"Creative and simple use cases for MCP with SSE URLs" matching MCP tools:

• zaira_get_docs

  Zaira Labs Guide

  Retrieve reference documentation for the Zaira Guide API and MCP server on demand. Topics: - getting_started — how to connect via MCP or REST, first queries - endpoints — full REST endpoint reference with parameters - mcp_tools — MCP tool reference with when-to-use guidance and a routing matrix - schema — the tool entry schema - errors — error taxonomy for REST (RFC 9457) and MCP (JSON-RPC) Call with no topic to get an index of available topics. Returns: the requested topic as a Markdown-KV block. With no topic, returns an index listing all available topics with short descriptions; call again with the relevant topic for the full content. Examples (topic selection): - "How do I call the REST API?" → {topic: "getting_started"} - "What parameters does /tools accept?" → {topic: "endpoints"} - "What fields are in a tool entry?" → {topic: "schema"} - "What error shapes do I handle, and what are the recovery steps?" → {topic: "errors"} - "Which MCP tool fits my task?" → {topic: "mcp_tools"} Edge cases: - No topic argument is valid — you get the index. This is the deferred-loading path; don't load every topic at once. - Topic must match the enum exactly (lowercase, underscore). "getting-started" with a hyphen is rejected as an unknown parameter. Risk: read-only, closed-world, idempotent — no state change possible.

  Connector

• upload_file

  CNAPS.ai MCP Server

  Get a file into cnaps.ai so a flow can use it. Handles images, video, audio and text (png, jpg, webp, RAW / mp4, mov, webm, mpeg, avi, flv, wmv, 3gp / wav, mp3, m4a, aac, ogg, flac / txt). Two ways in, chosen by what you pass: (1) The user gave a public HTTP/HTTPS URL → pass file_url and it is registered directly. (2) The file is on the user's machine → pass nothing, and you get back an upload link to show them; then call again with the returned token to wait for the upload and get the URLs. You CANNOT send bytes from the chat through MCP — even if you can see the image or video, use the link flow. Returns URLs usable in create_flow input_files or run_flow inputs.

  Connector

• fvs_download_final_video

  Future Video Studio

  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

• stream_task

  TunnelMind Data API

  Opens a persistent SSE connection that emits events as the task progresses. The stream closes automatically when the task reaches a terminal state or after ~90 seconds (timeout). Heartbeat comments are sent every ~15 seconds to keep the connection alive through proxies. Event types: - `status` — emitted when status changes (pending → running → complete/failed) - `result` — emitted on `complete` with the full result payload - `error` — emitted on `failed`, `cancelled`, or `expired` with error info - SSE comment (`: heartbeat`) — keepalive, no data Use this tool when: - You want real-time progress without polling. - You are in an environment that supports SSE (EventSource API). Do NOT use this tool when: - You want a simple one-shot status check — use `get_task` instead. - Your HTTP client doesn't support streaming responses. Inputs: - `task_id` (path, required): 26-char ULID. Returns: - SSE stream (`text/event-stream`). Each event is `event: <type>\\ndata: <json>\\n\\n`. Cost: - Free. Counts as one request against rate limits when the stream opens. Latency: - First event: <200ms. Stream duration: up to 90s.

  Connector

• call_creative_worlds

  Heista

  Heista's creative direction engine — same engine the Creative Director specialist runs internally, exposed over MCP. ONE-SHOT: give a brief, get N finished creative outputs. For back-and-forth refinement, or output shapes the `medium` enum below does not cover, use chat_with_creative_worlds instead. OUTPUT SHAPE switches on the `medium` arg: • omitted → N territory cards (default exploration). Each card sits on different psychology / craft / feel / world axis coordinates so the set spans the creative space rather than orbiting one insight. Card has: name, campaign line, 5-8 sentence pitch, one-sentence strategic bet, resolved axis state names, creative-director rationale. • `tvc` → N TVC scripts (15-90s — hook, arc, resolve, sound design, end line). • `billboard` / `ooh` / `print` → N out-of-home concepts (visual concept + line + placement rationale). • `social` → N social-video concepts (hook + format type + middle beat + payoff, optimised for Reels / TikTok / Shorts). • `activation` / `experiential` → N activation concepts (space design + user journey + peak moment + takeaway artifact). • `audio` → N sonic / radio concepts (sonic scene + voice + audio arc). • `campaign` → N full campaign platforms (insight → big idea → strategy → visual world → production roadmap). The engine can also produce manifesto / copy, naming, packaging, PR stunts, content series, brand positioning, partnerships — these output shapes are NOT in the medium enum, so use chat_with_creative_worlds when the user wants one of those. USE WHEN: user says "give me ideas / options / directions / territories", "what angles work for...", "show me three / five ways to...", "write a TVC for...", "draft billboard concepts for...", "I need fresh thinking on...". DO NOT USE to refine one existing direction (use chat tool), to critique work, for OKRs / internal docs / strategy decks, or anything outside advertising creative direction. INPUTS: brief (the creative problem, free text), count (2-6 concepts), optional brand_id (from list_brands or any create_powersource_* — when provided the engine grounds output in the brand's buyer tensions, voice, and selling points), optional medium (above), optional lens_hint (apply a playbook or signature move as a creative constraint), idempotency_key (safely retryable for 5 minutes). Returns the finished creative output as narrative text PLUS a structured array of resolved axis coordinates for programmatic use. Metered — typically 3-15 credits per call depending on count and brand context size. Charged after success on actual token usage.

  Connector

• get_channel_feed

  PoolParty Main Stage Airtime

  Get rich recent airings and current queue evidence for a PoolParty channel. Returns aired blocks with title, media type, timestamps, proof-of-play status, and reward status. Also returns current queue positions with mintStatus and poolEligibility so agents can distinguish pre-mint, mint-pending, minted, pool-eligible, and ineligible blocks. get_channel_feed is a rich feed and may be large. Use it for diagnostic recent airing and queue evidence, mintStatus, poolEligibility, proof, and reward readbacks. For first-pass channel awareness, use get_channel_stream(channelSlug="main", limit=10) or the REST /api/channels/main/activity snapshot; use /api/channels/main/activity/stream when an SSE watch is intended. Read-only. No auth required.

  Connector

• get_pdf

  turnale

  The printable PDF itself, returned as a base64 embedded resource — use this when the organiser wants the file handed to them and your client cannot fetch URLs. Default "sheet": the merged tournament document (match sheet with write-in score boxes, player sheet, standings/results when they exist). "results" and "plan" are deprecated pre-merge variants kept for comparison. For a lighter response, get_pdf_link returns download URLs instead.

  Connector

• caselaw_search

  caselaw

  Full-text search of 197,000+ Pakistani judgments (Supreme Court & High Courts, 1970–2025). Ranking follows how lawyers research: nearness to the legal point decides which cases are returned; among comparably-near cases, more senior court > larger bench > more recent > more cited. Use sort='newest' when you need the current state of the law (later judgments supersede as statutes are amended), or sort='court' for the most authoritative first. Returns ranked cases with id, title, citation, court, year, a snippet, and the public URL. For an exact report citation use caselaw_lookup_citation. To read a case, pass its id to caselaw_get_case.

  Connector

• tflogs

  InsideOut (Riley)

  MONITORING: Fetch Terraform deployment logs with pagination Fetches logs from a running or completed Terraform deployment job. For **completed jobs**: uses REST endpoint for instant retrieval (supports `tail` for server-side filtering). For **running jobs**: streams via SSE with timeout-based pagination. **PAGINATION** (running jobs only): Use `last_event_id` from the response to fetch more: 1. First call: `tflogs(session_id='...')` → get logs + `last_event_id` 2. Next call: `tflogs(session_id='...', last_event_id='...')` → get NEW logs only 3. Repeat until `complete: true` in response **RESPONSE FIELDS**: - `logs`: Array of log messages collected - `last_event_id`: Pass this back to get more logs (pagination cursor, SSE only) - `complete`: true if job finished, false if more logs may be available - `total_logs`: total log entries before tail truncation REQUIRES: session_id from convoopen response (format: sess_v2_...). OPTIONAL: job_id to target a specific deployment (use tfruns to discover IDs), timeout (default 50s, max 55s), last_event_id (for pagination), tail (return only last N entries) ⚠️ CONTEXT WARNING: Deploy logs can be hundreds of lines. Use tail: 50 for completed jobs to avoid blowing up the context window.

  Connector

• firecrawl_parse

  firecrawl-mcp

  Parse one supported document into markdown, HTML, links, summary, targeted answers, or JSON matching a schema. Supported inputs include common HTML, PDF, Word, RTF, OpenDocument, and spreadsheet files; PDF parsing can be bounded with `pdfOptions.maxPages`. Local MCP reads `filePath` from the server filesystem. Hosted MCP uses two calls: first provide `filePath` to receive upload instructions, upload locally, then call again with the returned `uploadRef`; do not send both fields together. Remote web URLs belong in `firecrawl_scrape`. Set `redactPII` to request redaction of personally identifiable information in the returned content. `zeroDataRetention` requires an eligible authenticated account; omit it for anonymous keyless use. Returns upload instructions for hosted phase one or parsed document content for the final call.

  Connector

• recommend_icons

  Supericons

  Recommend a coherent icon set for up to 20 named UI slots in one call. Uses task context to narrow ambiguous meanings. When context is insufficient, returns needs_clarification with labeled interpretation options instead of guessing. Invalid inputs and service failures return a plain-language reason and a next step instead of a bare protocol error. Returns one recommendation and optional alternatives for each resolved slot, with explicit public library labels and visual preview URLs where available. Library key si means Supericons, not Simple Icons.

  Connector

• tflogs

  InsideOut (Riley)

  MONITORING: Fetch Terraform deployment logs with pagination Fetches logs from a running or completed Terraform deployment job. For **completed jobs**: uses REST endpoint for instant retrieval (supports `tail` for server-side filtering). For **running jobs**: streams via SSE with timeout-based pagination. **PAGINATION** (running jobs only): Use `last_event_id` from the response to fetch more: 1. First call: `tflogs(session_id='...')` → get logs + `last_event_id` 2. Next call: `tflogs(session_id='...', last_event_id='...')` → get NEW logs only 3. Repeat until `complete: true` in response **RESPONSE FIELDS**: - `logs`: Array of log messages collected - `last_event_id`: Pass this back to get more logs (pagination cursor, SSE only) - `complete`: true if job finished, false if more logs may be available - `total_logs`: total log entries before tail truncation REQUIRES: session_id from convoopen response (format: sess_v2_...). OPTIONAL: job_id to target a specific deployment (use tfruns to discover IDs), timeout (default 50s, max 55s), last_event_id (for pagination), tail (return only last N entries) ⚠️ CONTEXT WARNING: Deploy logs can be hundreds of lines. Use tail: 50 for completed jobs to avoid blowing up the context window.

  Connector

• extract_contract_from_url

  transaction-coordinator

  Extract structured transaction data from a contract at a URL. Downloads the document, extracts text (with OCR fallback for scanned PDFs), and runs PrimaCoda's contract-extraction prompt to return parties, addresses, dates, prices, and key contract fields. Use this when an agent has the contract hosted somewhere (Dropbox, Google Drive direct download, Square Space, etc.) and wants to skip the upload step. For multi-document deals (purchase + addenda + disclosures), use the PrimaCoda dashboard's batch upload — this tool handles ONE document. Args: pdf_url: Direct download URL for the contract (PDF, DOCX, TXT, or image). Must be reachable from the PrimaCoda server. Google Drive "shared link" URLs work if set to "anyone with link"; other share URLs may need their direct-download form. api_key: Your PrimaCoda MCP API key (starts 'pck_').

  Connector

• decode_ad

  Heista

  Decode a specific video ad URL into its full structural formula — beat-by-beat breakdown, hook classification, behavioral psychology stack, creative format, runtime performance signals (active days on Meta Ad Library when available), and per-cut visual data. Takes one video URL plus an optional idempotency_key. Returns a job_id immediately; poll with get_decode every 15s until status is "completed" (typically 45-60s end-to-end). Use this when the user pastes an ad URL, names a specific competitor ad, asks "decode this" or "break down this ad" or "what makes this ad work", or wants sentence-level fidelity to one specific winner before writing a script with generate_adscript. Supports Facebook Ad Library, TikTok, Instagram Reels, YouTube Shorts, and direct .mp4 URLs. Costs 15 credits for videos ≤60s, 20 credits for 61-120s. Do NOT use to browse the corpus or find ads by category — use decoder_intelligence or adformula_intelligence (both free) for discovery. Do NOT use for image ads or static creative.

  Connector

• update_segment_content

  framesail

  Rewrite one segment's creative direction from feedback ("make this shot a close-up", "show the machine from above") — an LLM rewrites the shot's prompts; continuation links, SFX, and overlays are preserved. The visual assets reset to not_started: re-render them afterwards (generate_segments or regenerate_segment_asset). For a precise prompt tweak with no rewrite, use regenerate_segment_asset with editable_sections instead.

  Connector

• find_similar_creatives

  CreativeScope — Mobile Game Ad Creative Intelligence

  Find visually similar creatives using the stored vector of an existing creative. For a concept without an ID, query selects an explainable seed from available creative metadata and then uses the same vector-neighbor search. For an English concept, send the original English terms only. The service resolves Chinese source-label equivalents internally before selecting the seed. Returns creative records ordered from most to least visually similar; low-similarity and near-duplicate results are excluded, and raw similarity scores are not exposed. If request_echo.seed_basis identifies a proxy seed, clearly disclose that limitation instead of presenting the results as an exact concept match. Example: 'Show variants of the toilet run viral creative concept.'

  Connector

• submit_brief

  IBO Studio MCP

  Submit the creative brief for a PAID order: pass order_token (from get_order; session ids are not accepted here) plus project fields (product, goal, audience, channels, resolution, launch, links, constraints) and files[] from create_upload_url. Delivery resolution must be selected before creative kickoff. Customer identity comes from the verified payment. NOTE: unpaid/anonymous submissions are rejected here; for Custom Production inquiries without payment use the submit_custom_inquiry tool instead.

  Connector

• recommend_icons

  Supericons

  Recommend a coherent icon set for up to 20 named UI slots in one call. Uses task context to narrow ambiguous meanings. When context is insufficient, returns needs_clarification with labeled interpretation options instead of guessing. Invalid inputs and service failures return a plain-language reason and a next step instead of a bare protocol error. Returns one recommendation and optional alternatives for each resolved slot, with explicit public library labels and visual preview URLs where available. Library key si means Supericons, not Simple Icons.

  Connector

• ccs_info

  SqueezeOS — Institutional AI Market Intelligence

  Cognitive Credit Swarms discovery endpoint. Returns full system description, how-it-works, verdict definitions, pricing, all endpoint URLs, and MCP tool list. Written for AI agents to parse. Free — this is the doorbell. Use this first to understand the CCS system before calling ccs_validate.

  Connector

• test_hypothesis

  Ground Truth - Fresh Evidence for AI Agents

  Run a small verification plan made of concrete live checks and summarize whether a hypothesis is supported. Use this when one conclusion depends on multiple simple checks such as endpoint reachability, npm search counts, or whether a page contains an exact substring. This is a coordination tool, not an open-ended research agent: every test must be explicitly defined in advance, and tests run in order with no branching or early exit. The final verdict is mechanical: all tests passing => SUPPORTED, zero passing => REFUTED, otherwise PARTIALLY SUPPORTED. Use verify_claim when you already have evidence URLs, estimate_market for category sizing, and compare_competitors when you already know exact package names.

  Connector