MCP serverxyz.outsend/outsend

Enrich the results of a finished job (async): find emails, scrape reviews, detect social networks, verify emails, tech stack, etc. Returns the new job id.

Create AND start a multi-step pipeline (e.g. scrap → emails → verify_emails). Keep chains LINEAR (each block feeds the next). Edges use the keys "from" and "to" — NOT source/target

Launch a Google Maps extraction (async). Returns the job id immediately; poll get_job until status=done, then use get_job_results. When the user wants ~N results, set stop_at.

Turn a finished job or pipeline into recurring monitoring: outsend re-runs it every N days and computes the diff (new / removed / modified places).

Estimate the cost (EF) and volume of a Google Maps extraction WITHOUT launching it. Always estimate before creating a large job. 1 EF = a full-France scrape for one query type.

Account event feed (job.completed, pipeline.completed, veille.run_completed…). Cursor-based: pass back last_id as since_id.

Status, counters and download URL of a job.

Preview of a finished job's rows (max 50 per call, paginate with offset) + total count + CSV download URL. Never dump thousands of rows into the conversation: show a sample, give t

Machine contract for building pipelines: valid block types, per-block config schema, and chaining rules. Use before create_pipeline.

The account's recent jobs, newest first.

Catalog of outsend data modules: what each one needs and produces. Call this first to know what is possible. Modules listed as coming_soon cannot be launched.

The account's pipelines with status.

The account's recurring monitors.