View Categories

How to Connect PostgreSQL to Claude or Cursor via MCP

24 min read

MCP SERVER POSTGRESQL

Query PostgreSQL with Claude or Cursor via MCP.

Ask plain-English questions about your Postgres data — joins, aggregations, schema introspection, query performance — without exposing connection strings to the AI vendor or opening firewall ports on your network.

No firewall holes One key, every connector Live data, no cache lag Bring your own AI tool
Start Free Browse all MCP guides
See everything Query Streams can do beyond this guide Get Started Free
Supports
SQL Server PostgreSQL MySQL MariaDB SQLite MS Access Oracle BigQuery DuckDB
+more
Excel Sheets
Live Data

Replace exports with on-demand SQL

Excel Sheets
Nova
BI & AI Analytics

Ask Nova, get SQL + charts

Meet Nova
REST API
Database REST API

One key per partner. No credentials shared.

Build an API
Airtable Smartsheet Baserow SeaTable +more
Automation

Scheduled sync to 6+ platforms

Explore
Stripe HubSpot Shopify GA +more
API to SQL

Query APIs with SQL, no code

Explore
MCP Claude Cursor ChatGPT Grok +more
AI Database MCP

Claude, Cursor, ChatGPT & Grok talk to your data

Connect AI

Query Streams is a secure, real-time data integration platform that brings every database and SaaS API in your account into Claude, Cursor, ChatGPT, and Grok — through a single MCP key with no firewall changes. This guide walks through wiring up the PostgreSQL connector specifically, so your AI tool can answer plain-English questions about orders, customers, products, and any other Postgres data — joins, aggregations, schema exploration, query performance — without you copy-pasting CSV exports out of pgAdmin or DBeaver. Learn more at QueryStreams.com and sign up for free to start asking your AI tool real Postgres questions.

What Query Streams MCP gives you for PostgreSQL

Other “PostgreSQL MCP” servers on the open-source landscape connect the AI tool directly to a Postgres connection string. That works, but it pushes a database password (or an IAM token) into your AI client’s config, scopes the AI tool to only that one Postgres cluster, and gives you no audit trail of what the AI actually asked. Query Streams MCP solves a wider problem: one key, every connector, full audit trail, and the AI tool never holds your Postgres credentials.

Zero inbound firewall holes

The Network Agent opens a single outbound encrypted cloud link to Query Streams. Your AI client connects to the cloud, never to your Postgres host. No port to open, no IP to allowlist, no VPN, no Postgres listener exposed to the public internet.

One key, every connector

The same MCP key reaches every database and SaaS API your account has connected. Add a Stripe or Snowflake connector tomorrow and the AI tool sees it next to your Postgres tables without re-keying.

Schema Intelligence baked in

The AI sees AI-curated descriptions, semantic types, enum value lists, and discovered foreign keys for every Postgres column — not just bare information_schema output. It writes accurate SQL on the first try, even on legacy schemas with cryptic column names.

Read-only enforced at the agent

Even a hallucinating LLM can’t issue DELETE, UPDATE, or TRUNCATE through Query Streams MCP. The Network Agent rejects anything that isn’t SELECT, WITH, or EXPLAIN before Postgres ever sees the SQL.

Per-key rate limits

Default 60 requests per minute and 10 execute calls per minute, configurable per key. A runaway AI tool-call loop hits a token bucket, not your Postgres connection pool or your AWS RDS bill.

How it works without opening firewall ports

The Query Streams Network Agent is a small program you install once on a machine that can reach your PostgreSQL cluster (any laptop, on-prem server, EC2 instance, Azure VM, or cloud VM in the same VPC as your Postgres). It dials one outbound TLS link to the cloud and runs SQL against Postgres over the local network using the standard Postgres protocol — nothing inbound, nothing exposed, and the AI tool never sees your Postgres connection string. How the outbound-only architecture works →

AI Client

Cursor, Claude,
ChatGPT, Grok

QS MCP Server

Streamable HTTP
X-MCP-Key auth

Network Agent

On your network
Cloud link out

PostgreSQL

Connection string
held by the agent

No inbound port required — the agent dials out, never the other way around

The MCP key you give Cursor or Claude is scoped (read / analyze / execute), revocable at any time, and rate-limited per-key. The AI tool calls these MCP tools to do its work:

querystreams-mcp · tool catalog
qs_list_organizationsread
Returns the org bound to the calling key.
qs_list_agentsread
Lists Network Agents and online state.
qs_list_connectorsread
Lists data connectors (one entry per database server or API).
qs_get_connector_schemaread
Returns the PostgreSQL databases, schemas, tables, and columns the AI can query, with Schema Intelligence enrichment when available.
qs_profile_tableanalyze
Sample values, distributions, enum detection, semantic types — on demand.
qs_list_saved_queriesread
Pre-built parameterized SQL templates the team trusts. The AI runs them without ever seeing the SQL.
qs_run_saved_queryexecute
Executes a saved query by pattern_key with optional parameter overrides.
qs_run_queryexecute
Executes a SELECT against a connector. Read-only validator runs at the agent, before Postgres sees the SQL.

Why Schema Intelligence makes Query Streams MCP different

Most “MCP for Postgres” servers in the open-source landscape hand your AI tool the same information_schema Postgres hands a stranger. Column names. Data types. Maybe a primary key. The LLM is left to guess what status_id = 3 means, what usr_eml stores, or whether line_items.order_id actually joins to orders.id (no foreign key was ever declared either way). That’s why the first SQL most LLMs write against a bare schema is wrong — not because the LLM is bad, but because it doesn’t have the data it needs to be right.

Query Streams MCP returns that same schema enriched with what we call Schema Intelligence (SI) — AI-curated metadata that’s generated by running profiling queries against your actual Postgres data before the AI client ever asks. When SI is enabled on a connector and database, every schema tool the AI calls (qs_get_connector_schema, qs_get_table_schema, qs_profile_table, qs_get_relationships) returns the bare schema plus six layers of curated knowledge. The LLM stops guessing.

To make this concrete, here is what the AI client gets back from a single qs_get_table_schema call against a typical Postgres e-commerce schema (orders, line_items, customers, products) — first without Schema Intelligence, then with it.

Without Schema Intelligence data_source: captured_schema
// what the LLM sees == TABLE: orders == – id integer [PK, NOT NULL] – customer_id integer NOT NULL – total numeric(10,2) NOT NULL – status varchar(20) NOT NULL – created_at timestamp NOT NULL – shipped_at timestamp == TABLE: line_items == – id integer [PK] – order_id integer NOT NULL – product_id integer NOT NULL – qty integer NOT NULL – unit_price numeric(10,2) NOT NULL == TABLE: customers == – id integer [PK] – email varchar(255) – name text == TABLE: products == – id integer [PK] – name text – sku varchar(64) Foreign Keys: (none declared) si_recommendation: state: “not_run” what_youre_missing_for_this_call: – AI-discovered foreign keys – Per-column sample values + enum detection – Table and column descriptions – Semantic type classifications – Business domain tagging note: “types only, no semantic context”
With Schema Intelligence data_source: schema_intelligence
// what the LLM sees == TABLE: orders [FACT, domain:sales] == “Customer order header rows; one per checkout. total is the order grand total in USD.” – id integer [PK] identifier – customer_id integer identifier FK -> customers.id (100% overlap, conf 0.99) – total numeric(10,2) currency Range: 0.00 – 4,820.00 · mean 142.30 – status varchar(20) status_code (enum) paid (62%) | shipped (28%) | refunded (6%) | pending (4%) – created_at timestamp date_iso Sample: 2026-04-28 14:02:11+00 – shipped_at timestamp date_iso (nullable) == TABLE: line_items [FACT, domain:sales] == “One row per product per order. Revenue = SUM(qty * unit_price).” – order_id integer identifier FK -> orders.id (98% overlap, conf 0.95) – product_id integer identifier FK -> products.id (100% overlap, conf 0.99) – qty integer counter – unit_price numeric(10,2) currency == TABLE: customers [DIM, domain:customers] == – email varchar(255) email Sample: [email protected], [email protected] – name text person_name == TABLE: products [DIM, domain:products] == – name text text_content – sku varchar(64) identifier Sample: [‘QS-001-MINT’,’QS-014-DARK’,’QS-027-AMBER’]

The six layers Schema Intelligence adds

Each layer addresses a class of question the LLM would otherwise guess at. The opt-in SI profiling pass runs read-only against your Postgres data without changing your schema or writing to your database, and refreshes incrementally when your schema changes. what Schema Intelligence adds and how it stays current →

AI-curated descriptions

Plain-English purpose for every database, schema, table, and column — generated once, refreshed when your schema changes. Confidence-scored; user-authored descriptions always win.

orders: “Customer order headers;
one row per checkout.”

Table classifications

Each table tagged FACT (transactional events), DIM (descriptive reference), or LOOKUP (small code maps), plus a business domain — sales, hr, seo, finance, support, and 14 more.

orders [FACT, domain:sales]
customers [DIM, domain:customers]

Semantic types per column

Eighteen types — currency, email, date_iso, status_code, percentage, ranking_position, identifier, url, person_name, and more. The AI generates dialect-correct Postgres SQL appropriate to each type.

total: currency · email: email
created_at: date_iso

Sample values from real data

Random rows surfaced to the LLM so it recognises patterns no schema can show — formatting conventions, encoded values, abbreviation styles, and the actual shape of your strings.

sku: [‘QS-001-MINT’, ‘QS-014-DARK’,
‘QS-027-AMBER’]

Enum detection with distributions

Low-cardinality columns (50 or fewer distinct values, at most 5% of rows unique) mapped to their full value list with row counts. The AI never guesses casing or spelling.

status: paid (62%) | shipped (28%)
| refunded (6%) | pending (4%)

Implicit foreign-key discovery

Cross-table data overlap analysis finds joins that aren’t declared as DDL constraints. Stored alongside formal FKs with confidence scores, returned by qs_get_relationships.

line_items.order_id -> orders.id
(98% overlap, conf 0.95)

Same prompt, different SQL

The proof is in the SQL the AI tool actually writes. Same Cursor session, same Claude model, same prompt — “What were the top 5 products by revenue in the last 30 days?” Without Schema Intelligence the LLM has to guess. With it, the LLM knows.

Without Schema Intelligence
— LLM’s first attempt against bare schema: SELECT product_id, SUM(unit_price) AS revenue FROM line_items WHERE created_at >= ‘2024-01-01’ ORDER BY revenue DESC LIMIT 5 ✕ ERROR: column “created_at” does not exist ✕ created_at is on orders, not line_items ✕ no JOIN — line_items isn’t time-stamped ✕ SUM(unit_price) ignores qty — wrong revenue ✕ hardcoded date — “last 30 days” is dynamic ✕ returns product_id, not product name
With Schema Intelligence
— LLM’s first attempt with SI enabled: SELECT p.id, p.name, SUM(li.qty * li.unit_price) AS revenue FROM orders o JOIN line_items li ON li.order_id = o.id JOIN products p ON p.id = li.product_id WHERE o.created_at >= NOW() – INTERVAL ’30 days’ GROUP BY p.id, p.name ORDER BY revenue DESC LIMIT 5 ✓ 5 rows. Correct first try. ✓ FACT/DIM tags guided the join structure ✓ FK discovery surfaced order_id -> orders.id ✓ created_at saw semantic type = date_iso ✓ Postgres-idiomatic NOW() – INTERVAL ’30 days’
Don’t want to run Schema Intelligence? MCP still works. Without SI, schema tools return bare metadata (types, primary keys, formal foreign keys, indexes) and every degraded response carries an si_recommendation block telling the AI exactly what it’s missing — including a one-call option to enable SI mid-conversation via qs_request_si_analysis. Your AI client can offer to trigger an SI run on the spot (“would you like me to enable Schema Intelligence on this database first? It runs through your Network Agent in the background and will dramatically improve my answers”). Run time scales with table count: a small database under 100 tables completes in around 10 minutes; a typical mid-size database (a few hundred tables) finishes in 15–25 minutes; a large enterprise database with 1,500+ tables can take 45–60 minutes for a full scan. Subsequent refreshes after schema changes are incremental and much faster than the first run. Schema Intelligence is opt-in. We just don’t think you’ll want to opt out.
Nova AI

MCP not for you? Try Nova AI instead.

Skip the JSON config entirely: Nova AI is built into the Query Streams web portal and asks the same plain-English questions across your PostgreSQL connector — “top 10 customers by lifetime value,” “orders that haven’t shipped in over 7 days” — plus every other connector on your account, with the same agent, read-only enforcement, and Schema Intelligence, and no MCP plumbing.

Meet Nova AI

Prerequisites

Before you start, make sure you have:

  1. A free Query Streams account at my.querystreams.com.
  2. The Query Streams Network Agent installed on a machine that can reach your PostgreSQL cluster — see Download the Query Streams Agent.
  3. A PostgreSQL connector configured against the agent — see the existing connector setup guides for the connection string. The agent holds the Postgres password (or IAM credentials for managed Postgres); the AI tool never touches them.
  4. Any MCP-capable AI client. We’ll show Cursor, Claude Desktop, ChatGPT, and Grok in this guide; if you use Windsurf, Zed, Continue, Cline, VS Code Copilot, Codex, or Goose, the config block is essentially the same.
  5. Five minutes.
You only set up the agent once. The same agent that powers Query Streams’ Excel and Google Sheets add-ons, the web Query Builder, and Nova AI also serves MCP. Adding MCP to an existing Query Streams account is just generating a key — the agent and Postgres connector are already running.
1

Generate an MCP key

From the /mcp page in Query Streams, mint a key with the scopes you want.

2

Drop it into your AI client

One JSON snippet for Cursor, Claude, ChatGPT, or Grok. Same key everywhere.

3

Ask a question

“What were our top 10 customers by lifetime value?” — the AI calls the right tools, you get the answer.

Step 1: Generate an MCP key in Query Streams

Sign in to Query Streams and open the MCP page (or sign in first at my.querystreams.com and click MCP in the left navigation). Click Generate key, give the key a recognizable name (something like cursor-laptop or claude-desktop), and pick the scopes you want this key to have:

  • read — the AI can browse connectors and read schema. Required for everything else.
  • analyze — the AI can profile tables and discover relationships (sample values, distributions, semantic types). Optional but strongly recommended for Postgres work, where understanding the shape of your data matters when the LLM is generating joins.
  • execute — the AI can actually run SQL. Without this, the AI is read-only against schema metadata only.

For a typical “let Claude analyse my Postgres data” workflow, all three scopes are appropriate. For a key you’re handing to a teammate or a less-trusted client, drop execute and let them browse only. You can revoke any key at any time from the same page; the AI client will see MCP_KEY_REVOKED on its next call and stop working immediately. There’s no propagation delay.

Copy the key now — Query Streams shows it once, then stores only a hash. If you lose it, generate a new one. The key looks like qsmcp_ followed by 48 random characters and is what your AI client sends in the X-MCP-Key request header.

Step 2: Add Query Streams MCP to your AI client

The configuration is the same shape across every MCP-capable client — an MCP server entry pointing at https://mcp.querystreams.com with your key in the X-MCP-Key header. Pick your client below.

Cursor
Cursor ~/.cursor/mcp.json 
// Edit ~/.cursor/mcp.json
{
  "mcpServers": {
    "querystreams": {
      "url": "https://mcp.querystreams.com",
      "headers": {
        "X-MCP-Key": "qsmcp_PASTE_KEY_HERE"
      }
    }
  }
}
Claude Desktop
Claude Desktop claude_desktop_config.json 
// Settings → Developer → Edit Config
{
  "mcpServers": {
    "querystreams": {
      "url": "https://mcp.querystreams.com",
      "headers": {
        "X-MCP-Key": "qsmcp_PASTE_KEY_HERE"
      }
    }
  }
}
ChatGPT
ChatGPT Apps & Connectors 
// Settings → Apps & Connectors → Add MCP
Server URL  https://mcp.querystreams.com
Auth header X-MCP-Key
Header value qsmcp_PASTE_KEY_HERE

// Requires a paid ChatGPT plan
// (Plus / Pro / Team / Enterprise).
Grok
Grok Remote MCP Tools 
// Grok → Settings → Tools
{
  "mcp_servers": [{
    "name": "querystreams",
    "url": "https://mcp.querystreams.com",
    "auth_header": "X-MCP-Key",
    "auth_value": "qsmcp_..."
  }]
}

Restart your AI client. On its next start it will discover the eight Query Streams MCP tools listed above and surface them in its tool palette. In Cursor and Claude Desktop you can verify by typing “list connectors” — the AI should call qs_list_connectors and return your PostgreSQL connector along with anything else you have configured.

Step 3: Ask the AI a PostgreSQL question

You don’t write SQL — the AI does. You ask a question, the AI picks the right MCP tool, the agent runs the query against your Postgres database, and the answer comes back as text plus tables. Three example prompts to try first:

“What were our top 10 customers by lifetime value?”
Customers
The AI will call qs_get_connector_schema to discover the orders, line_items, and customers tables, then qs_run_query with a SELECT that joins customers to orders to line_items, computes SUM(qty * unit_price) per customer, and returns the top 10 by lifetime value. You’ll see the result table inline, plus a written interpretation — which customers are concentrated in which products or regions, repeat-purchase patterns, average order size — that the AI inferred from the data.
“Show me orders that haven’t shipped in over 7 days.”
Operations
The AI uses Schema Intelligence’s enum-detection on orders.status to filter to 'paid' orders that have a NULL shipped_at and a created_at older than NOW() - INTERVAL '7 days'. The result is a focused list with order id, customer email, total, and days-since-paid — usually the AI sorts by oldest first and flags the most concerning ones, which are fulfillment-team escalations rather than rounding errors. You can drill in by asking “why is order 4821 still pending?” and the AI will pull the relevant rows.
“How does this month’s revenue compare to the same month last year?”
Revenue
A year-over-year comparison with totals, percentage change, and a per-product or per-category breakdown if the AI thinks it’s relevant. The AI will use Postgres-idiomatic DATE_TRUNC('month', o.created_at) and date arithmetic, and will typically follow up with “want me to chart this by week?” or “want to see the same comparison split by acquisition channel?” if you have those columns in another table. Conversational; you don’t need to reset context between questions.

The first time the AI calls a tool, your client may pop up a confirmation prompt asking you to approve the tool call — that’s MCP’s standard consent flow, not anything Query Streams adds. Approve once and the AI proceeds with the rest of the conversation freely. You can revisit the consent at any time in your client’s settings.

Honest billing notice: MCP usage is charged on uncompressed bytes

Query Streams’ Excel add-in, Google Sheets add-on, web Query Builder, and Nova AI all run over our compressed cloud link — we measure and bill compressedBytes against your data realm. The MCP transport (Streamable HTTP per the official MCP spec) does not reliably support compression end-to-end across every client and intermediate proxy, so we measure and bill uncompressedBytes for MCP traffic.

  • What this means: a 1 MB Postgres result set costs ~1 MB of your data realm when fetched via MCP, vs. ~150–250 KB via Excel / Sheets / Nova / the Query Builder. A 10,000-row aggregate query that lands as ~2 MB of JSON over MCP would have been ~300–400 KB of LZ4-compressed bytes through the Excel / Sheets / Nova / Query Builder clients. Same data, different transport, different billable size.
  • What this isn’t: a markup or a punishment for using MCP. We pass through actual bytes shipped. The other clients are cheaper because compression works reliably on those transports; we don’t punish you for the protocol choice, but we have to be transparent about the cost shape.
  • What you can do: for very large recurring queries (e.g. 100K+ row exports), prefer the Excel / Sheets / Nova path. For interactive AI tool calls (the typical 100–5,000 row Postgres response that fits in an LLM context), MCP is the right choice and the cost difference is in cents.

Frequently asked questions

Do I need to open ports or run a VPN to use this? +
No inbound rules, port-forwarding, NAT punchthrough, or VPN. The Network Agent makes one outbound TLS connection (port 443) and your AI client reaches https://mcp.querystreams.com from the public internet — if outbound HTTPS works on the agent host, MCP works. See how the outbound-only connection works →
Which AI tools can I use with Query Streams MCP? +
Any client that speaks the open Model Context Protocol — Claude Desktop, Claude Code, Cursor, ChatGPT (paid), Grok, Gemini CLI, Windsurf, Zed, and 500+ more. Bring your own AI tool; you don’t have to switch. Full list of supported AI clients →
Can I revoke an MCP key? +
Yes — three independent kill-switches (per-key from the /mcp page, per-org via plan settings, and platform-level), none of which need a database password rotation or agent restart. More on MCP key security →
How is MCP usage billed against my data realm? +
MCP execute calls deduct from the same data-realm budget your Excel, Google Sheets, web Query Builder, and Nova AI usage already draws on — one consumption budget across every access method. The size measured for MCP differs. The other clients run over our compressed cloud link (we bill compressedBytes); MCP runs over Streamable HTTP, which doesn’t reliably support compression end-to-end through every client and proxy, so we bill uncompressedBytes. A 1 MB Postgres result returned to Excel typically costs ~150–250 KB of your data realm; the same 1 MB result returned to Cursor over MCP costs ~1 MB. We’re transparent about it because we’d rather you know up front than be surprised at the end of the billing cycle.
Does Query Streams MCP work with my managed PostgreSQL on AWS RDS, Azure Database for PostgreSQL, or Google Cloud SQL? +
Yes — Query Streams MCP works with any Postgres engine the Network Agent can reach over TCP, regardless of where it’s hosted. Specifically supported: AWS RDS for PostgreSQL, AWS Aurora PostgreSQL-compatible, Azure Database for PostgreSQL (Single Server, Flexible Server), Google Cloud SQL for PostgreSQL, DigitalOcean Managed PostgreSQL, and self-hosted Postgres on EC2, Azure VMs, Google Compute Engine, or on-premise hardware. The agent handles the connection string — IAM auth, SCRAM-SHA-256, SSL/TLS, custom CA certs are all supported. Multiple Network Agents are available across subscription tiers, so you can deploy an agent in the same region or VPC as each Postgres cluster for the best latency. The MCP server doesn’t see the credentials; only the agent does.
How does this differ from running an open-source PostgreSQL MCP server myself? +
A direct PostgreSQL MCP server (community projects on GitHub do exist) is one MCP per data source. To get Claude reading from your Postgres + Google Search Console + your Stripe account + your Snowflake warehouse you’d need four MCP servers configured separately in every AI client, each with its own credentials, each with its own scope model, each with its own audit story. Query Streams MCP is one key reaching every connector your account has paired. You also pick up Schema Intelligence, agent-layer read-only enforcement, per-key rate limits, audit trail in event_logs, and the same data-realm billing pipeline you already use — none of which a direct MCP gives you.
What happens if the AI tries to write or delete data? +
It’s rejected at the agent before the data source sees the SQL. Every qs_run_query call is parsed by a hardcoded read-only validator that allows only SELECT, WITH, and EXPLAIN statements; anything else returns READONLY_VIOLATION and never reaches PostgreSQL. The validator runs in the agent process on your network, not in the cloud, so a compromised cloud surface couldn’t bypass it. (You can layer a Postgres-side READ ONLY role on top if you want belt-and-suspenders — the agent’s validator is independent of whatever Postgres role you’ve configured.)
Can I see what the AI actually asked? +
Yes. Every MCP tool call writes a row to event_logs with the org, user, key, scope, latency, and result code. The org-admin can answer “who used MCP last week, which connector, and what did they ask?” with a single query. Note that we log the tool name and metadata, not the SQL text or returned rows — those flow through the cloud link and never land in cloud logs. If you want full SQL audit, enable database-side audit on the underlying engine; for Postgres specifically that’s pgaudit or your existing query-log pipeline.
Do I have to run Schema Intelligence to use Query Streams MCP? +
No — Schema Intelligence is opt-in per (connector, database) pair, and MCP works fine without it. The AI gets bare schema (types, primary keys, formal foreign keys, indexes) and writes basic queries. With SI enabled, the AI gets six additional layers of curated metadata: (1) AI-curated descriptions on every database, table, and column; (2) table classifications (FACT for transactional events, DIM for descriptive reference, LOOKUP for small code maps) plus a business domain tag (sales, hr, seo, finance, support, and 14 more); (3) a semantic type on every column (currency, email, date_iso, status_code, percentage, ranking_position, identifier, url, person_name, and 9 more) that drives dialect-correct Postgres SQL generation; (4) sample values from your real data so the LLM recognises patterns no schema can show; (5) enum detection with full value distributions for low-cardinality columns; and (6) AI-discovered foreign keys based on cross-table data overlap, surfaced through qs_get_relationships. Without SI, every schema-tool response also carries an si_recommendation block listing exactly what’s missing for the call — the AI can read this and offer to trigger SI mid-conversation via qs_request_si_analysis. Run time scales with table count: a small database under 100 tables completes in around 10 minutes; a typical mid-size database (a few hundred tables) finishes in 15–25 minutes; a large enterprise database with 1,500+ tables can take 45–60 minutes for a full scan. SI runs through your Network Agent against your data (never in the cloud), never writes to your database, never changes your schema, and refreshes incrementally when your schema changes — so subsequent runs after you add or alter tables are much faster than the first one. The end-to-end effect: with SI enabled, your AI client writes correct SQL on the first try far more often than it does against any “MCP for X” server that just hands the LLM information_schema.
What if I add another connector later, like Stripe or PostgreSQL? +
Nothing changes client-side — the same key reaches the new connector the moment the agent pairs it (qs_list_connectors picks it up automatically). One config block buys your whole account, present and future. Why one key covers every connector →
Do I have to set up MCP just to chat with my data? +
No — Nova AI is built into the Query Streams portal and works against every connector (PostgreSQL included) with no MCP setup or config files. Use Nova to chat with your data inside Query Streams; use MCP when you want your own AI client (Claude, Cursor, ChatGPT, …) to reach the same data — same agent, same connectors, same Schema Intelligence underneath. Learn more about Nova AI →

Get started

Connect your AI tool to your PostgreSQL data in five minutes.

One MCP key reaches PostgreSQL, every other database, and every API connector in your Query Streams account — with full audit trail, per-key rate limits, and zero firewall changes. Claude, Cursor, ChatGPT, and Grok all work out of the box.

Sign Up Free Download Agent

Related guides: Download the Query Streams Agent | Database Connector Setup | All MCP Server guides | Nova AI text-to-SQL

Category: MCP Server

Tags: mcp, claude, cursor, postgresql, postgres, postgres-mcp, ai

Meta Description: Connect Postgres to Claude or Cursor via Query Streams MCP. Outbound-only, read-only, 5-min setup.

Updated on June 16, 2026
claude cursor database mcp open-source-database postgresql

What are your Feelings

  • Happy
  • Normal
  • Sad

Powered by BetterDocs