Pipedrive + AI in 60 seconds
Unofficial. Community-built Claude Code Skill and MCP server for the Pipedrive API. Not affiliated with, endorsed by, or sponsored by Pipedrive OÜ.
Awaiting live verification - passes every mechanical gate (build, command-surface, claims, install). Be the first to confirm it against your tenant: report it works.
Ask your AI “which deals are dying and who do I call today,” and get a ranked answer in seconds. The Pipedrive skill keeps a local copy of your pipeline so it can join deals, people, activities, and notes the portal shows on separate screens - surfacing stale deals by dollar at risk, a weighted forecast, stage bottlenecks, and rep leaderboards without exporting a single CSV.
New to the term? An MCP server is the same thing ChatGPT calls an app or connector, Claude on the web calls a connector, and Claude Code calls a Skill. One thing, many names →
Install in 60s → View on GitHub →
Instead of clicking through Pipedrive, just ask
Instead of Export the deals report to a spreadsheet every Monday and eyeball which ones have gone quiet.
just ask: “Which open deals has nobody touched in two weeks, worst dollar value first?”
Your agent runs: pipedrive-cli stale --quiet-days 14 --agent
Instead of Rebuild the weighted-pipeline math (deal value times stage probability) in a spreadsheet before every pipeline review.
just ask: “What’s my weighted forecast for this quarter by pipeline?”
Your agent runs: pipedrive-cli forecast --period this-quarter --agent
Instead of Click through five screens - person, org, deals, activities, notes - to prep for one call.
just ask: “Give me the full picture on Jane Smith before my call.”
Your agent runs: pipedrive-cli who "Jane Smith" --agent
See it in 30 seconds
Demo data is simulated. Every command shown exists in the real CLI.
What it does
| Question your MSP keeps asking | Command your agent runs |
|---|---|
| Which open deals has nobody touched in two weeks, worst dollar value first? | pipedrive-cli stale --quiet-days 14 --agent |
| What’s my weighted forecast for this quarter, and what’s expected to close? | pipedrive-cli forecast --period this-quarter --agent |
| Which deals are stuck in a stage longer than that stage usually takes? | pipedrive-cli aging --agent |
| Which open deals have no next activity scheduled? | pipedrive-cli next-activity --missing --agent |
| Rank my reps by won value over the last 90 days. | pipedrive-cli leaderboard --by won-value --window 90d --agent |
| What changed since yesterday, and who do I need to call today? | pipedrive-cli digest --for-me --agent |
| Which deals did we lose in the last six months, with reasons, for a re-engagement push? | pipedrive-cli lost --since 180d --agent |
| Find likely-duplicate organizations so I can clean up the CRM. | pipedrive-cli dupes --entity organizations --agent |
| Search every synced deal, person, and organization for a name. | pipedrive-cli search "Acme Corp" --agent |
| Pull my whole pipeline into a local copy for offline, zero-API-call analysis. | pipedrive-cli sync --agent |
Full command reference at github.com/servosity/msp-skills/blob/main/skills/pipedrive/guide.md.
What makes this one different
Most Pipedrive integrations proxy each question straight into a live API call - one deal, one page, one entity at a time, rate-limited and shaped for single lookups. This skill keeps a local SQLite mirror of your pipeline (run sync once), so the high-value questions - stale deals ranked by dollar at risk, a weighted forecast, stage aging, a rep leaderboard, duplicate detection - are computed by joining deals, people, activities, and stages locally. That is analysis a thin wrapper cannot do without paging the entire API on every ask.
Pipedrive’s Insights dashboards live in the portal and answer the questions Pipedrive pre-built. This skill answers the ones it did not - value at risk, next-activity gaps, lost-deal re-enrollment lists, a one-card contact view - in your terminal or AI agent, joined across entities, complementing the portal rather than replacing it.
The pain this closes
- Reporting is Pipedrive’s single most-cited complaint across G2, Capterra, and Trustpilot. Insights covers the basics, but anything cross-entity - value at risk by organization, a weighted forecast by pipeline, rep contribution over a window - means exporting to a spreadsheet and rebuilding the math by hand.
- Deals die quietly. CRM contact data decays roughly 30% a year, and a deal nobody has logged an activity against just sits in the pipeline. By the time it surfaces in a review it is already cold.
- “Great for managing deals, not for managing customers.” Prepping for one call means opening the person, their organization, their open deals, the last and next activity, and recent notes on separate screens and stitching them together yourself.
Install
Works in any of these agents - pick yours:
| Agent | Quick install |
|---|---|
| Claude Desktop | Step-by-step → |
| ChatGPT (Plus/Pro+) | Step-by-step → |
| Claude Code | Step-by-step → |
| Codex CLI | Step-by-step → |
| Cursor, Windsurf, Cline, Continue, Zed, Copilot, Gemini, Hermes, OpenClaw | Which agent? → |
Quickest path for everyone else (terminal):
macOS / Linux:
bash <(curl -fsSL https://raw.githubusercontent.com/servosity/msp-skills/main/skills/pipedrive/install.sh)
Windows (PowerShell):
iwr -useb https://raw.githubusercontent.com/servosity/msp-skills/main/skills/pipedrive/install.ps1 | iex
After install, authenticate once with your Pipedrive credentials, then verify with pipedrive-cli --version.
Safety model
| Tier | Examples | Recommended agent policy |
|---|---|---|
| Read | every get/list command, the local-join analytics (stale, forecast, aging, digest, leaderboard, next-activity, lost, who, changes, dupes), search, export, and sync (which writes only the local SQLite mirror, never Pipedrive) |
Allow |
| Write (routine) | deals add, deals update, persons add, organizations update, notes add, activities add, leads add, and the bulk import - 73 routine-write commands in all |
Preview with –dry-run, then a reviewed write |
| Destructive / config | deals delete, persons delete, organizations delete and the other 40 delete commands, plus the credential commands (auth set-token, oauth get-tokens, oauth refresh-tokens) |
Human-in-the-loop only |
The skill can read your whole pipeline and can create, update, and delete CRM records, so treat it like any account with write access. Reads - the reports, the analytics rollups, and search - are always safe. Routine writes such as deals add, deals update, and the bulk import should be previewed with --dry-run and approved before they run. Deletes and token commands are human-in-the-loop only. The recommended agent policy is read plus previewed writes, with a human approving anything that mutates or removes data. Full details in governance.md.
Frequently asked questions
Does this work with ChatGPT?
Yes, on paid ChatGPT plans. ChatGPT connects to remote MCP servers over HTTPS, so you expose the local Pipedrive MCP server via a secure bridge. Step-by-step in the install guide.
Do I need to know how to code?
No. Paste one sentence into Claude Code or Codex and your agent does the install, or run a one-line installer. You enter your credentials once.
Is my Pipedrive data safe?
Your data stays on your machine. The CLI, MCP server, and the local mirror are all local. The AI sees query results, not raw bulk data, and credentials are never bundled or transmitted by MSP Skills.
What does it cost?
Free. Apache-2.0 licensed. You pay only for whichever AI agent you already use.
Does this need a higher Pipedrive plan or the paid Insights tier?
No. Any Pipedrive plan that issues an API token works - find it under Settings > Personal preferences > API. The skill talks to the standard Pipedrive API, and the cross-entity analytics (stale, forecast, aging, leaderboard) run locally on your synced data, so they are not gated behind a reporting add-on.
Will this burn through my Pipedrive API rate limits?
Day-to-day questions answer from the local mirror after a sync, so they make zero API calls. sync itself paginates politely - tune --rate-limit and --concurrency, and use --since 24h to refresh only what changed - and live calls only happen when local data is missing or stale.
Status
Beta. Validated against the Pipedrive API surface and being validated with MSPs running it live against their own production tenants in our weekly Build Sessions.
Standards. Conforms to the open Agent Skills spec (Anthropic, Dec 2025; 40+ agents). MCP-compatible - works with any MCP-capable agent including Hermes. OpenClaw-ready (frontmatter pre-wired, awaiting OpenClaw launch).
Maintained by Servosity for the MSP community. Apache-2.0 licensed. Built with CLI Printing Press.