"Free AI Tools for Generating Images and Videos" matching MCP tools:

• create_agent

  Vendo AI

  Create a new AI sales agent. Costs 1 credit. The agent is created in DRAFT status and does not start contacting anyone — you still need to attach it to a campaign and launch the campaign. Required: name + description. Company info (name/website/description) is required BEFORE generating a sales script, so you can either pass it here OR call `set_agent_company` later.

  Connector

• start_contract_draft

  contracts

  Start generating a contract draft with Pactlio's multi-agent AI engine (drafter, critic, compliance checker). Takes 3-5 minutes — returns a preview_id immediately; poll get_draft_status. Free preview shows the opening sections; the full contract is unlocked by a human via checkout. Provide deal_summary fields collected via get_intake_questions (at minimum: parties, plus the required fields for the contract type).

  Connector

• convert_html_to_pdf

  Sats4AI - Bitcoin-Powered AI Tools

  Convert HTML or Markdown to a pixel-perfect PDF. Returns JSON: { url } — a temporary download URL (valid ~1 hour). Great for generating invoices, reports, receipts, or formatted documents programmatically. Supports full HTML/CSS including tables, images (base64 or URL), and inline styles. For Markdown input, set format='markdown'. 50 sats per conversion. Use convert_file instead for converting existing files between formats (e.g., DOCX→PDF). Pay per request with Bitcoin Lightning — no API key or signup needed. Requires create_payment with toolName='convert_html_to_pdf'.

  Connector

• picsart_generate

  Picsart GenAI

  Runs any Picsart AI model end-to-end to produce an image, video, audio, or text result. Spends credits. Recommended flow: `picsart_list_models` to pick the model → `picsart_model_params` to learn its inputs → `picsart_preflight` to validate the payload and quote cost → `picsart_generate` to actually run. Do NOT use this for editing operations that have dedicated tools — background removal (`picsart_remove_bg`), background replacement (`picsart_change_bg`), upscale / enhancement (`picsart_enhance`), or raster-to-SVG conversion (`picsart_vectorize`). Also do NOT use it to validate params, quote cost, or browse the catalog — those are separate tools above. Required inputs: `model` (id) and `prompt`. Model-dependent optional inputs: `duration` (video seconds), `aspectRatio` (e.g. "16:9", "9:16", "1:1"), `resolution` (e.g. "1080p", "4k"), `count` (1–8 outputs), `quality`, `style`, `negativePrompt`, `imageUrls` (for image-to-X models), `videoUrl` (for video-to-X), `enhancePrompt`, `generateAudio`, and `extra` — a free-form record for model-specific params (discover them via `picsart_model_params`). Example (image): `{ model: "flux-2-pro", prompt: "a cat in a hat", aspectRatio: "16:9", count: 1 }`. Example (video): `{ model: "kling-v3-pro", prompt: "a cat skiing down a mountain", duration: 5, aspectRatio: "16:9" }`. Returns `{ assets, id, model, created_at, prompt, summary, why_relevant, url, results: [{ url, metadata? }], drive? }` in structured content, plus one `resource_link` block per result URL — image models emit image links, video models emit video links (mime `video/mp4`). `id` is the SDK's generation handle; `metadata` may include model-specific tags (e.g. `exploreImageId` for Recraft Explore models). Text/LLM models (mode "text" in the catalog — e.g. gemini-3-pro, gpt-5.5, claude-*) run synchronously (`async` is ignored) and return the generated text as the text content block plus `text` in structured content. ChatGPT renders images and videos with the Picsart media gallery UI; clients fetch the assets from URLs, never base64. Spends credits and writes to the user's Picsart Drive when the Drive option is enabled. Requires Authorization: Bearer <picsart_token>.

  Connector

• list_brand_assets

  Heista

  List images for a brand. Filter by PowerSource (this scan only, via powersource_id), by on-pack product_name (the vision tagger's read), by type (logo, product, product_cutout, hero, lifestyle, ingredient, packaging, certification, before_after, infographic, screenshot, video, general), or by is_primary_product. Use this BEFORE generating any image-based output so you pick from the brand's real assets, not generic stock. Returns asset_id, signed url, type, detected_product_name, is_primary_product, sources. Free, read-only. Paginated via cursor.

  Connector

• stophy_get_channel

  Stophy

  Browse a YouTube channel's content. Returns channel{id, name, handle, subscriberCount, videoCount, isVerified, thumbnails} on every tab. tab options: video, short, live (past live streams), playlist, post (community posts), about. Video and live tabs return items[{id, videoUrl, title, author, publishedAt, thumbnails}]; the short tab returns items with shortUrl instead of videoUrl (no publishedAt); the playlist tab returns items[{id, playlistUrl, title, videoCount, thumbnails}]. All of these paginate with continuationToken. The post tab returns items[{id, url, content, publishedTimeText, likeCountText, commentCountText, images, video}]. About tab returns the full profile including country, joinedDate, viewCount, and links[]. Set query to search within the channel (returns matching videos; tab is ignored). Best for: auditing a creator's catalog, pulling all videos from a channel, finding a channel's video on a topic, reading community posts or the channel description. Not recommended for: fetching a single known video. Use stophy_get_video instead.

  Connector

• clipform_search_media

  Clipform

  Search images or stock video clips. Pass one query or many (max 10) - multiple queries run in one call instead of separate tool calls. Use results to feed into clipform_generate_video for narrated slideshow videos, or upload directly as still images via clipform_upload_media_asset then clipform_attach_node_media. All results are pre-cleared for commercial use. Results include a description (alt text where the provider has it) - use it to pick visually distinct images. Example: { queries: [{ query: "saturn rings" }, { query: "mars surface", count: 3 }] } returns portrait images for both.

  Connector

• get_draft_status

  contracts

  Check a contract draft started with start_contract_draft. While generating returns status "pending". When complete, returns the free preview (opening sections), the titles of locked sections, and the URL where a human can pay to unlock the full contract.

  Connector

• create_content_campaign

  ProductClank

  Launch a content campaign: rally the ProductClank community to create content (posts, threads, videos) for a product. Spends 1000 credits. The platform's AI expands your brief into a full campaign and auto-activates it; community submissions and winner selection happen in the ProductClank web app. Requires a product_id from search_products. Preview with suggest_content_campaign and confirm the 1000-credit cost with the user before calling.

  Connector

• search_public_apis

  agentView

  Searches a curated catalog of 600+ free public APIs (no key, HTTPS) for embedding live data in display HTML via fetch(): weather, news, finance, sports, images, food and 40+ more categories. Use when generating HTML that needs live internet data. Set list_categories=true to get the category menu with counts instead of search results. Returns docs links, CORS status and fetch() hints. No authentication required.

  Connector

• get_video

  canton-ccpedia

  Get a Canton Network video that CCPEDIA has cached (curated channels: Canton Network, Digital Asset, Sync Insights, Canton Foundation, Daml) by its YouTube id: title, channel, publish date, description and full transcript text if stored. CANTON-ONLY and limited to videos already in CCPEDIA's index. Does NOT fetch arbitrary YouTube videos (use a dedicated YouTube tool for that). Obtain ids from list_videos or search.

  Connector

• brc_find_help_resources

  Red by Big Red Cloud

  Find Big Red Cloud customer help across Freshdesk support articles, customer documentation, recorded webinar videos, and upcoming live webinars. Use when the customer asks a support question or how-to question about Big Red Cloud. Do not use for connecting companies, listing connected companies, clearing connections, or any company books data. Read-only. Does not require a connected company. Return a concise synthesized answer for the customer: direct answer, clear steps where applicable, then a Sources section with Articles / Videos groupings and exact public links from customerFacingSourcesMarkdown or the sources array. Use only publicUrl or registrationUrl values returned in resources for hyperlinks. Freshdesk links use bigredcloud.freshdesk.com — never rewrite them onto bigredcloud.com/support. Keep screenshot Markdown links beside their related steps — never move them into Sources. Prefer customer documentation for procedural questions, Freshdesk for detailed step-by-step instructions, recorded webinars for video walkthroughs, and upcoming webinars for training/onboarding/live help requests. Do not show internal resource IDs, Azure blob names, storage URLs, relevance scores, or sync metadata to the customer. For Big Red Cloud how-to or tutorial questions, automatically open the best matching Freshdesk article from usedResourceIds with brc_get_help_resource_details using includeImages=true and imagePresentation=links. Place each relevant screenshot beside its step even when the user did not explicitly ask for images. Never claim no Freshdesk article exists when usedResourceIds includes a matching Freshdesk resource. Sources must list only usedResourceIds — never unrelated login, API-key, user, or webinar search hits. Under Sources, group Freshdesk / documentation under Articles and recorded webinars under Videos — omit an empty Videos heading. For procedural how-tos, automatically include the strongest topic-aligned training video under Videos when one exists — do not require the user to ask for a video. Always emit Sources before any Do this through Red section. When redActionAvailable is true, include customerFacingRedActionMarkdown after Sources and before support — do not start the action unless the user asks. Always end every help answer with Still need help? and [Contact Big Red Cloud Support](https://bigredcloud.com/contact/) — support must be last. Never claim company data was changed by a tutorial answer.

  Connector

• get_setup_snippet

  AfterLaunch

  The paste-able 'Growth (AfterLaunch)' markdown section for this repository's CLAUDE.md or AGENTS.md. It teaches any coding agent how to use AfterLaunch for growth, marketing, SEO, AI visibility (GEO), competitor and distribution work: which tools to call, which cost money, and what AfterLaunch never does. Free, read-only, no arguments. Write it into the repo rather than asking the founder to copy it. The same text is public at /agents/snippet.md.

  Connector

• image_related

  Openverse

  "Find images similar to [X]" / "more images like this" — related images for a given Openverse image ID. Use for visual-similarity exploration in CC content.

  Connector

• cite_image

  MemeStack

  Generate canonical attribution blocks for one or more MemeStack images. Returns markdown, HTML, and plain-text citation strings ready to paste into your output, plus a combined block for citing multiple images at once.

  Connector

• list_assets

  agentView

  Lists the user's uploaded assets (images, videos, fonts, documents) with public URLs for use in display HTML. Filter by type, search term or group. Check before upload_asset to avoid duplicates. response_format 'detailed' adds description, size and timestamps per asset. Requires content scope.

  Connector

• vest_search_tools

  vest-mcp

  Search and browse AI tools available in Vest's cashback catalog. Returns names, slugs, categories, and live cashback rates. Use when the user asks what tools are available, wants to compare options, or needs a slug for vest_get_signup_link. Real triggers: 'what AI writing tools does Vest have?', 'show me coding tools with high cashback', 'find tools under $50/mo'. Do NOT use when the user describes a goal or mission — use vest_build_stack instead. Do NOT use to get a signup link — use vest_get_signup_link.

  Connector

• tiktok_search_hashtag_list

  Social Fetch

  Search TikTok videos by hashtag (not free-text keyword — use tiktok.search.videos.list for that). Returns a list (use cursor when paginated).

  Connector

• compare_listings

  Agentic.ai Directory

  Compare exactly two AI tools side-by-side. Returns structured field matrix and 'Choose A if... Choose B if...' verdict. Use this when a user wants to decide between two specific tools. For finding tools first, use search_listings or semantic_search.

  Connector

• list_drive_folder

  Adbloop Meta Ads

  List the images/videos inside a PUBLIC Google Drive folder (must be shared as 'Anyone with the link'). Returns each file's name and a Drive URL usable directly as imageUrl in bulk_create_campaigns. Perfect for 'create one campaign per image in this folder'. Read-only.

  Connector