Giphy for AI agents
Giphy is a search engine and library of GIFs and stickers used to add animated reactions to chats, apps, and social posts. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.
What agents do in Giphy.
Search for a reaction GIF
Search GIPHY for a GIF matching a mood or keyword to drop into a chat message or post.
Pull today's trending GIFs
Fetch the current trending GIFs list to suggest options for a social post.
Fetch a specific GIF by ID
Retrieve a known GIF's details by its ID to reuse it consistently across a campaign.
23 Giphy actions, graded by risk.
Every Giphy action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
8Look things up. Allowed by default.
- giphy.search_gifsGIPHY: Search GIFs
- giphy.get_random_idGiphy Get Random ID
- giphy.search_channelsGIPHY: Search Channels
- giphy.search_stickersGIPHY: Search Stickers
- giphy.get_content_by_idGet Content by ID
- giphy.get_content_by_idsGet Content by IDs
- giphy.translate_gifGIPHY Translate GIF
- giphy.translate_stickerGIPHY Translate Sticker
write
15Create and change things. Allow, or ask the user first.
- giphy.emojiGIPHY Emoji
- giphy.categoriesGIPHY Categories
- giphy.random_gifGiphy Random GIF
- giphy.tag_randomGIPHY: Random Tag
- giphy.tag_searchGIPHY: Tag Search
- giphy.upload_gifGiphy Upload GIF
- giphy.tag_relatedGet Related Tags
- giphy.tag_trendingGIPHY Trending Tags
- giphy.category_gifsGIPHY: Category GIFs
- giphy.trending_gifsGIPHY Trending GIFs
- giphy.category_by_idGIPHY: Get Category by ID
- giphy.random_stickerGiphy Random Sticker
- giphy.action_registerGiphy Analytics Register
- giphy.emoji_variationsEmoji Variations
- giphy.trending_stickersGet Trending Stickers
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Giphy in three steps.
- 01Your users connect GiphyThey add their Giphy api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “gIPHY Emoji” can wait for the user to approve.
- 03Any agent can actYour agent calls Giphy through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('giphy', { read: 'allow', write: 'ask', // emoji destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Giphy connects.
Users add their Giphy api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
The same Giphy connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →
- AUTH
- API key
- CREDENTIALS
- Per-tenant encrypted vault
- MODEL SEES
- Results only, never credentials
- AUDIT LOG
- Every call, on every plan
Use Giphy from any agent.
Giphy and Arc0, answered.
Can I use Giphy with Claude, ChatGPT or Cursor?
Yes. Connect Giphy to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the Giphy actions you allow.
How do users connect Giphy?
Users add their Giphy api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
Which Giphy actions can my agent take?
23 in total: 8 read, 15 write and 0 destructive, such as “gIPHY Emoji”. Your policies decide which of them each agent may call.
Can I make my agent read-only in Giphy?
Yes. Allow read actions and deny writes in the Giphy policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Giphy too?
Yes. The same Giphy connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Giphy into your agent.
Your users connect Giphy once, under your brand. Your agent gets 23 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan