absolute path, "encoding_used": "utf-8" | "cp1252" | ..., "ermhdr": file header dict (P6 version, export user, etc.), "tables": [{"name", "fields", "record_count"}, ...], "table_count": int, "total_records": int, "project_summary": { "proj_id", "proj_short_name", "proj_long_name", "data_date", "plan_end_date" } (from first PROJECT row, if any) }
    ConnectorNo auth

Matching MCP Servers

  • F
    license
    Not graded
    quality
    A
    maintenance
    A filesystem MCP server that preserves file inode and metadata when writing or editing files, operating within allowed directories.
    1
    -
  • F
    license
    A
    quality
    B
    maintenance
    A minimal MCP server that exposes three file operations (read_file, write_file, list_directory) within a sandboxed workspace, enabling file management via natural language.
    3
    -

Matching MCP Connectors

  • Honeydew AI Documentation MCP — semantic search and ripgrep-grade filesystem queries over Honeydew AI docs and OpenAPI specs, for AI coding agents.

  • Political Comms documentation MCP server: search docs, query the docs filesystem. No auth.

  • Run a read-only shell-like query against a virtualized, in-memory filesystem rooted at `/` that contains ONLY the Cerebrium documentation pages and OpenAPI specs. This is NOT a shell on any real machine — nothing runs on the user's computer, the server host, or any network. The filesystem is a sandbox backed by documentation chunks. This is how you read documentation pages: there is no separate "get page" tool. To read a page, pass its `.mdx` path to `head` or `cat` — a page at the URL path `/some/page` lives at `/some/page.mdx`. To search the docs with exact keyword or regex matches, use `rg`. To understand the docs structure, use `tree` or `ls`. **Paths are specific to this site — never guess them.** Discover real paths with `tree / -L 2`, `ls /`, or the search tool before reading. If a path does not exist, that only means the guess was wrong; it does NOT mean the topic is undocumented — use `rg -il "keyword" /` to find where it is covered. **Workflow:** Start with the search tool for broad or conceptual queries like "how to authenticate" or "rate limiting". Use this tool when you need exact keyword/regex matching, structural exploration, or to read the full content of a specific page by path. Supported commands: rg (ripgrep), grep, find, tree, ls, cat, head, tail, stat, wc, sort, uniq, cut, sed, awk, jq, plus basic text utilities. No writes, no network, no process control. Run `--help` on any command for usage. Each call is STATELESS: the working directory always resets to `/` and no shell variables, aliases, or history carry over between calls. If you need to operate in a subdirectory, chain commands in one call with `&&` or pass absolute paths (e.g., `cd /some-directory && ls` or `ls /some-directory`). Do NOT assume that `cd` in one call affects the next call. Examples (replace the placeholder paths with real ones from `tree` or search): - `tree / -L 2` — see the top-level directory layout - `rg -il "rate limit" /` — find all files mentioning "rate limit" - `rg -C 3 "apiKey" /some-directory/` — show matches with 3 lines of context around each hit - `head -80 /some/page.mdx` — read the top 80 lines of a specific page - `head -80 /page-one.mdx /page-two.mdx /section/page-three.mdx` — read multiple pages in one call - `cat /some/page.mdx` — read a full page when you need everything - `cat '/openapi/https://s3.eu-west-1.amazonaws.com/www.cerebrium.ai/openapi_spec.json' | jq '.paths | keys'` — list OpenAPI endpoints OpenAPI specs for this site are mounted at: `'/openapi/https://s3.eu-west-1.amazonaws.com/www.cerebrium.ai/openapi_spec.json'`, `/openapi/package.json`, `/openapi/data/training-dataset-example.json`. Use them to answer questions about endpoints, request/response schemas, parameters, and authentication. Output is truncated to 30KB per call. Prefer targeted `rg -C` or `head -N` over broad `cat` on large files. To read only the relevant sections of a large file, use `rg -C 3 "pattern" /path/file.mdx`. Batch multiple file reads into a single `head` or `cat` call whenever possible. When referencing pages in your response to the user, convert filesystem paths to URL paths by removing the `.mdx` extension. For example, `/some/page.mdx` becomes `/some/page`.
    ConnectorNo auth
  • Upload data to work on. This hosted endpoint has no filesystem, so instead of a file path you send the data once with sheet_load and then pass its name as `path` to sheet_info, sheet_read, sheet_query, sheet_stats, sheet_find, sheet_add_column, sheet_convert and sheet_write. Give exactly one of csv (raw text, comma or tab separated), xlsx_base64 (a base64-encoded .xlsx workbook) or url. url: fetch a public file instead of pasting base64 (recommended above about 10 KB): the url is fetched here with a 10 second timeout, at most 3 redirects, public http(s) hosts only, and a 2 MB cap, and a fetched file is stored as an .xlsx when it carries the PK zip header and as delimited text otherwise. Loaded sheets are kept for your token and survive between calls; the total is capped at 2 MB per token. Files the other tools write come back as a download link that is valid for one hour.
    ConnectorNo auth
  • Return bounded rows for a dataflow — the completion path for hosted clients. Use this when the client cannot execute a client-download plan locally (no shell/filesystem — e.g. a hosted store app or connector) but still needs actual values. ``fetch`` server-side downloads the exact GET/fan-out plan ``build_url`` would produce, concatenates it, runs one bounded literal-equality query, and releases the artifact — the raw dataset never enters model context. Clients that CAN execute locally should keep using ``ask``/``build_url`` and run the plan themselves; ``fetch`` is the affinity-free hosted shortcut, not the power path. POST-only selections have no hosted download path: ``fetch`` raises ``fetch_shape_unsupported`` and the caller must execute the ``build_url`` plan client-side. A rejected/over-length selection raises the same reason ``build_url`` would report; narrow the selection and retry. **``fetch`` does not page, deliberately.** It holds no dataset between calls: every call rebuilds the plan, re-downloads every part from the provider, and releases the artifact. An offset over that would be unsound as well as wasteful — there is no snapshot behind the cursor, so rows shifting upstream between calls would silently skip or duplicate observations, and N pages would mean N full downloads of the same dataflow from an agency that may rate-limit. When a result is ``truncated``, narrow it (``select``, ``where``, ``time_range``) or switch to ``stage_url`` + ``query_dataset``, which pages with ``offset`` over ONE immutable staged artifact and downloads once. ``no_records_for_selection`` is TERMINAL, not a fault: the request was well-formed and the source holds no observations for it. Widen the selection or state that no data exists — do not retry the same selection. Only ``upstream_origin_error`` (an origin fault) and ``upstream_rate_limited`` are worth retrying. Args: agency_id: SDMX agency code, e.g. "ABS", "ESTAT", "OECD" dataflow_id: SDMX dataflow identifier, e.g. "ERP_Q" selections: Optional {dimension_id: [code or name, ...]} to anchor the query time_range: Optional time filter (e.g. "2020-2024", "since 2015", "2024") precision: URL breadth — "point", "series" (default), or "cube" availability: "confirmed" (default) or "best_effort" select: Optional list of columns to return (defaults to all columns) where: Optional {column: value | [values]} literal-equality row filters limit: Optional max rows to return (a safe default applies when omitted) max_bytes: Optional smaller byte budget for this response; it can only lower the server ceiling, never raise it response_format: Which channel carries the rows. "auto" (default) means no preference and lets the server decide; "text" sends them as CSV in the text channel only, "structured" as typed rows only, "both" in both. If you got a summary but no rows, call again with response_format="text".
    ConnectorOAuth
  • Free (requires an active plan). Upload one reference image and get a `reference_id` to reuse: a product photo, a character, a brand shot. Give exactly one of image_base64 or file_path. image_base64 - the image bytes as base64 (a `data:image/png;base64,...` URL is also accepted); this is the way for any remote agent, because the image never has to be public. file_path - a path on the FILESYSTEM OF THE MCP SERVER, so it only works for local / self-hosted runs where the server and the agent are on the same machine, and only when the server enables it (otherwise the tool answers with code local_files_disabled - then send image_base64 instead). Formats jpeg, png, webp, heic, up to 10 MB, shorter side at least 360 px, longer at most 4096 px. Bad input comes back as validation_error with details.reason, before anything is uploaded: one_source_required (gave both or neither), bad_base64, empty, not_image, too_small, too_large_dimensions, too_large; a file_path that cannot be read is file_not_readable, and a server that forbids local files answers with code local_files_disabled. label - a short note (e.g. "hero", "product"), optional, kept to the first 120 characters. Returns reference_id, the stored url, the label and a model-written description. The reference expires together with scenarios (the server's scenario TTL, 7 days by default), so upload it again for a later video. Pass the returned reference_id in `reference_urls` of tegas_write_scenario or tegas_start_video - no public link needed. Errors: no_active_plan -> ask the user to activate a plan in the cabinet.
    ConnectorOAuth
  • Free (requires an active plan). Upload one music track and get a `url` to reuse in tegas_edit_video's `music.url`. Give exactly one of audio_base64 or file_path. audio_base64 - the audio bytes as base64 (a `data:audio/mpeg;base64,...` URL is also accepted); this is the way for any remote agent, because the file never has to be public. file_path - a path on the FILESYSTEM OF THE MCP SERVER, so it only works for local / self-hosted runs where the server and the agent are on the same machine, and only when the server enables it (otherwise the tool answers with code local_files_disabled - then send audio_base64 instead). Formats mp3, wav, m4a, up to 25 MB. Bad input comes back as validation_error with details.reason, before anything is uploaded: one_source_required (gave both or neither), bad_base64, empty, not_audio, too_large; a file_path that cannot be read is file_not_readable, and a server that forbids local files answers with code local_files_disabled. label - a short note (e.g. "background track"), optional, kept to the first 120 characters. Returns music_id, the stored url, the label and expires_at. Pass the returned url in `music.url` of tegas_edit_video (and set `music.enabled` to true if music was off). Errors: no_active_plan -> ask the user to activate a plan in the cabinet.
    ConnectorOAuth
  • Upload data to work on. This hosted endpoint has no filesystem, so instead of a file path you send the data once with sheet_load and then pass its name as `path` to sheet_info, sheet_read, sheet_query, sheet_stats, sheet_find, sheet_add_column, sheet_convert and sheet_write. Give exactly one of csv (raw text, comma or tab separated), xlsx_base64 (a base64-encoded .xlsx workbook) or url. url: fetch a public file instead of pasting base64 (recommended above about 10 KB): the url is fetched here with a 10 second timeout, at most 3 redirects, public http(s) hosts only, and a 2 MB cap, and a fetched file is stored as an .xlsx when it carries the PK zip header and as delimited text otherwise. Loaded sheets are kept for your token and survive between calls; the total is capped at 2 MB per token. Files the other tools write come back as a download link that is valid for one hour.
    ConnectorNo auth
  • Upload data to work on. This hosted endpoint has no filesystem, so instead of a file path you send the data once with sheet_load and then pass its name as `path` to sheet_info, sheet_read, sheet_query, sheet_stats, sheet_find, sheet_add_column, sheet_convert and sheet_write. Give exactly one of csv (raw text, comma or tab separated), xlsx_base64 (a base64-encoded .xlsx workbook) or url. url: fetch a public file instead of pasting base64 (recommended above about 10 KB): the url is fetched here with a 10 second timeout, at most 3 redirects, public http(s) hosts only, and a 2 MB cap, and a fetched file is stored as an .xlsx when it carries the PK zip header and as delimited text otherwise. Loaded sheets are kept for your token and survive between calls; the total is capped at 2 MB per token. Files the other tools write come back as a download link that is valid for one hour.
    ConnectorNo auth
  • Upload data to work on. This hosted endpoint has no filesystem, so instead of a file path you send the data once with sheet_load and then pass its name as `path` to sheet_info, sheet_read, sheet_query, sheet_stats, sheet_find, sheet_add_column, sheet_convert and sheet_write. Give exactly one of csv (raw text, comma or tab separated), xlsx_base64 (a base64-encoded .xlsx workbook) or url. url: fetch a public file instead of pasting base64 (recommended above about 10 KB): the url is fetched here with a 10 second timeout, at most 3 redirects, public http(s) hosts only, and a 2 MB cap, and a fetched file is stored as an .xlsx when it carries the PK zip header and as delimited text otherwise. Loaded sheets are kept for your token and survive between calls; the total is capped at 2 MB per token. Files the other tools write come back as a download link that is valid for one hour.
    ConnectorNo auth
  • Upload data to work on. This hosted endpoint has no filesystem, so instead of a file path you send the data once with sheet_load and then pass its name as `path` to sheet_info, sheet_read, sheet_query, sheet_stats, sheet_find, sheet_add_column, sheet_convert and sheet_write. Give exactly one of csv (raw text, comma or tab separated), xlsx_base64 (a base64-encoded .xlsx workbook) or url. url: fetch a public file instead of pasting base64 (recommended above about 10 KB): the url is fetched here with a 10 second timeout, at most 3 redirects, public http(s) hosts only, and a 2 MB cap, and a fetched file is stored as an .xlsx when it carries the PK zip header and as delimited text otherwise. Loaded sheets are kept for your token and survive between calls; the total is capped at 2 MB per token. Files the other tools write come back as a download link that is valid for one hour.
    ConnectorNo auth
  • Return the list of ARCO variables available for a dataset. Each row's type (index 2) is either "zarr" or "reference" (kerchunk). A "reference" variable is often listed multiple times, once per kerchunk reference variant (plain, "-remote-https", "-remote-osdf", etc.) — always pick the "-osdf" variant's URL; the others' chunk targets can be internal paths that only resolve on NCAR's network. Open it with xr.open_dataset(url, engine="kerchunk", storage_options={"remote_protocol": "https", "lazy": True}) — that's better behaved than hand-building an fsspec reference filesystem. A "zarr" row needs no variant picking — its URL already routes through the OSDF director (rewritten automatically); open it directly with xr.open_dataset(url, engine="zarr"). Results are capped at 300 rows (look for "truncated": true); narrow with search_arco_variables if you hit the cap. Args: dsid: Dataset ID (dNNNNNN), e.g. d083002
    ConnectorNo auth
  • When to use: Hugging Face Hub models, datasets, Spaces, collections, papers, daily papers, today's trending models, current paper leaderboard, docs, and repository files. Examples: {"operations":[{"cmd":"ls","args":["hf://models/trending","--limit","10"]}]} {"operations":[{"cmd":"ls","args":["hf://papers/trending"]}]} {"operations":[{"cmd":"ls","args":["hf://papers/daily/latest"]}]} {"operations":[{"cmd":"cat","args":["hf://papers/2501.00001/paper.md"]}]} Use hf_fs for Hugging Face Hub filesystem operations. Call it with operations, an array of {cmd, args} items; multiple operations may be submitted together. Usage: {"operations":[{"cmd":"ls","args":["hf://models/org/repo"]}]} Grammar; each string below is one args array item: ls URI [--recursive] [--glob GLOB] [--type TYPE] [--sort SORT] [--limit N] cat URI [--offset N] [--max-bytes N] attach URI [--max-bytes N] stat URI find URI [--name GLOB] [--path GLOB] [--type TYPE] [--limit N] search URI [QUERY] [--type TYPE] [--sort SORT] [--tag TAG] [--kind mcp] [--limit N] COMMAND = ls|cat|attach|stat|find|search. TYPE = file|dir|repo|bucket|collection|paper|link. SORT = createdAt|downloads|likes|lastModified|likes30d|trendingScore|mainSize|id|trending|upvotes. URI is a canonical hf:// URI. QUERY and GLOB are each one string. Use search for resource discovery, not repository-content search; ls for a known directory, find for recursive file discovery by name/path (not file contents), stat for filesystem metadata or an uncertain target type, cat for text contents, and attach for a complete JPEG, PNG, or WebP image. When the request gives an exact text-file URI, use cat directly; do not add ls or stat first. stat does not read the contents of JSON, Markdown, or other text files. Search scopes: hf://models[/OWNER], hf://datasets[/OWNER], hf://spaces[/OWNER], hf://collections[/OWNER], hf://papers, and hf://docs[/...]. Repository and repository-file scopes are not supported: search a resource root or owner scope to discover resources; use find for file discovery within a repository or cat for a known text file. Paper and documentation search require QUERY. --tag (repeatable) and --kind are supported only on exactly hf://spaces, not owner scopes or other roots. The only valid --kind value is mcp, which selects MCP Spaces. Use ls hf://models/trending, hf://datasets/trending, hf://spaces/trending, or hf://papers/trending for trending listings. hf://papers/ID is a paper directory, not paper text. Use cat hf://papers/ID/paper.md for paper text and cat hf://papers/ID/metadata.json for metadata. No preliminary listing is needed for these known paths. Use ls hf://papers/ID to discover other resources. Omit --limit, --sort, and --type unless the request requires them. Limits and path-specific behavior are documented at hf://README.md. Issue one hf_fs call.
    ConnectorNo auth
  • Download a completed Future Video Studio final render URL to a local file. Use this only after fvs_get_render_status or fvs_get_paid_render_status returns a final_video_url for a completed render. The tool performs an unauthenticated HTTPS GET to that signed URL and writes the response bytes to output_path on the MCP server's local filesystem. It does not call the FVS Agent API, spend wallet credits, require FVS_AGENT_API_KEY, cancel jobs, or modify remote render state. Side effects and constraints: output_path is a local filesystem path for the MCP server process, parent directories are created, existing files are not replaced unless overwrite is true, and large videos may take minutes to download. The request timeout is 600 seconds. Use a fresh status check to refresh expired signed URLs, and do not pass arbitrary or untrusted URLs.
    Connector
    Destructive
    No auth
  • Analyze text for writing style issues: weasel words, passive voice, duplicate words, long sentences, nominalizations, hedging, filler adverbs, and research-cited AI tells. Read-only and stateless — text is analyzed in memory on the hosted server and never stored. Returns a plain-text report with each issue's line and column, the matched text, surrounding context, and the reason for AI tells; texts over 100,000 characters return an error message. This hosted server has no filesystem access — the wsc-mcp npm package adds a check_file tool for local files. It only reports issues — to auto-remove duplicate words, follow up with fix_duplicates.
    ConnectorNo auth
  • Restores a backup into an existing volume (volumeId), an instance's volume (instanceId), or a new one (volumeName). Poll list_volumes for the restored volume. DISASTER RECOVERY (the original VM is gone, so its volume died with it): restore with volumeName to rebuild the data as a NEW volume. To bring the MACHINE back, pass that volume as create_instance's boot_volume_id - it boots from the restored disk, so the VM returns with its filesystem intact and nothing to mount. Use attach_volume instead only when you want the data as an EXTRA disk on an existing machine (then get_ssh_command -> lsblk -> mount). A restored volume is inert until it is booted from or attached.
    ConnectorNo auth
  • Run a read-only shell-like query against a virtualized, in-memory filesystem rooted at `/` that contains ONLY the nTop documentation pages. This is NOT a shell on any real machine — nothing runs on the user's computer, the server host, or any network. The filesystem is a sandbox backed by documentation chunks. This is how you read documentation pages: there is no separate "get page" tool. To read a page, pass its `.mdx` path to `head` or `cat` — a page at the URL path `/some/page` lives at `/some/page.mdx`. To search the docs with exact keyword or regex matches, use `rg`. To understand the docs structure, use `tree` or `ls`. **Paths are specific to this site — never guess them.** Discover real paths with `tree / -L 2`, `ls /`, or the search tool before reading. If a path does not exist, that only means the guess was wrong; it does NOT mean the topic is undocumented — use `rg -il "keyword" /` to find where it is covered. **Workflow:** Start with the search tool for broad or conceptual queries like "how to authenticate" or "rate limiting". Use this tool when you need exact keyword/regex matching, structural exploration, or to read the full content of a specific page by path. Supported commands: rg (ripgrep), grep, find, tree, ls, cat, head, tail, stat, wc, sort, uniq, cut, sed, awk, jq, plus basic text utilities. No writes, no network, no process control. Run `--help` on any command for usage. Each call is STATELESS: the working directory always resets to `/` and no shell variables, aliases, or history carry over between calls. If you need to operate in a subdirectory, chain commands in one call with `&&` or pass absolute paths (e.g., `cd /some-directory && ls` or `ls /some-directory`). Do NOT assume that `cd` in one call affects the next call. Examples (replace the placeholder paths with real ones from `tree` or search): - `tree / -L 2` — see the top-level directory layout - `rg -il "rate limit" /` — find all files mentioning "rate limit" - `rg -C 3 "apiKey" /some-directory/` — show matches with 3 lines of context around each hit - `head -80 /some/page.mdx` — read the top 80 lines of a specific page - `head -80 /page-one.mdx /page-two.mdx /section/page-three.mdx` — read multiple pages in one call - `cat /some/page.mdx` — read a full page when you need everything Output is truncated to 30KB per call. Prefer targeted `rg -C` or `head -N` over broad `cat` on large files. To read only the relevant sections of a large file, use `rg -C 3 "pattern" /path/file.mdx`. Batch multiple file reads into a single `head` or `cat` call whenever possible. When referencing pages in your response to the user, convert filesystem paths to URL paths by removing the `.mdx` extension. For example, `/some/page.mdx` becomes `/some/page`.
    ConnectorNo auth