# Mcp Starter Kit > Templates and install scripts to wire any MCP-compatible AI client (Claude Code, Cursor, Continue.dev, Cline, Windsurf, etc.) to Jenkins, Bitbucket, Atlassian, AWS (CloudWatch/Athena/SQS), MySQL, MS SQL Server. - **Type:** MCP server - **Install:** `agentstack add mcp-rathore97aditya-mcp-starter-kit` - **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior - **Seller:** [rathore97aditya](https://agentstack.voostack.com/s/rathore97aditya) - **Installs:** 0 - **Category:** [Databases](https://agentstack.voostack.com/c/databases) - **Latest version:** 0.1.0 - **License:** MIT - **Upstream author:** [rathore97aditya](https://github.com/rathore97aditya) - **Source:** https://github.com/rathore97aditya/mcp-starter-kit ## Install ```sh agentstack add mcp-rathore97aditya-mcp-starter-kit ``` Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent. ## About # MCP Starter Kit Templates and install scripts for wiring up **any MCP-compatible AI client** to a useful set of [Model Context Protocol](https://modelcontextprotocol.io) servers — so your assistant can talk to AWS, Jenkins, Bitbucket, Atlassian, and your databases directly instead of through copy-paste. ## Who this is for Engineers who want their AI coding assistant to actually *do* work against real systems — read pod logs, look up a Jira ticket, inspect a queue's backlog, check a DB schema — not just chat about code. Wiring each MCP server up by hand is fiddly: every server has its own auth, env vars, and gotchas, and config snippets you find online are usually pinned to one specific AI client. This kit ships an opinionated, **client-agnostic** bundle of the MCP servers most teams need, plus reference docs written *for* the AI to read so it knows when to reach for which tool. After setup (~15 min): ```text $ claude mcp list Checking MCP server health… aws-cloudwatch: uvx awslabs.cloudwatch-mcp-server@latest - ✓ Connected atlassian: npx -y mcp-remote https://mcp.atlassian.com/v1/mcp - ✓ Connected jenkins: uvx mcp-jenkins - ✓ Connected aws-sqs: uvx awslabs.amazon-sns-sqs-mcp-server@latest - ✓ Connected aws-athena: uvx awslabs.aws-dataprocessing-mcp-server@latest - ✓ Connected aws-rds: uvx awslabs.aws-api-mcp-server@latest - ✓ Connected bitbucket: uvx atlassian-bitbucket-mcp@latest - ✓ Connected mysql-db: mysql-mcp-server - ✓ Connected mssql-db: mcp-sqlserver - ✓ Connected ``` (Output shown for Claude Code; equivalent status views exist in Cursor, Continue.dev, Cline, etc. — see [SETUP.md § "Verify"](SETUP.md).) Works with: - [Claude Code](https://claude.com/claude-code) - [Cursor](https://cursor.com) - [Continue.dev](https://continue.dev) - [Cline](https://github.com/cline/cline) - [Windsurf](https://codeium.com/windsurf) - [Zed](https://zed.dev) (via its MCP support) - VS Code MCP extensions - Any custom app built with the [official MCP SDKs](https://modelcontextprotocol.io/sdk) The MCP server config block (`{"mcpServers": {...}}`) is a cross-client standard; the per-tool wrapping differs only in *where* you paste it (see [SETUP.md](SETUP.md) for the per-client mapping). ## What you get A **base layer** everyone needs, plus **independent database modules** so you only install what you use. ### Base layer | MCP server | What it does | Backed by | |---|---|---| | `jenkins` | List jobs, read build console output, trigger builds | [`mcp-jenkins`](https://pypi.org/project/mcp-jenkins/) | | `bitbucket` | Read PRs, branches, commits, diffs (Bitbucket Cloud) | [`atlassian-bitbucket-mcp`](https://pypi.org/project/atlassian-bitbucket-mcp/) | | `atlassian` | Jira issues + Confluence pages (OAuth, no token to manage) | [`mcp-remote`](https://www.npmjs.com/package/mcp-remote) → official Atlassian endpoint | | `aws-cloudwatch` | CloudWatch Logs Insights + metrics + alarms | [`awslabs.cloudwatch-mcp-server`](https://github.com/awslabs/mcp) | | `aws-athena` | Athena SQL + Glue Data Catalog (named here `aws-athena`, but covers Glue/EMR too) | [`awslabs.aws-dataprocessing-mcp-server`](https://github.com/awslabs/mcp) | | `aws-sqs` | SNS topics + SQS queues | [`awslabs.amazon-sns-sqs-mcp-server`](https://github.com/awslabs/mcp) | | `aws-rds` | Generic AWS CLI runner (named `aws-rds` for legacy reasons; runs any `aws ...` command) | [`awslabs.aws-api-mcp-server`](https://github.com/awslabs/mcp) | ### Database modules (optional, independent) | Module | Backed by | Use it for | |---|---|---| | `databases/mysql/` | npm [`mysql-mcp-server`](https://www.npmjs.com/package/mysql-mcp-server) | Reading MySQL tables / schemas | | `databases/mssql/` | npm [`@bilims/mcp-sqlserver`](https://www.npmjs.com/package/@bilims/mcp-sqlserver) | Reading SQL Server tables / schemas | Different npm packages, different env-var conventions — shipped as independent modules so you install zero, one, or both. ## Repo layout ``` mcp-starter-kit/ ├── README.md ← you are here ├── SETUP.md ← step-by-step base setup + per-client wiring ├── LICENSE ← MIT ├── install.sh ← installs base layer (uvx, AWS CLI, MCP packages) ├── AGENTS.md.template ← drop-in instructions for your AI assistant — │ copy to your tool's instruction-file location │ (CLAUDE.md, .cursorrules, AGENTS.md, etc.) ├── templates/ │ ├── aws-config.template ← AWS SSO config skeleton │ └── mcp-servers.json ← cross-client MCP config block (no DB) ├── databases/ │ ├── mysql/ → README.md + install.sh + mcp-block.json │ └── mssql/ → README.md + install.sh + mcp-block.json └── docs/ ← per-MCP reference, written FOR your AI to read ├── jenkins.md ├── bitbucket.md ├── atlassian.md ├── aws-cloudwatch.md ├── aws-athena.md ├── aws-sqs.md └── aws-rds.md ``` ## Why ship docs FOR the AI? When you invite an AI assistant into your workflow, the limiting factor isn't *"can the tool reach the system"* — it's *"does the assistant know which tool to reach for, and how."* The `docs/` directory is plain markdown your assistant can read; combined with `AGENTS.md.template`, it ends up knowing things like: - "For application logs, use the CloudWatch MCP — don't shell out to `aws logs`." - "If an AWS call returns `Token has expired`, run `aws sso login` and retry once before asking the user." - "The SQS MCP defaults to `us-east-1` — pass an explicit `region=` if your queues live elsewhere." These aren't novel insights — they're the kind of operational knowledge a human teammate accumulates after a week. Front-loading it for your AI on day one is what an AGENTS.md / CLAUDE.md / .cursorrules / .clinerules file is *for*. ## Quick start ```bash # 1. Install base chmod +x install.sh && ./install.sh # 2. Configure (see SETUP.md for details) cp templates/aws-config.template ~/.aws/config # then edit # Edit templates/mcp-servers.json — fill in placeholders # Wire it into your AI client (per-client steps in SETUP.md) # 3. Add a database (only if you need one) bash databases/mysql/install.sh # for MySQL bash databases/mssql/install.sh # for MS SQL Server # 4. Verify # Claude Code: claude mcp list # Cursor: Settings → Features → MCP Servers (UI shows status) # others: check your client's MCP server / tool list ``` Full walkthrough: [SETUP.md](SETUP.md). ## License MIT — see [LICENSE](LICENSE). Use it however you like. ## Contributing PRs welcome. Especially: - Additional MCP modules (Postgres, Redis, GitHub, GitLab, Kubernetes, …) - Per-client wiring examples (more clients, Windows install scripts) - Per-MCP doc improvements ## Source & license This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code. - **Author:** [rathore97aditya](https://github.com/rathore97aditya) - **Source:** [rathore97aditya/mcp-starter-kit](https://github.com/rathore97aditya/mcp-starter-kit) - **License:** MIT Install and usage instructions live in the source repository linked above. ## Pricing - **Free** — Free ## Security capabilities Automated source analysis of v0.1.0 — what this tool can access: - **Network access:** no - **Filesystem access:** no - **Shell / process execution:** no - **Environment & secrets:** no - **Dynamic code execution:** no *"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.* ## Versions - **0.1.0** — security scan: passed — Imported from the upstream source. ## Links - Listing page: https://agentstack.voostack.com/l/mcp-rathore97aditya-mcp-starter-kit - Seller: https://agentstack.voostack.com/s/rathore97aditya - Browse the marketplace: https://agentstack.voostack.com/browse --- Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.