ReferenceWhat you can callLeadsrunleads.enrich

leads.enrich

leads.enrich is dispatched on 2 endpoints. Which one runs depends on the URL you post to, not on the name.

run leads.enrich

Enrich one lead from a natural-language instruction.

EndpointPOST /mcp/run
Scopepipeline
Sandbox keyrefused
Extra entitlementnone
MCP toolsnone, HTTP only
Convex functionleads/enrichBatch:enrichLead

A free sandbox key is refused: it resolves real people’s contact details through a paid provider, which costs money per call.

Arguments

ArgumentTypeRequiredNotes
leadIdstringrequired
rolesstring[]optional
languagestringoptional

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.

ArgumentFilled in from
orgIdyour organisation, resolved from the API key

Example request

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

curl -X POST https://api.selda.ai/mcp/run \
  -H "Authorization: Bearer sk_live_..." \
  -H "Content-Type: application/json" \
  -d '{ "fn": "leads.enrich", "args": { "leadId": "<leadId>" } }'
{
  "fn": "leads.enrich",
  "args": {
    "leadId": "<leadId>"
  }
}

Example response

Every endpoint answers in the same envelope.

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

The shape of value is not documented here. leads/enrichBatch:enrichLead 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.

run leads.enrich

Enrich a workspace’s leads from a natural-language instruction (legacy path).

EndpointPOST /mcp/run
Scopepipeline
Sandbox keyrefused
Extra entitlementnone
MCP toolsnone, HTTP only
Convex functionleads/enrichBatch:enrichBatch

A free sandbox key is refused: it resolves real people’s contact details through a paid provider, which costs money per call.

🚫
Not reachable. Another registry table (INTERNAL_ACTIONS) declares leads.enrich on /mcp/run too, and the dispatcher checks that one first. This entry can never be the one that runs. It is documented because it exists in the registry, not because you can call it.

Arguments

ArgumentTypeRequiredNotes
projectIdid<"projects">required
instructionstringrequired
concurrencynumberoptional

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.

ArgumentFilled in from
orgIdyour organisation, resolved from the API key

Example request

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

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

Example response

Every endpoint answers in the same envelope.

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

The shape of value is not documented here. leads/enrichBatch:enrichBatch 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.