Sign in
mcp server · kalehdoo.github.io

warehouse-mcp

Production MCP server for Postgres, Oracle, Snowflake, BigQuery, Redshift, DuckDB, MotherDuck.

What it says

The record the registry holds

How you get it

There is no address to call. This one is a package you install and run yourself, wherever your assistant runs.

warehouse-mcp · npm · 0.4.2
the record Copied from the official MCP registry, exactly as it holds it.
{
  "server": {
    "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
    "name": "io.github.kalehdoo/warehouse-mcp",
    "description": "Production MCP server for Postgres, Oracle, Snowflake, BigQuery, Redshift, DuckDB, MotherDuck.",
    "repository": {
      "url": "https://github.com/kalehdoo/warehouse-mcp",
      "source": "github"
    },
    "version": "0.4.2",
    "websiteUrl": "https://github.com/kalehdoo/warehouse-mcp",
    "packages": [
      {
        "registryType": "npm",
        "identifier": "warehouse-mcp",
        "version": "0.4.2",
        "transport": {
          "type": "stdio"
        },
        "runtimeArguments": [
          {
            "description": "Boots the MCP server. Use 'init' for interactive setup or 'doctor' to diagnose configuration.",
            "isRequired": true,
            "value": "start",
            "type": "positional"
          }
        ],
        "environmentVariables": [
          {
            "description": "Set to 'stdio' for desktop AI clients (Claude Desktop, Cursor). Defaults to 'http'.",
            "default": "stdio",
            "name": "MCP_TRANSPORT"
          },
          {
            "description": "Which warehouse to connect to. One of: postgres, oracle, redshift, snowflake, bigquery, duckdb. (DuckDB also handles MotherDuck via DUCKDB_PATH=md:<db>.)",
            "isRequired": true,
            "format": "string",
            "choices": [
              "postgres",
              "oracle",
              "redshift",
              "snowflake",
              "bigquery",
              "duckdb"
            ],
            "name": "WAREHOUSE_TYPE"
          },
          {
            "description": "Comma-separated bearer keys with role and optional warehouse-role impersonation: 'key1:reader,key2:admin', 'key3:reader:set_role=alice'. Leave empty for stdio (OS process boundary is the trust boundary). Required for HTTP.",
            "format": "string",
            "isSecret": true,
            "name": "MCP_API_KEYS"
          },
          {
            "description": "DuckDB file path, ':memory:', or 'md:<database>' for MotherDuck. Required when WAREHOUSE_TYPE=duckdb.",
            "format": "string",
            "name": "DUCKDB_PATH"
          },
          {
            "description": "MotherDuck service token. Required when DUCKDB_PATH starts with 'md:'.",
            "format": "string",
            "isSecret": true,
            "name": "MOTHERDUCK_TOKEN"
          },
          {
            "description": "Postgres host. Required when WAREHOUSE_TYPE=postgres. (Use REDSHIFT_HOST for Redshift.)",
            "name": "PG_HOST"
          },
          {
            "description": "Postgres database name.",
            "name": "PG_DATABASE"
          },
          {
            "description": "Postgres user.",
            "name": "PG_USER"
          },
          {
            "description": "Postgres password.",
            "isSecret": true,
            "name": "PG_PASSWORD"
          },
          {
            "description": "Oracle user. Required when WAREHOUSE_TYPE=oracle.",
            "name": "ORACLE_USER"
          },
          {
            "description": "Oracle password.",
            "isSecret": true,
            "name": "ORACLE_PASSWORD"
          },
          {
            "description": "Oracle Easy Connect (e.g. host:1521/SERVICE), TNS descriptor, or alias.",
            "name": "ORACLE_CONNECT_STRING"
          },
          {
            "description": "Snowflake account identifier (e.g. xy12345.us-east-1). Required when WAREHOUSE_TYPE=snowflake.",
            "name": "SNOWFLAKE_ACCOUNT"
          },
          {
            "description": "Snowflake username.",
            "name": "SNOWFLAKE_USER"
          },
          {
            "description": "Path to PKCS8 private key (.p8). Snowflake auth is key-pair only; password auth is not supported.",
            "name": "SNOWFLAKE_PRIVATE_KEY_PATH"
          },
          {
            "description": "GCP project id. Required when WAREHOUSE_TYPE=bigquery.",
            "name": "BIGQUERY_PROJECT"
          },
          {
            "description": "Path to BigQuery service-account JSON. Omit on GKE / Cloud Run with workload identity.",
            "name": "GOOGLE_APPLICATION_CREDENTIALS"
          },
          {
            "description": "Set to 'on' to enable role-aware PII masking on result rows (emails, SSNs, phones, IPs, Luhn-validated CCs). Off by default.",
            "default": "off",
            "choices": [
              "on",
              "off"
            ],
            "name": "GUARDRAIL_PII_MASK"
          },
          {
            "description": "Per-principal token-bucket rate limit on tool invocations. 0 = disabled. Recommend 60 for production.",
            "default": "0",
            "name": "MCP_RATE_LIMIT_RPM"
          }
        ]
      }
    ]
  },
  "_meta": {
    "io.modelcontextprotocol.registry/official": {
      "status": "active",
      "statusChangedAt": "2026-05-06T21:52:22.38453Z",
      "publishedAt": "2026-05-06T21:52:22.38453Z",
      "updatedAt": "2026-05-06T21:52:22.38453Z",
      "isLatest": true
    }
  }
}
Make it installable

Draft an Agent Plugin from this

An MCP server is raw capability: some tools, wired to something. An Agent Plugin is the packaging that says what job it does, what it leaves behind and where it stops. The prompt below carries this record and asks for the packaging; your own assistant writes it, and nothing here is sent anywhere.

Make it installable

Draft an Agent Plugin from warehouse-mcp

Paste it into your assistant. It asks for the manifest, the server wiring and the skills, and for an honest account of what this record does not say. Read that second file first.

217 lines · the record is inside it, so nothing else is needed
Draft an Agent Plugin (agent-plugins.org, specification 1.1.0) that wraps the
MCP server described below, so that somebody could install one thing and have
an assistant that knows when and how to use it.

An Agent Plugin is one installable unit: a `plugin.json` manifest, an
`mcp.json` that wires up the servers it needs, and a `skills/` directory
where each skill is a folder holding a `SKILL.md`. Hand back every file in
full, each under its own path, ready to save.

1. Write `plugin.json` with `$schema` exactly `https://agent-plugins.org/schemas/1.1.0/plugin.schema.json`. The name is
   1 to 64 characters of a-z, 0-9, `-` and `.`, alphanumeric at both ends, with
   no `--` and no `..` in it.

2. Write `mcp.json` wiring THIS server exactly as its record declares it. A
   remote keeps the URL and the transport type as written. A package keeps the
   registry, the identifier and the version as written. Do not invent a command,
   a port, a flag or an argument that is not in the record.

3. Every secret stays an input. No key, token, password or connection string
   belongs in either file. Declare what has to be supplied, name it, and say what
   it is for.

4. Do not invent tools. The record lists the tools it lists, and if it lists
   none then the honest plugin says the tool list was not published rather than
   guessing one from the description.

5. Skills are jobs, not tools. Write one skill per thing somebody would actually
   ask for, and inside each one say when to reach for this server, what a good
   result looks like, and what to do when it comes back empty. A skill per tool
   is a manual page with a different filename.

6. Say where it stops. Name what this plugin will not do — what it has no tool
   for, what needs a person, and what it must not be pointed at. A plugin with no
   stated edge reads as one with no edge.

7. Keep the author's own words for the description. If you would rather say it
   differently, say yours somewhere else and leave theirs where it is.

8. Record which version of the server you wrapped, and where the record came
   from, at the top of `plugin.json`'s description or in the readme. A plugin
   nobody can trace back to a version is one nobody can update.

Produce a second file alongside them, `LIMITS.md`, and treat it as the more
important of the two. The plugin is for whoever installs it. This is for
whoever has to decide whether installing it is a good idea, and that is
usually a different person who will never read the manifest.

It has three parts.

**What this is built from.** One paragraph: whose server it is, what the
record says it does, which version, and the fact that the record is all you
had. Say plainly that nobody ran it.

**What the record does not say.** One entry per gap. Whether the tool list was
published. What the server does with what it reads. What it costs. Whether it
writes anything anywhere. What credentials it will ask for and what those
credentials can reach. An unanswered question stays an unanswered question:
do not fill one in from the description or from what similar servers usually do.

**What a person has to check before trusting it.** The specific things
somebody should verify for themselves, in the order that would stop them
soonest if the answer is bad.

Write it in plain English, and do not soften it. A plugin drafted from a
directory record is a starting point to argue with, not something to install
into anything that matters.

The server record follows, exactly as the public index holds it. It is
everything I have: nobody has run this server, called a tool on it, or checked
that the address answers.

```json
{
  "server": {
    "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
    "name": "io.github.kalehdoo/warehouse-mcp",
    "description": "Production MCP server for Postgres, Oracle, Snowflake, BigQuery, Redshift, DuckDB, MotherDuck.",
    "repository": {
      "url": "https://github.com/kalehdoo/warehouse-mcp",
      "source": "github"
    },
    "version": "0.4.2",
    "websiteUrl": "https://github.com/kalehdoo/warehouse-mcp",
    "packages": [
      {
        "registryType": "npm",
        "identifier": "warehouse-mcp",
        "version": "0.4.2",
        "transport": {
          "type": "stdio"
        },
        "runtimeArguments": [
          {
            "description": "Boots the MCP server. Use 'init' for interactive setup or 'doctor' to diagnose configuration.",
            "isRequired": true,
            "value": "start",
            "type": "positional"
          }
        ],
        "environmentVariables": [
          {
            "description": "Set to 'stdio' for desktop AI clients (Claude Desktop, Cursor). Defaults to 'http'.",
            "default": "stdio",
            "name": "MCP_TRANSPORT"
          },
          {
            "description": "Which warehouse to connect to. One of: postgres, oracle, redshift, snowflake, bigquery, duckdb. (DuckDB also handles MotherDuck via DUCKDB_PATH=md:<db>.)",
            "isRequired": true,
            "format": "string",
            "choices": [
              "postgres",
              "oracle",
              "redshift",
              "snowflake",
              "bigquery",
              "duckdb"
            ],
            "name": "WAREHOUSE_TYPE"
          },
          {
            "description": "Comma-separated bearer keys with role and optional warehouse-role impersonation: 'key1:reader,key2:admin', 'key3:reader:set_role=alice'. Leave empty for stdio (OS process boundary is the trust boundary). Required for HTTP.",
            "format": "string",
            "isSecret": true,
            "name": "MCP_API_KEYS"
          },
          {
            "description": "DuckDB file path, ':memory:', or 'md:<database>' for MotherDuck. Required when WAREHOUSE_TYPE=duckdb.",
            "format": "string",
            "name": "DUCKDB_PATH"
          },
          {
            "description": "MotherDuck service token. Required when DUCKDB_PATH starts with 'md:'.",
            "format": "string",
            "isSecret": true,
            "name": "MOTHERDUCK_TOKEN"
          },
          {
            "description": "Postgres host. Required when WAREHOUSE_TYPE=postgres. (Use REDSHIFT_HOST for Redshift.)",
            "name": "PG_HOST"
          },
          {
            "description": "Postgres database name.",
            "name": "PG_DATABASE"
          },
          {
            "description": "Postgres user.",
            "name": "PG_USER"
          },
          {
            "description": "Postgres password.",
            "isSecret": true,
            "name": "PG_PASSWORD"
          },
          {
            "description": "Oracle user. Required when WAREHOUSE_TYPE=oracle.",
            "name": "ORACLE_USER"
          },
          {
            "description": "Oracle password.",
            "isSecret": true,
            "name": "ORACLE_PASSWORD"
          },
          {
            "description": "Oracle Easy Connect (e.g. host:1521/SERVICE), TNS descriptor, or alias.",
            "name": "ORACLE_CONNECT_STRING"
          },
          {
            "description": "Snowflake account identifier (e.g. xy12345.us-east-1). Required when WAREHOUSE_TYPE=snowflake.",
            "name": "SNOWFLAKE_ACCOUNT"
          },
          {
            "description": "Snowflake username.",
            "name": "SNOWFLAKE_USER"
          },
          {
            "description": "Path to PKCS8 private key (.p8). Snowflake auth is key-pair only; password auth is not supported.",
            "name": "SNOWFLAKE_PRIVATE_KEY_PATH"
          },
          {
            "description": "GCP project id. Required when WAREHOUSE_TYPE=bigquery.",
            "name": "BIGQUERY_PROJECT"
          },
          {
            "description": "Path to BigQuery service-account JSON. Omit on GKE / Cloud Run with workload identity.",
            "name": "GOOGLE_APPLICATION_CREDENTIALS"
          },
          {
            "description": "Set to 'on' to enable role-aware PII masking on result rows (emails, SSNs, phones, IPs, Luhn-validated CCs). Off by default.",
            "default": "off",
            "choices": [
              "on",
              "off"
            ],
            "name": "GUARDRAIL_PII_MASK"
          },
          {
            "description": "Per-principal token-bucket rate limit on tool invocations. 0 = disabled. Recommend 60 for production.",
            "default": "0",
            "name": "MCP_RATE_LIMIT_RPM"
          }
        ]
      }
    ]
  },
  "_meta": {
    "io.modelcontextprotocol.registry/official": {
      "status": "active",
      "statusChangedAt": "2026-05-06T21:52:22.38453Z",
      "publishedAt": "2026-05-06T21:52:22.38453Z",
      "updatedAt": "2026-05-06T21:52:22.38453Z",
      "isLatest": true
    }
  }
}
```

The server is listed as "warehouse-mcp".
What this is

MCP server

application/mcp-server-record+jsonlocal · you run it yourselfversion 0.4.2last seen 2026-08-23

These are the publisher's own words, filed by them with the official MCP registry and mirrored here. This catalog did not read them from the publisher and has not run, called or installed anything.

Where it lives

The publisher's own address

https://github.com/kalehdoo/warehouse-mcp

The address the publisher put in their registry record, printed as they wrote it. Nobody here has opened it.