{
  "markdown": "# 🥒 Pickle: the free AI ops manager for ClickUp, Slack & Teams\n\n![Pickle: catch what slips through ClickUp, Slack and Teams. The AI ops manager that catches what your team dropped](docs/pickle-cover.png)\n\n> **ClickUp Brain reads your tasks. Slack AI reads your messages. Both are paid add-ons, and each only sees its own app.**\n> **Pickle is a free AI ops manager that runs on your own machine, reads across all three, and tells you what slipped through: stale tasks, dropped promises, decisions buried in a DM.**\n\n[![License: MIT](https://img.shields.io/badge/license-MIT-blue.svg?style=flat-square)](LICENSE)\n[![MCP compatible](https://img.shields.io/badge/MCP-compatible-7c3aed?style=flat-square)](https://modelcontextprotocol.io)\n[![No account · no telemetry](https://img.shields.io/badge/no%20account-no%20telemetry-22c55e?style=flat-square)](#privacy)\n[![Works with](https://img.shields.io/badge/works%20with-Claude·Cursor·Codex·Cline·Zed-f97316?style=flat-square)](#works-with)\n[![Star this repo](https://img.shields.io/github/stars/adityaarsharma/pickle?style=flat-square&color=eab308)](https://github.com/adityaarsharma/pickle/stargazers)\n\nPickle is a free, open-source **AI ops manager** for your team, packaged as an MCP server you run yourself. Give it **your own** ClickUp / Slack / Teams token, and your AI client (Claude, Cursor, Codex, Cline, Zed…) audits your workspace the way a sharp ops manager would: catching the work that quietly fell through.\n\n**No account. No hosted server. No key from us. No telemetry.** Pickle adds no middleman. It talks only to *your* tools, with *your* token. Nothing is sent to us, because there's no \"us\" to send it to.\n\n> ⭐ **Pickle is free and will stay free. There is no paid tier.** If you think workspace tools should run on your own machine, **star the repo.** Stars are the only way it gets found.\n\n---\n\n## <a id=\"privacy\"></a>Why this is different\n\n| | ClickUp Brain | Slack AI | **Pickle** |\n|---|---|---|---|\n| Sees **across** your tools | ❌ ClickUp only | ❌ Slack only | ✅ ClickUp + Slack + Teams |\n| Where your data flows | Their cloud | Their cloud | **Only to your own tools, with your token** |\n| A third party holds your token | Yes | Yes | **No, it stays in your local config** |\n| Cost | Paid add-on | ~$10/user/mo | **Free · MIT · open source** |\n| You can read every line | ❌ | ❌ | ✅ it's all right here |\n\nHonest version of the privacy claim: Pickle *does* read your ClickUp/Slack/Teams. That's the job. But it reads them **directly, from your machine, with your token**, and sends nothing to any Pickle server. Verify it yourself. The code is in [`server-remote/server.mjs`](server-remote/server.mjs), and there is no analytics, no beacon, no phone-home.\n\n---\n\n## <a id=\"install\"></a>Install: one command\n\nGuided: it asks which tools you use, points you to where each token lives, and writes your MCP config for you.\n\n```bash\ncurl -fsSL https://pickle.adityaarsharma.com/install.sh | bash\n```\n\n**Or add it to your MCP client yourself** (via [npm](https://www.npmjs.com/package/pickle-mcp)):\n\n```json\n{\n  \"mcpServers\": {\n    \"pickle\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"pickle-mcp\"],\n      \"env\": { \"CLICKUP_API_KEY\": \"pk_your_own_token\" }\n    }\n  }\n}\n```\n\nAdd `SLACK_TOKEN` (`xoxp-…`) and/or `TEAMS_TOKEN` to the same `env` block to switch on the cross-tool patterns. Restart your client. `npx` runs it locally on your machine, no global install, no clone.\n\nThe installer asks which tools you use (ClickUp / Slack / Teams), takes the token *you already have* for each, and writes the MCP config for your client automatically. No hand-editing, no key from us.\n\n> Prefer to do it by hand? See [`docs/manual-install.md`](docs/manual-install.md). The only token you ever provide is your own platform token (e.g. ClickUp `pk_…` from Settings → Apps).\n\nThen just ask your AI:\n\n> *\"Pickle, run my morning audit: scan my ClickUp from the last 7 days and show me the 3 worst things I missed, worst first.\"*\n\n---\n\n## What it catches\n\n- **Stale in-progress**: \"doing\" for days, zero activity\n- **Dropped promises**: \"I'll do X by Friday\" with no follow-through\n- **Decisions buried in DMs**: a call made in a thread that never became a task\n- **Delegations nobody chased**: you asked, it never landed, everyone forgot\n- **Standup copy-paste**, zombie tasks, empty-description work, blocker rot… full list in [`docs/patterns.md`](docs/patterns.md)\n\n---\n\n## <a id=\"works-with\"></a>Works with\n\nClaude Code · Claude Desktop · Cursor · Codex · Cline · Continue · Zed · any MCP host. The reasoning runs in **your** model. Pickle just fetches and structures the data. Optional [Claude Code skills](docs/skills.md) add `/pickle-*` slash commands as a convenience layer.\n\n---\n\n## Free, and what I ask instead of money\n\nPickle has no paid tier and never will. Instead:\n\n- ⭐ **Star the repo** if it caught even one thing worth fixing. A free tool has no ad budget, so a star is genuinely how the next person finds it.\n- 📮 **[Get update notes + workspace-AI tips](https://adityaarsharma.com)**: occasional, practical notes on using AI in real team workflows (the same patterns Pickle runs). Reply anytime with a suggestion or a pattern you want added. I read every one.\n\n### 🧭 Want your team to actually *use* AI well?\n\nPickle is what I use to keep my own team honest. If you're rolling AI into how your company works (onboarding people onto it, wiring it into real workflows, choosing which LLM for what), **[reach out to me](https://adityaarsharma.com/?src=pickle-readme)**. I help teams go from \"we bought AI licenses\" to \"AI is actually in our workflow,\" with real use-cases instead of hype.\n\nBuilt in the open by **[Aditya Sharma](https://adityaarsharma.com)**, a marketer who codes.\n\n## FAQ\n\n**Is Pickle really free?**\nYes. MIT-licensed, no paid tier, no account, no credit card. I built it in the open; a ⭐ is the only thing I ask.\n\n**Do I need a Pickle account or an API key from you?**\nNo. Pickle issues nothing. The only token you provide is your *own* ClickUp / Slack / Teams token, and it lives in your local MCP config.\n\n**Does my data get sent to you or to any cloud?**\nNo middleman. Pickle runs on your machine and talks only to *your* tools (ClickUp / Slack / Microsoft Graph) using *your* token. There is no Pickle server, no telemetry, no phone-home. Pickle does read your ClickUp/Slack/Teams (that's the job), but it sends nothing to us. Verify it in [`server-remote/server.mjs`](server-remote/server.mjs).\n\n**Which AI clients does it work with?**\nAny MCP-compatible host: Claude Code, Claude Desktop, Cursor, Codex, Cline, Continue, Zed, and more. The reasoning runs in *your* model.\n\n**What should I ask Pickle first?**\nAfter installing, restart your AI client and paste: *\"Pickle, run my morning audit: scan my ClickUp from the last 7 days and show me the 3 worst things I missed, worst first.\"* You get a ranked, punchy result instead of a data dump, so you feel the value on the first run.\n\n**How is this different from ClickUp Brain or Slack AI?**\nThose are cloud add-ons that each see only their own tool and send your data to their servers. Pickle runs locally, reads *across* ClickUp + Slack + Teams, and keeps your token on your machine. Different axis: privacy + cross-tool, not \"more features.\"\n\n**Is it safe to give it my token?**\nThe token stays in your local config file (`chmod 600`), and the code is open. Read it before you connect. Nothing is transmitted anywhere except the platform's own API.\n\n**Will Pickle change or delete anything in my tools?**\nThe audit itself is read-only — it only reads and reports. Pickle *can* create a reminder, drop a comment, or make a task if you explicitly ask it to (for example \"remind me about XYZ-184\"), because the server also exposes write tools for that. If you want a hard, code-level guarantee that nothing can be written or deleted no matter what a model asks, set `PICKLE_READONLY=1` in the `env` block — it blocks every mutating tool at the server. Details in [`docs/security.md`](docs/security.md). You stay in control.\n\n**Do I need Slack and Teams too, or is ClickUp enough?**\nClickUp alone is a great start. Slack/Teams unlock the cross-tool patterns (decisions-in-DMs, ghost mode) because those need chat data.\n\n**Can it audit GitHub or other tools?**\nNot yet. A GitHub audit (stale PRs, dropped reviews) is a planned/welcome contribution.\n\n**Is there a hosted version?**\nNo. Pickle is local by design. If you want your team to adopt AI tools like this well, [reach out](https://adityaarsharma.com). That's the consulting I do.\n\n## Contributing\n\nIssues and PRs welcome: new patterns, new connectors (a GitHub audit for stale PRs is a great first one), better client configs.\n\n## License\n\nMIT © [Aditya Sharma](https://adityaarsharma.com)\n",
  "bytes": 8791,
  "sha": "401b05b5f5c8c17b16d558d9675520808fdb7d490bc7603ce0224b15f75e6eb1",
  "repo_slug": "adityaarsharma/pickle",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_adityaarsharma_pickle_96ca542c/readme"
}