Connect Neon to Microsoft Copilot via MCP

💡 No install? Use cloud.anythingmcp.com directly. Sign in, click Connectors → Neon, paste your credentials, mint an MCP API key and you're done. No Docker, no git clone, no local server.

Neon + Microsoft Copilot

Let your AI manage Neon serverless Postgres: projects, branches, compute endpoints, databases, roles, schemas, operations and consumption. It can create branches and start or suspend computes after your confirmation. Never returns passwords. With a Neon API key.

Prerequisites

See the full setup instructions baked into the connector (visible in the in-app store when you select the connector). The required environment variables for this connector are:

NEON_API_KEY

Step 1 — Get credentials

1. In the Neon Console, open Account settings → API keys for a personal key (it acts as you, in every organization you belong to), or Organization settings → API keys for a key that reaches only that organization's projects. A project-scoped key reaches a single project.
2. Create the key and copy it at once: Neon shows it only once. Paste it into NEON_API_KEY and install the connector. The key is sent only to console.neon.tech.
3. Check the setup with neon_list_organizations: it lists the organizations the key belongs to, with their org_id.

What it covers: organizations, projects, branches, compute endpoints, databases, roles, database schemas, operations and consumption, through the Neon API v2. The AI walks down from neon_list_projects to neon_get_project, neon_list_branches, neon_list_endpoints, neon_list_databases, neon_list_roles and neon_get_database_schema, which shows the tables, columns, indexes and constraints of a database, also as they were at a past time. With a personal key, organization projects need the org_id.

Asks before every change: neon_create_branch, neon_start_endpoint and neon_suspend_endpoint change your project, so the AI tells you what will happen and waits for your yes.

• A running compute uses compute hours, which count against your plan's allowance or are billed on paid plans. neon_start_endpoint starts that meter; computes scale to zero by themselves after the suspend timeout.
• neon_suspend_endpoint closes every open connection to that compute at once.
• neon_create_branch makes an instant copy-on-write branch, optionally from a point in time. Branches beyond your plan's allowance can be billed, and a compute added to the branch starts right away. Give temporary branches an expiry date.
• Every change runs as an operation in the background; neon_list_operations and neon_get_operation show when it has finished.

Switched off at install: neon_delete_branch, which deletes a branch together with its computes. An administrator turns it on deliberately. The root and default branch can never be deleted.

Usage and cost: neon_get_consumption returns compute time, storage, branch counts and network transfer per project, by hour, day or month. It needs the org_id, works on paid plans only (Launch, Scale, Business, Enterprise) and does not wake any compute. Project and branch details also show this period's compute time, active time, written data and data transfer.

No passwords, no SQL: role passwords and connection strings are never returned, so no database password reaches the AI. This connector does not run SQL either: Neon's SQL over HTTP needs a connection string with the role's password, not the API key. To query your data, add the PostgreSQL connector with a dedicated read-only Postgres role on your Neon host (port 5432, SSL required). neon_get_database_schema still shows the structure without any password.

Common errors: 401: the API key is wrong or was revoked; create a new one. 403: the key may not reach that project or organization (a project or organization key used elsewhere), or your plan does not include the feature, for example consumption history. 404: wrong project, branch or endpoint id. 423 Locked: another operation is running on the project; wait for it and retry. 429: too many requests; wait a moment and retry.

The connector does not create or delete projects, databases or roles, reset passwords, or cover Neon Auth, the Data API, snapshots or organization administration.

Step 2 — Install the adapter

curl -fsSL https://raw.githubusercontent.com/HelpCode-ai/anythingmcp/main/docker-compose.quickstart.yml -o docker-compose.yml
printf 'JWT_SECRET=%s\nENCRYPTION_KEY=%s\n' "$(openssl rand -hex 32)" "$(openssl rand -hex 32)" > .env
docker compose up -d

Step 3 — Add the connector in Microsoft Copilot

Your server URL: in AnythingMCP, open MCP Servers → the server this connector is on, and copy its URL (https://cloud.anythingmcp.com/mcp/…). Use it wherever this guide shows YOUR_SERVER_ID.

Microsoft Copilot uses MCP servers through agents built in Copilot Studio: you add AnythingMCP to an agent as a tool, then publish the agent to Microsoft 365 Copilot and Teams. Copilot Studio connects from Microsoft's cloud over Streamable HTTP, which AnythingMCP supports.

1. In Copilot Studio, open your agent (or create one), go to Tools and choose Add a tool → New tool → Model Context Protocol.
2. Enter a Server name (for example AnythingMCP), a Server description that says what the connector does, and the Server URL https://cloud.anythingmcp.com/mcp/YOUR_SERVER_ID. Copilot Studio uses the description to decide when to call the server.
3. Under authentication, choose API key, set Type to Header and the header name to X-API-Key, then select Create.
4. In Add tool, choose Create a new connection, paste an MCP API key from AnythingMCP (MCP Servers → your server → API keys) and select Add to agent.
5. Try it in the agent's Test pane: ask for something that needs the Neon tools.
6. Select Publish, then Channels → Microsoft 365 and Microsoft Teams, keep Make agent available in Microsoft Copilot selected and choose Add channel. See agent in Teams installs it for you; in Microsoft 365 Copilot, type @ and pick the agent.

Prefer per-user sign-in? Choose OAuth 2.0 → Dynamic discovery instead of an API key: each user then signs in to AnythingMCP the first time the agent calls it.

Self-hosting? Use your instance's public HTTPS address instead of https://cloud.anythingmcp.com. Copilot Studio connects from Microsoft's cloud, so localhost does not work.

Available tools

Example prompts

• "List all our Neon projects with region, Postgres version and storage size, and tell me which ones had no compute activity this month."
• "Show me the schema of the app database on our production branch: tables, columns and indexes."
• "Create a branch called feature-billing from main that expires in 7 days. Tell me what it may cost before you create it."
• "Which computes are active right now? Suspend the one on the preview branch, but ask me first."
• "How much compute time and storage did each project use last month?"

FAQ

Which Copilot is this for? Microsoft 365 Copilot at work, through agents built in Copilot Studio. The Microsoft Copilot app for personal accounts has no option to add your own MCP server.

What do I need? A work account with access to Copilot Studio (a license or a trial) to build the agent. People who use it in Microsoft 365 Copilot or Teams need access to the agent: share it with them, or ask an admin to publish it to the organization. If your organization applies data policies to Power Platform connectors, they cover MCP servers too.

The agent doesn't call the tools. Check that the header name is exactly X-API-Key and that the key belongs to the same MCP server as the URL, and make the server description specific: Copilot Studio uses it to decide when to call the server. Publish the agent again after each change; in an open chat, type "start over" to get the new version.

Next steps

• Connector landing page
• Connect to Claude
• Connect to ChatGPT
• Connect to Cursor
• Connect to Gemini
• Connect to Meta Muse