24 posts tagged with "Provider Spotlights"

Grafana is where engineering teams go to understand what's happening in their infrastructure. Dashboards, alerts, logs, metrics — it's all there. But when something goes wrong at 3am, the workflow is still manual: open Grafana, find the right dashboard, scan the panels, correlate timestamps, dig into logs.

MCP changes that. With a Grafana MCP server, your AI agent can search dashboards, pull panel data, read alert states, create annotations, and explore datasources — answering "what happened?" conversationally instead of through dashboard clicking.

Snowflake doesn't have an official MCP server. For a platform where most users interact through SQL, that's a meaningful gap — every question an analyst has starts with "what tables do we have?" and ends with a query, and that's exactly the workflow MCP is built for.

MCPBundles provides a purpose-built Snowflake toolset that connects your AI agent directly to your Snowflake account through the SQL REST API. Your AI can explore databases, navigate schemas, inspect table structures, execute arbitrary SQL, manage warehouses, and review query history — all authenticated with a Programmatic Access Token.

Supabase ships an official MCP server that gives your AI access to the full Supabase platform — Postgres databases, authentication, storage, edge functions, and project management. It's one of the more complete official MCP implementations, covering both development workflows and production operations.

This guide covers what the Supabase MCP server offers, how to set it up, and how to access it through MCPBundles alongside your other tools.

Linear has one of the best official MCP servers in the ecosystem. Built in partnership with Cloudflare and Anthropic, it runs as a remote hosted server at mcp.linear.app/mcp with OAuth 2.1 authentication and 25+ tools for managing your entire project workflow.

This guide covers what the Linear MCP server can do, how to set it up across different AI clients, and how to access it through MCPBundles for a hosted experience alongside your other tools.

There's no official PostgreSQL MCP server from the PostgreSQL Foundation — and there probably won't be, since PostgreSQL is an open-source project without a commercial entity pushing integrations. The community implementations that exist mostly stop at "run a query, get rows" — fine as a starting point, light on everything that actually shows up in real database work.

MCPBundles provides 20+ purpose-built tools that go far beyond raw SQL. Your AI explores schemas, profiles columns, analyzes index health, detects data quality issues, finds duplicates, explains query plans, and exports data — all without you writing a single SQL statement. And if you do want raw SQL, that's there too.

Most Discord server management is repetitive moderation and community work. Read every message in #support to find unanswered questions, then draft and post threaded replies. Scan #general for the day's key discussions and post a summary to #daily-digest. Create separate discussion threads for each agenda item in a pinned meeting note. React with checkmarks to every completed task message. Pin important announcements so they're easy to find.

Each of those is a 15-minute task in the Discord UI and a 30-second task as a chat message — if your AI agent can actually call the Discord API. This guide is the use-case version of "AI + Discord": what you ask, what the agent does, what comes back. The protocol underneath is MCP (Model Context Protocol), the bundle is /skills/discord on MCPBundles, but the framing here is workflow-first.

Every other LinkedIn MCP server on GitHub is either a scraper that violates LinkedIn's Terms of Service or a thin wrapper around unofficial endpoints that can break at any time. Some use Patchright (a Playwright fork) to automate the browser. Others reverse-engineer private APIs. LinkedIn actively blocks these — and your account is at risk if you use them.

MCPBundles ships two LinkedIn MCP servers that work the way LinkedIn allows you to work:

• LinkedIn — built on LinkedIn's official REST API with OAuth 2.0. Manages company pages, publishes posts with images and carousels, engages with comments and reactions, runs ad campaigns, and tracks analytics.
• LinkedIn Sales Navigator — drives Sales Navigator search, profile lookups, InMail, and inbox as your connected LinkedIn account. Sign in once on a hosted page (no cookies, no extensions, no scraping); the bundle then runs SN-grade prospecting and outreach with built-in per-account rate caps so a careless agent can't get the seat banned.

You can connect either or both. The pages are the canonical product surfaces — keep this article open if you want the comparison; jump to the skill page when you're ready to use one.

Most small-business accounting is repetitive operational work. Create an invoice for last week's hours, send it to the customer, and record the payment when it hits the bank. Pull a P&L for the quarter, export an aged-receivables report, check which customers are 30+ days overdue. Batch-update item prices, void an invoice that was sent to the wrong contact, reconcile what changed this week across customers, invoices, bills, and payments.

Each of those is a 5–10 minute task in the QuickBooks UI and a 20-second task as a chat message — if your AI agent can actually call the QuickBooks API. This guide is the use-case version of "AI + QuickBooks": what you ask, what the agent does, what comes back. The protocol underneath is MCP (Model Context Protocol), the bundle is /skills/quickbooks on MCPBundles, but the framing here is workflow-first.

Most Obsidian MCP servers give you six tools: read a file, write a file, search, list, patch, delete. Basic CRUD over Markdown. That's table stakes.

This one does things the others can't. Your AI sees images in your vault — diagrams, whiteboard photos, screenshots — through actual vision, not file paths. It traverses your wikilink graph and finds orphaned notes nothing links to. It edits a specific section of a document by heading or block reference without overwriting the rest. It lists every open task across your entire vault. It runs Obsidian commands directly from the command palette.

It works with Claude Desktop, ChatGPT, Cursor, Windsurf, or any MCP client. No npm install, no local server, no JSON config. One remote URL and your AI has the tools.