Model Context Protocol
Your agent gets a user researcher.
telepace is a first-class MCP server. Five stateful tools your agent can call the same way a human PM would open a research tab.
Tools
Every tool returns a next_actions field. That is what makes tool-using agents effective.
create_campaignMCP toolDraft a study from a goal + background. Returns a persistent campaign_id.
Input
{ title, goal, background?, target_completions?, channels? }Output
{ campaign_id, outline, share_url, next_actions }get_campaign_progressMCP toolRead the projection: completions so far, coverage per question, spend to date.
Input
{ campaign_id }Output
{ status, completions, coverage, spend_usd, next_actions }get_campaign_insightsMCP toolReturn the current cluster of themes with representative verbatims.
Input
{ campaign_id, min_confidence? }Output
{ themes[], verbatims[], next_actions }ask_followupMCP toolMine the transcript corpus with a natural-language question. Non-destructive.
Input
{ campaign_id, question }Output
{ answer, supporting_quotes, next_actions }push_insightsMCP toolExport to Notion, Linear, Slack, or a webhook. Idempotent per destination.
Input
{ campaign_id, destination, config }Output
{ status, external_ref, next_actions }Try it in 60 seconds
Wire telepace into Claude Code.
One command, no config. Your Claude gains an entire research team.
# 1. Add the MCP server
$ claude mcp add telepace https://mcp.telepace.io
# 2. Ask Claude to do research
claude> Run a study on why users churn from our pro tier.
· Calling telepace.create_campaign …
↳ campaign_id: 4f2b…9c1
↳ share_url: https://telepace.io/r/4f2b9c1
· Calling telepace.get_campaign_progress …
↳ 32 / 50 completions · coverage 78%
· Calling telepace.get_campaign_insights …
↳ 3 themes surfaced (confidence ≥ 0.7)
Ready to push? Reply "push to Notion" and I'll finalize.