Integration

Sendspark integration

Sendspark creates AI-personalized prospecting videos. Through its API an agent can find its workspace, list and create dynamic video campaigns, read and update a campaign's settings, add one prospect or a batch of prospects to a campaign so Sendspark generates a personalized video for each, read a prospect's video by email, fetch a video's transcript, and create, update or delete webhooks that report video events. Not exposed: video-minute bundle purchases and cancellation, the internal step-by-step editor routes, and the webhook read routes (the vendor documents no response for them). Authentication sends two values on every call: the workspace API key in x-api-key and the user's API secret in x-api-secret, both from the API Credentials tab of the Sendspark settings.

Connect Sendspark How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Sendspark.Built from the 17 Sendspark tools below, on the connection you add once.

What you can do with Sendspark

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Bulk, 3 operations

add_prospects_bulkAdd prospects bulkPOSTAdds up to 10,000 prospects to a campaign in one call; a video is generated for each (billed above the plan limit). processAndAuthorizeCharge must be true. Limited to 1 call per minute.
generate_campaign_videosGenerate campaign videosPOSTStarts generating the personalized videos for the prospects already in a campaign. Billed: videos above the plan limit are charged. Returns the vendor's answer whole.
update_prospect_backgroundsUpdate prospect backgroundsPATCHSets (true) or removes (false) every prospect's background URL from their email domain, for a whole campaign. Returns how many prospects were updated.

Dynamic, 3 operations

create_dynamic_campaignCreate dynamic campaignPOSTCreates a dynamic video campaign and returns it with its _id. Record the campaign video in Sendspark, then add prospects with add_prospect or add_prospects_bulk.
get_dynamic_campaignGet dynamic campaignGETReturns one dynamic video campaign by id. The vendor documents no field list for this answer, so it is returned whole.
list_dynamic_campaignsList dynamic campaignsGETLists the dynamic video campaigns of the workspace, with paging (offset, limit), text search and sort order. Each campaign's _id is the dynamicId of the other campaign tools.

Webhook, 3 operations

create_webhookCreate webhookPOSTCreates a webhook: Sendspark POSTs the chosen video events to your URL. module dynamics limits it to dynamic campaigns (with identifiers), global covers the workspace.
delete_webhookDelete webhookDELETEDeletes a webhook: its URL stops receiving events.
update_webhookUpdate webhookPATCHChanges a webhook: name, URL, events, scope or enabled. Leave a field out to keep its current value.

Prospect, 2 operations

add_prospectAdd prospectPOSTAdds one prospect to a campaign; Sendspark generates a personalized video for them (billed above the plan limit). processAndAuthorizeCharge must be true. Poll get_prospect for its status.
get_prospectGet prospectGETReturns one prospect of a campaign by email: status (saved, billed, errored, processing, uploaded, completed), shareUrl of the personalized video, background and validation details.

Settings, 2 operations

list_dynamic_languagesList dynamic languagesGETLists the languages available for dynamic video campaigns (single-variable and multi-variable).
update_dynamic_campaign_settingsUpdate dynamic campaign settingsPATCHChanges a campaign setting: useFallbackData (use fallback values when a prospect field is missing). Returns the vendor's answer whole.

Identifier, 1 operation

get_workspace_idGet workspace idGETReturns the workspaceId of the workspace the API key belongs to. Call it first: every other tool needs this workspaceId.

Status, 1 operation

get_video_transcript_statusGet video transcript statusGETReports whether a campaign video has a transcript and whether it is ready to read with get_video_transcript.

Transcript, 1 operation

get_video_transcriptGet video transcriptGETReturns the transcript of a campaign video as JSON: full text, language and timed segments. Check get_video_transcript_status first.

Workspace, 1 operation

list_workspacesList workspacesGETLists the workspaces of the user the API secret belongs to.

Use Sendspark from Claude Code, Cursor or Codex

Connect Sendspark in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Sendspark operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect Sendspark

Create your workspace
Sign up free. Nothing to install.
Connect Sendspark once
Add your Sendspark connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.