Provides secure enterprise search over Notion knowledge bases, allowing AI agents to search internal wikis and documents.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Neon Enterprise MCP Gateway Search our Notion workspace for the Q3 security policy"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
The Zero-Trust Firewall for Claude & AI Agents
Neon Gateway allows you to securely connect your Claude Desktop or custom AI agents to internal Enterprise databases (Postgres) and Knowledge Bases (Notion) without exposing root credentials or risking data destruction.
Zero-Trust Postgres: Execute remote SQL queries forced into READ-ONLY transaction blocks. Agents cannot drop tables or delete data.
Notion Enterprise Search: Let Claude search your internal wikis and documents securely.
Audit Logging & Routing: All MCP traffic is routed through a secure Python Gateway.
Related MCP server: Brand MCP Server
This is a hosted, premium MCP Gateway for Enterprise and Agency teams.
Purchase an API Key here: https://neoninnovationlab.com/mcp
You will receive an mcp_live_... key instantly via email.
Configure your Claude Desktop using the instructions below.
Add the following to your claude_desktop_config.json:
{
"mcpServers": {
"neon-enterprise-gateway": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/client-cli",
"sse",
"--header",
"Authorization: Bearer YOUR_API_KEY_HERE",
"https://api.neoninnovationlab.com/sse"
]
}
}
}Execute a read-only query against the remote Neon database
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description's strongest behavioral disclosure is 'read-only', which conveys that the tool has no mutating side effects. However, with no annotations, the description carries the full burden and does not mention how the query is executed, whether there are any restrictions on query types, or what happens on errors.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, well-structured sentence that front-loads the essential action and target. There is no filler or redundant wording, making it appropriately concise.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with no output schema and no annotations, the description is too sparse. It does not describe the return format, how results are presented, or any limitations, leaving the agent to guess at critical execution details beyond the core purpose.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must compensate for the undocumented 'query' parameter, but it only says 'read-only query' without explaining query format, SQL dialect, or constraints. The target 'remote Neon database' adds context, but it does not meaningfully define the parameter's semantics beyond the parameter name.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a clear action ('Execute a read-only query') and a specific resource ('the remote Neon database'), going beyond the tool's generic name. It is unambiguous about the intended operation, though there are no sibling tools to differentiate from, so it falls just short of a full 5.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The term 'read-only' implies when the tool should be used, but no explicit guidance is given about when not to use it or what alternatives exist. With no sibling tools listed, the description provides the basic context but leaves the decision entirely to inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
With only one tool, there is no possibility of confusing it with another tool. The purpose of execute_query is clear and unambiguous within the tool set.
The single tool uses a clear verb_noun pattern. Although there is only one tool to judge, the naming style is predictable and conventional for a database query operation.
A single tool feels far too thin for a database gateway MCP server, even if it is intentionally read-only. The apparend scope of Neon Enterprise MCP Gateway implies more useful surface area than one query endpoint.
The server provides only read-only querying with no schema discovery, table listing, query planning, or write operations. Agents are left with a very limited surface that will be insufficient for most practical database workflows.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Query your warehouse or a CSV with Claude/ChatGPT over MCP, governed by table-level ACL + audit.
Query 40 databases from Claude, ChatGPT, or Cursor — on any device. Read-only, encrypted, audited.
Safe, read-only Postgres and MySQL access for AI agents. Audit log + column-level controls.
Query your org's data in natural language — read-only MCP access to SQL, NoSQL, files & warehouses.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/neoninnovationlab/neon-mcp-gateway'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
