# agent campaign planning bridge — PipelineCPC

MCP and agent API bridge that lets AI agents use PipelineCPC for Google Ads planning without launching ads.

Type: project entry

Published: 2026-05-16

[Original page](<https://artlu.ai/project/agent-campaign-planning-bridge-pipelinecpc>)

[Browse this group](<https://artlu.ai/ai/groups/pipelinecpc.md>)

Parent project: PipelineCPC

Recorded status: launched

Updated: 2026-09-16T16:22:33.961Z

Technologies: Node.js, MCP, Firestore, Firebase Auth, Google Ads, Railway, Codex

## Details

PipelineCPC now has a separate MCP bridge and agent-facing API for campaign planning. Agents can read saved keyword lists, group keywords into draft ad groups, suggest negative keywords, and export draft Google Ads campaign structures. Fresh keyword fetches stay gated behind explicit API-key permissions and credit caps, while saved-data planning stays read-only.

The bridge was split into its own repo so Claude, Codex, Hermes, and future agent clients can connect without living inside the main SaaS codebase. The planning flow also now infers likely campaign intent and separates keywords into included, needs-review, and excluded buckets before creating ad groups, so noisy saved lists do not turn into bad campaign recommendations.

## Links

[Site or demo](<https://pipelinecpc.com/>)

## Related build notes

[pipelinecpc got an agent planning bridge](<https://artlu.ai/ai/log/day-60-pipelinecpc-got-an-agent-planning-bridge.md>)


Status and dates describe the published record, not a recent test of an external service. Missing details are not inferred. Public links do not imply an open-source licence or permission to reuse material.

[Directory](<https://artlu.ai/llms.txt>)
