Isthmus is a local [MCP](https://modelcontextprotocol.io) server that gives AI models safe, read-only access to your PostgreSQL database. One binary
Isthmus MCP server is a locally run integration for AI assistants that speak the Model Context Protocol. Isthmus is a local MCP server that gives AI models safe, read-only access to your PostgreSQL database. One binary, runs on your machine, credentials never leave.
Once Isthmus is connected, these are the calls the assistant has available:
list_schemas — Discover available database schemaslist_tables — Tables with row counts, sizes, and descriptionsdescribe_table — Columns, types, keys, indexes, and statisticsprofile_table — Deep analysis: sample rows, disk usage, inferred relationshipsquery — Execute read-only SQL, results as JSONexplain_query — PostgreSQL execution plans with optional ANALYZEYou will need one environment variable: DATABASE_URL. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.
Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client. The configuration blocks on this page cover the common clients.
This sits in the database access group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Isthmus's toolset — list_schemas, list_tables, describe_table and 3 more — is a fair guide to whether it matches your workflow. It is maintained by guillermoballester; worth a glance at recent repository activity before you build anything load-bearing on it.
This entry was verified against Isthmus's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.
| Tool | What it does |
|---|---|
| list_schemas | Discover available database schemas |
| list_tables | Tables with row counts, sizes, and descriptions |
| describe_table | Columns, types, keys, indexes, and statistics |
| profile_table | Deep analysis: sample rows, disk usage, inferred relationships |
| query | Execute read-only SQL, results as JSON |
| explain_query | PostgreSQL execution plans with optional ANALYZE |
```json
{
"mcpServers": {
"isthmus": {
"command": "isthmus",
"env": {
"DATABASE_URL": "postgres://user:pass@localhost:5432/mydb"
}
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| DATABASE_URL | Endpoint or connection string the server talks to. | Yes |
Read-only SQL access to Postgres — let your assistant inspect schemas and answer questions from real data.
Manage your whole Supabase project in conversation — database, auth, storage, Edge Functions and branches.
Query, modify and analyse local SQLite databases in conversation — the fastest way to chat with a data file.
Metabase ships its own MCP endpoint — search your BI content, build and run queries, and save questions and dashboards without leaving the chat.
Official MongoDB server covering data, schemas and Atlas management — from find queries to spinning up clusters.
Serverless Postgres with database branching — point your assistant at Neon and let it work on disposable copies.