Sendspark for AI agents
Sendspark is a video messaging platform for recording and sending personalized videos to prospects and customers over email or social channels. Sales and support teams use it to add a human touch. 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 Sendspark.
Add a prospect to a video campaign
Enroll a single prospect or a batch of leads into a dynamic personalized video campaign.
Look up a prospect's video activity
Get a workspace prospect's data by email to check whether they've watched a sent video.
Launch a new video campaign
Create a dynamic video campaign for a sales sequence before adding prospects to it.
9 Sendspark actions, graded by risk.
Every Sendspark action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
4Look things up. Allowed by default.
- sendspark.list_webhooksList Webhooks
- sendspark.get_dynamic_campaign_by_idGet Dynamic Campaign by ID
- sendspark.list_dynamic_video_campaignsList Dynamic Video Campaigns
- sendspark.get_workspace_prospect_data_by_emailGet Workspace Prospect Data by Email
write
4Create and change things. Allow, or ask the user first.
- sendspark.create_dynamic_video_campaign2Create Dynamic Video Campaign V2
- sendspark.add_prospect_to_dynamic_video_campaignAdd Prospect to Dynamic Video Campaign
- sendspark.add_multiple_prospects_to_dynamic_campaignAdd Multiple Prospects to Dynamic Campaign
- sendspark.api_health_statusAPI Health Status
destructive
1Delete, cancel or archive. Ask first, or deny outright.
- sendspark.delete_webhookDelete Webhook
Sendspark in three steps.
- 01Your users connect SendsparkThey add their Sendspark api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, writes like “create Dynamic Video Campaign V2” can wait for the user, and “delete Webhook” can be denied outright.
- 03Any agent can actYour agent calls Sendspark through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('sendspark', { read: 'allow', write: 'ask', // create_dynamic_video_campaign2 destructive: 'deny', // delete_webhook }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Sendspark connects.
Users add their Sendspark 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 Sendspark 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 Sendspark from any agent.
Sendspark and Arc0, answered.
Can I use Sendspark with Claude, ChatGPT or Cursor?
Yes. Connect Sendspark 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 Sendspark actions you allow.
How do users connect Sendspark?
Users add their Sendspark 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 Sendspark actions can my agent take?
9 in total: 4 read, 4 write and 1 destructive, such as “create Dynamic Video Campaign V2”. Your policies decide which of them each agent may call.
Can I stop my agent from deleting things in Sendspark?
Yes. Actions like “delete Webhook” are graded destructive. Set destructive actions to deny, or to ask so the user approves each one, and blocked calls still show up on the audit log.
Can my own backend call Sendspark too?
Yes. The same Sendspark connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Sendspark into your agent.
Your users connect Sendspark once, under your brand. Your agent gets 9 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan