"pandas" matching MCP tools:

• customer_tiering_get_engineA

  Customer Intelligence & SegmentationA

  For books LARGER than 500 transaction rows. Returns a complete, runnable Python script that scores the book into A/B/C/D tiers with survival modelling (BG/NBD), spend modelling (Gamma-Gamma), tier migration, a money layer and plain-language decision cards. Run it in your code sandbox against the user's transaction file. The rows never pass through you as tokens, so a 10,000-row book costs the same to run as a 600-row one. Needs numpy. Prints ranked decisions and headline figures; writes the full per-customer ledger to customer_tiering_result.json beside the input file. No customer data reaches this server on this path. SAVE AND RUN THE RETURNED SCRIPT VERBATIM — every block of it is required for the computation. Do not retype it from memory, shorten it, reformat it, split it up, or reimplement the maths with pandas/sklearn; only the PATH / AS_OF / CURRENCY / OUT / OVERRIDES / CONTACTS lines at the bottom may be edited. The script cleans customer identities itself before scoring — merging capitalisation and spelling variants by rule, printing what it merged, and listing the similar-but-unproven groups for you to rule on via OVERRIDES — so do not pre-clean the file or edit those rules. Optionally takes contacts_path, a log of rep calls or visits (customer_id + date only). It is not required and the book scores fine without it, but it is valuable: with it the money layer MEASURES what a contact is worth per tier from touched-vs-untouched tier transitions instead of assuming a flat rate, so ask for it whenever the user mentions a CRM, a call log or a visit register.

  ConnectorOAuth

• get_quickstartA

  Vector Panda DocumentationA

  The Vector Panda quickstart: install the veep Python SDK, upload a file, and run similarity queries end to end.

  ConnectorNo auth

• panda_list_profilesA

  Panda VideoB

  List all player profiles (GET /profile). 'Profiles' are player UI configs, not user accounts. Returns {data: [{id, name, pullzone_name}]} — a profile's `name` is the ID of the video it was created for. Use panda_get_profile for a profile's full settings. No pagination.

  ConnectorNo auth

• panda_create_profileA

  Panda VideoB

  Create a new player profile (POST /profile). IMPORTANT: per the Panda API, `name` MUST be the ID of an existing video — if it is not a real video ID the API returns 500 and nothing is created. Create only accepts `name` and `exclusive`; it does NOT accept colors/controls/vsl. To set those, call panda_update_profile with the returned profile id afterward. Returns {data: {id, name}}.

  ConnectorNo auth

• panda_add_pause_thumbnailA

  Panda VideoB

  Upload a pause thumbnail — an image shown when the viewer pauses the video. Provide `image_url` pointing to a publicly reachable image. Returns the uploaded thumbnail's filename. NOTE: the upload alone is NOT visible in the player — the viewer-facing display requires a pause CTA wiring (with time window and optional button overlay) which is configured separately via the dashboard. Use this MCP tool only to upload the asset; for full setup, redirect the user to the dashboard pause-thumbnail editor.

  ConnectorNo auth

• panda_add_end_thumbnailA

  Panda VideoB

  Upload an end thumbnail — an image shown after the video finishes. Provide `image_url` pointing to a publicly reachable image. Returns the uploaded filename. NOTE: the upload alone is NOT visible in the player — the viewer-facing display requires an `end` CTA on the player config that references this thumbnail. Use this MCP tool to upload the asset; for full setup (CTA wiring), redirect the user to the dashboard end-thumbnail editor.

  Connector

  Destructive

  No auth

• read_docA

  Vector Panda DocumentationA

  Fetch the full Markdown of one document by its site path (for example /docs/concepts/embeddings-101), as returned by search_docs.

  ConnectorNo auth

• get_pricingA

  Vector Panda DocumentationA

  Current storage-tier pricing, monthly usage credits, and billing cycle. Storage-only pricing: no per-query or egress fees.

  ConnectorNo auth

• run_pythonA

  Oblique MarketsC

  Run a short Python program in an isolated sandbox and get back exit code, stdout, stderr, duration and up to 3 artifact files from ./out/. Python 3.12 + numpy/pandas/requests, no network, 512 MB, 30 s max, 32 KB code, 4 input files of 256 KB. Free compile-only syntax check first at POST /api/v1/run-python/validate. $0.05/call (one run) via x402. Free syntax check: POST /api/v1/run-python/validate. Free worked example: GET /api/v1/run-python/example.

  ConnectorNo auth

• panda_update_profileA

  Panda VideoB

  Update a player profile's settings. Covers: player colors (colors.primaryColor / controlsColor), enabled controls list, smart autoplay (vsl.smartAutoplay), VSL mode (vsl.disablePause / disableForward / alternativeProgress), playback speed (general.default_speed), save progress, big play button (use panda_update_video_config — that lives elsewhere), and SUBTITLE APPEARANCE: caption text/background colors (captions.foreground / captions.background — 8-char hex with alpha) and caption font size (general.fontSize as keyword 'extraSmall'|'small'|'normal'|'large'|'extraLarge', plus general.fontSizePx as the matching pixel number). When the user names a UI label like "extra pequeno" / "extra small", map it to the corresponding fontSize keyword and send both fontSize + fontSizePx. Do NOT use this tool for: chapters (use panda_update_video_config), subtitle generation (use panda_generate_ai_subtitles), thumbnails, or title/description (use panda_update_video). Each nested object REPLACES the existing one — send the COMPLETE object you want to keep.

  Connector

  Destructive

  No auth

• panda_add_thumbnailA

  Panda VideoB

  Upload the video cover (start thumbnail) — the image shown before the user presses play. Provide `image_url` pointing to a publicly reachable image (PNG/JPG/WEBP); the tool downloads it and uploads as multipart to the Panda API. Replaces any existing start thumbnail. After this returns, the cover is active immediately for the player.

  ConnectorNo auth

• panda_action_delete_folder_videosA

  Panda VideoB

  Deterministically resolve a folder and send every video inside it to the trash (30-day recovery). DESTRUCTIVE. dry_run=true (default) returns a preview of what would be deleted; set dry_run=false AND confirm=true to actually delete.

  Connector

  Destructive

  No auth

• validate_csvA

  Project GumballA

  Validates CSV against RFC 4180 and reports ragged rows individually with both field counts, because "row 4813 has 6 fields, the header has 5" is the entire answer. A ragged row loads without complaint almost everywhere — pandas pads or throws by engine, Excel shifts the columns, split(",") mis-assigns every field after the extra one — so nobody notices until a figure is wrong. Sniffs the delimiter from the header ignoring quoted regions, and always reports it, because a semicolon-separated European export read as comma-separated yields one column and no error. Also unterminated quotes, duplicate and unnamed and space-padded column names, mixed line endings, and a byte order mark that makes the first column impossible to look up by name. WHY DELEGATE THIS: Syntax errors are the easy half. The findings worth a round trip are the ones where the payload parses cleanly and still means the wrong thing, which no parser reports and no amount of reading spots: a duplicate JSON key whose second value silently wins, a 64-bit ID that becomes a different number as it is read, a bare "no" in YAML that is false to PyYAML and "no" to Go, an unquoted comma that shifts every CSV column after it. Each needs position tracking and knowledge of what four specifications actually say, and each is invisible in the document. Owned by Payload Validator at https://payload-validator.gumballtools.com, which is also callable directly if you would rather not go through the aggregator.

  ConnectorNo auth

• validate_csvA

  Payload ValidatorA

  Validates CSV text against RFC 4180 and reports ragged rows individually, with both field counts. Use this before loading a CSV, and whenever a CSV-derived number looks wrong. Do not attempt this by reading the file, and be aware that loading it successfully proves nothing. The failure that matters is the ragged row: a file where one row has six fields and the header has five loads without complaint almost everywhere — pandas pads or throws depending on the engine, Excel shifts the columns, and `split(",")` silently mis-assigns every field after the extra one. Nobody notices until a figure is wrong in a report. This reports it as "row 4813 has 6 fields; the header has 5", per row. The other half is the delimiter. A European CSV is semicolon-separated because the comma is the decimal separator; reading it as comma-separated yields one column of nonsense and no error. The delimiter is sniffed from the header — ignoring quoted regions so their contents cannot vote — and always reported, with a warning when the guess was a close call. Pass `delimiter` to remove the guess entirely. Also reports: unterminated quotes (which swallow the rest of the file into one field, which is why one typo can make thousands of rows look ragged), text after a closing quote, stray quotes in unquoted fields, duplicate column names, unnamed columns, column names with invisible leading or trailing whitespace, mixed CRLF/LF line endings, CR-only endings, and a byte order mark — which becomes part of the first column's name, so a lookup for "id" fails against a column that prints identically. Input: `input`, the raw CSV text. Optional `delimiter` (a single character) and `hasHeader` (default true; pass false and rows are compared against the first row instead, and header checks are skipped). Up to 1,000,000 bytes. Returns: `valid` (no errors), `parseable` (whether a conforming parser would accept it — deliberately separate, because a duplicate key parses fine and still means two different things), a `diagnostics` array where each entry has a 1-based `line` and `column`, a stable `rule` code, a `message`, an `excerpt` showing the offending line with a caret under the column, a `fixHint`, and `blocksParse`; plus `counts` and format-specific `stats`. Rule codes are stable and safe to branch on; messages are not. Safety: nothing is resolved, fetched or expanded. External XML entities are reported, never retrieved; alias bombs are detected without being expanded; no schema or DTD is fetched over the network. Payloads are validated in memory and never stored.

  ConnectorNo auth

• get_api_operationA

  Vector Panda DocumentationA

  List public REST API operations, or pass one (e.g. "POST /api/v1/query") for its parameters, request body, responses, and auth. Sourced from the published OpenAPI spec.

  ConnectorNo auth

• list_supported_formatsA

  Vector Panda DocumentationA

  File formats accepted for vector ingestion, from the canonical features page.

  ConnectorNo auth

• panda_update_ai_assistant_video_bindingsA

  Panda VideoB

  Replace the videos bound to an AI assistant. Sends the FULL list of video_ids — existing bindings not in the list will be removed.

  Connector

  Destructive

  No auth

• panda_get_business_rulesA

  Panda VideoB

  Returns the platform business rules: the real consequences of actions that modify, delete or move resources (e.g., removing a video from a funnel deletes it permanently, it does not just unlink it). Useful before planning such actions, so the advice given to the user matches how the platform actually behaves. Domains: funnels, videos_and_folders, playlists, drm_watermark, comparisons_ab_tests, lives, shorts, player_profiles, anti_download_and_domains, credits, thumbnails_and_subtitles.

  ConnectorNo auth

• panda_list_refer_allA

  Panda VideoB

  List all of the library's domains consolidated by hostname across library and folder scopes. Returns { refers: [{ hostname, type, status, scope, library_refer_id, folders, type_inconsistency, created_at }] }. scope is library|folder|mixed; status may be 'mixed' when rows differ; library_refer_id is the library-level row id (null if folder-only); folders is an array of { folder_id, name, refer_id, status }; type_inconsistency=true when the same hostname has divergent ALLOW/BLOCK rows. Referrers with status=deleting are ignored. library_id is resolved automatically when omitted.

  ConnectorNo auth

• panda_create_referA

  Panda VideoB

  Add one or more library-level domain referrers. Each entry has a hostname and a type (ALLOW|BLOCK, default ALLOW). The same hostname cannot coexist as both ALLOW and BLOCK at the library scope (duplicate check is type-agnostic). New rows start in 'pending' (when domain protection is active) or 'inactive'. library_id is resolved automatically when omitted. On error the API returns { errCode, errMsg }.

  ConnectorNo auth

• panda_set_refer_statusA

  Panda VideoB

  Activate (active=true) or deactivate (active=false) a single referrer by refer_id. Activation moves inactive→pending; deactivation moves active→turning_inactive (the async worker finalizes the state). If the referrer is already in an intermediate state (pending|deleting|turning_inactive) the API returns 400 ({ errCode, errMsg }: 'Operation in progress, ...'). Works for both library- and folder-level referrers.

  Connector

  Destructive

  No auth