Search and data
Neon for AI agents.
Make the right project easier to review.
Read accessible projects and related records in Neon. Prepare a source-grounded database project inventory within the selected account.
About Neon
With the Neon connector, your agent reads database projects with the project’s Agent200 API key, so no separate Neon account or key is needed. It can list and read projects, list and read branches, and list databases, using only the tools your project allows.
Neon is a serverless Postgres database service.
Tools
What your agent can do in Neon.
Each tool is a capability the model can call. You decide which ones a project allows, and your Agent200 API key reaches them.
-
List projects
Readneon_list_projectsFind projects visible to the Neon API key.
-
Read a project
Readneon_get_projectRetrieve one project by ID.
-
List branches
Readneon_list_branchesFind branches for an identified project.
-
Read a branch
Readneon_get_branchRetrieve one branch by ID.
-
List databases
Readneon_list_databasesFind databases on the selected branch.
No tool matches that search.
Control
Limits you can set.
You decide what your agent may do in Neon, and Agent200 runs every call within those limits.
-
Turn single tools on or off
Let the agent read projects and branches, and switch off
neon_list_databasesif it should not see which databases exist. -
Restrict what the agent reaches
Choose the endpoints a project may use, for example projects and branches but not databases. A call outside them is refused.
Get started
Connect Neon
in two steps.
-
1
Set up the SDK
Add the Agent200 SDK to the codebase you already have and authenticate with your API key. The key covers every connector enabled for the project.
agent.jsConceptual exampleSet up the SDK with the Agent200 API key // One Agent200 API key covers every connector enabled for the project. const agent200 = new Agent200({ apiKey: process.env.AGENT200_API_KEY, }); -
2
Run with the Neon tools
Name the model and the tools. The model decides which Neon tools to call, and Agent200 executes them with your Agent200 API key.
run.jsConceptual exampleRun a request with the connector's tools const result = await agent200 .user("user_123") .run({ model: "openai/gpt-5.6-sol", input: "List my Neon projects", tools: ["neon"], }); console.log(result.output);
For agents
Instructions for AI agents.
Using a coding agent? Paste this brief into it, or give it the address of this page. It describes the Neon connector and how to use it.
Connector: Neon, through Agent200. In code: "neon". What it does: Read accessible projects and related records in Neon. Prepare a source-grounded database project inventory within the selected account. Page: https://www.agent200.com/connectors/neon/ 1. Get an Agent200 API key. If the developer has none, send them to https://agent200.com/platform/apikeys/ and ask them to choose "Create an API key". Read the key from the AGENT200_API_KEY environment variable. Never ask for it in chat, and never write it into code, prompts or logs. 2. Agent200 reaches Neon with the project's Agent200 API key. No separate Neon key is needed. 3. Read tools: neon_list_projects, neon_get_project, neon_list_branches, neon_get_branch, neon_list_databases. Name "neon" in the tools of a request; the model decides which tool to call. 4. Stay within the project's settings. If a tool is turned off or a call is refused, tell the user. Do not work around it. 5. Before a write, confirm with the user, unless they asked for that exact change. 6. For setup with a specific framework, follow its guide: https://www.agent200.com/connectors/neon/framework/claude/ https://www.agent200.com/connectors/neon/framework/chatgpt/ https://www.agent200.com/connectors/neon/framework/claude-code/ https://www.agent200.com/connectors/neon/framework/muse/ https://www.agent200.com/connectors/neon/framework/grok-bot/ https://www.agent200.com/connectors/neon/framework/openai-dots/ https://www.agent200.com/connectors/neon/framework/claude-duet/ https://www.agent200.com/connectors/neon/framework/hermes-agent/ https://www.agent200.com/connectors/neon/framework/openclaw/ The code on the connector page is a conceptual example of the SDK. SDK reference: https://docs.igpt.ai/
This page is also available as Markdown, for agents and LLMs: /connectors/neon.md
Guides
Use Neon with the AI you build on.
Step-by-step setup for Neon with a specific model, assistant or agent framework.
-
Neon + Claude
How to connect Neon to Claude
-
Neon + ChatGPT
How to connect Neon to ChatGPT
-
Neon + Claude Code
How to connect Neon to Claude Code
-
Neon + Muse
How to connect Neon to Muse
-
Neon + Grok Bot
How to connect Neon to Grok Bot
-
Neon + OpenAI Dots
How to connect Neon to OpenAI Dots
-
Neon + Claude Duet
How to connect Neon to Claude Duet
-
Neon + Hermes Agent
How to connect Neon to Hermes Agent
-
Neon + OpenClaw
How to connect Neon to OpenClaw
FAQ
Neon and Agent200, answered.
What access does Neon need?
Use a Neon personal, organization or project API key held securely by the project. Key scope determines which organizations and projects can be listed. Provider documentation.
Does a list include every record?
A project inventory is control-plane metadata, not database row access. Do not expose connection strings or credentials in an agent answer.
Can this workflow make changes?
The listed Neon operations are read-only. A proposed change in the agent answer does not edit the source.
How should I verify the answer?
Identify the selected project and compare the answer with project, branch, database and operation fields. Disclose missing or inaccessible fields.
Are these exact runtime tool schemas?
The listed identifiers describe catalogue capabilities. Discover the actual runtime tool names and input schemas before executing a request.