linkedin.conversations

LinkedIn conversations: last message, whose turn it is, how long it has been silent, language and stage. Filter by turn, paged, at most 50 per page. Read only.

A free sandbox key may call it.

Arguments

What Selda fills in

You never send these. The HTTP layer overwrites them from the API key, which is what keeps one organisation’s data out of another’s reach.

Example request

Required arguments only. Values in angle brackets are yours to fill in; the optional ones are in the table above.

curl "https://api.selda.ai/v1/linkedin/conversations?projectId=<projectId>" \
  -H "Authorization: Bearer sk_live_..."

The same call in the RPC form

One dispatcher answers both, so this is the same request at a different URL. Use it when you are already posting to /mcp/*, or for a function that has no path of its own.

curl -X POST https://api.selda.ai/mcp/query \
  -H "Authorization: Bearer sk_live_..." \
  -H "Content-Type: application/json" \
  -d '{ "fn": "linkedin.conversations", "args": { "projectId": "<projectId>" } }'

{
  "fn": "linkedin.conversations",
  "args": {
    "projectId": "<projectId>"
  }
}

Example response

Every endpoint answers in the same envelope, whichever URL you called.

{
  "value": <the function's return value>,
  "request_id": "req_..."
}

The shape of value is not documented here. linkedin/mcpReads:conversations declares no returns validator, so there is nothing to derive it from, and a shape written out by hand here is a shape that goes stale without anything noticing. Call it once against a test key and read what comes back.

On failure the body is { "error": { "type", "code", "message", "request_id" }, "request_id" } and request_id is echoed in the X-Request-Id header.

Generated from convex/lib/mcpRegistry.ts. Nothing in this reference sends: launchRun is in no registry and never will be, so a script can prepare a campaign completely and a person still presses send in the app.