Supabase
MCP server for interacting with the Supabase platform
Beschreibung vom Entwickler (englisches Original)
Read-only PostgreSQL performance diagnostics: slow queries, EXPLAIN, index advice, locks, functions
Diese drei werden nie zu einer Punktzahl zusammengefasst: Meinungen, Messungen und Beliebtheit sind verschiedene Dinge.
Für diesen Server haben wir noch keine Zusammenfassung in einfacher Sprache geschrieben. Unten stehen die Fakten, die wir aus der Registry gelesen haben.
Wähle die KI-App, die du nutzt, und kopiere die Einstellungen.
PGPERF_DB_URL, PGPERF_DB_USER, PGPERF_DB_PASSWORD, MCP_API_KEYAls geheim markierte Werte sind Schlüssel zu deinem Konto. Gib sie nie weiter und füge sie nie in einen Chat ein.
Du brauchst
Welche App nutzt du?
Wähle oben deine App. Wir merken sie uns, damit der Button beim nächsten Mal „In … installieren“ anzeigt.
Öffne Claude Desktop → Settings → Developer → Edit Config und füge dies in claude_desktop_config.json ein
{
"mcpServers": {
"pg-perf": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"PGPERF_DB_URL",
"-e",
"PGPERF_DB_USER",
"-e",
"PGPERF_DB_PASSWORD",
"-e",
"MCP_API_KEY",
"ghcr.io/gouranshul/pg-perf-mcp:0.1.0"
],
"env": {
"PGPERF_DB_URL": "your-value",
"PGPERF_DB_USER": "your-value",
"PGPERF_DB_PASSWORD": "your-value",
"MCP_API_KEY": "your-value"
}
}
}
}Führe das in deinem Terminal aus
claude mcp add pg-perf --env PGPERF_DB_URL=your-value --env PGPERF_DB_USER=your-value --env PGPERF_DB_PASSWORD=your-value --env MCP_API_KEY=your-value -- docker run -i --rm -e PGPERF_DB_URL -e PGPERF_DB_USER -e PGPERF_DB_PASSWORD -e MCP_API_KEY ghcr.io/gouranshul/pg-perf-mcp:0.1.0Trag die leeren Werte ein, bevor du ihn startest.
In .cursor/mcp.json in deinem Projekt oder in ~/.cursor/mcp.json einfügen
{
"mcpServers": {
"pg-perf": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"PGPERF_DB_URL",
"-e",
"PGPERF_DB_USER",
"-e",
"PGPERF_DB_PASSWORD",
"-e",
"MCP_API_KEY",
"ghcr.io/gouranshul/pg-perf-mcp:0.1.0"
],
"env": {
"PGPERF_DB_URL": "your-value",
"PGPERF_DB_USER": "your-value",
"PGPERF_DB_PASSWORD": "your-value",
"MCP_API_KEY": "your-value"
}
}
}
}Dein Browser fragt, ob er die App öffnen darf, dann zeigt die App die Einstellungen und bittet dich um Bestätigung. Schlüsselwerte bleiben leer, damit du sie selbst einträgst.
In .vscode/mcp.json in deinem Projekt einfügen
{
"servers": {
"pg-perf": {
"type": "stdio",
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"PGPERF_DB_URL",
"-e",
"PGPERF_DB_USER",
"-e",
"PGPERF_DB_PASSWORD",
"-e",
"MCP_API_KEY",
"ghcr.io/gouranshul/pg-perf-mcp:0.1.0"
],
"env": {
"PGPERF_DB_URL": "your-value",
"PGPERF_DB_USER": "your-value",
"PGPERF_DB_PASSWORD": "your-value",
"MCP_API_KEY": "your-value"
}
}
}
}Dein Browser fragt, ob er die App öffnen darf, dann zeigt die App die Einstellungen und bittet dich um Bestätigung. Schlüsselwerte bleiben leer, damit du sie selbst einträgst.
Dieser Server läuft auf deinem Computer, und ChatGPT kann sich nur mit Servern im Internet verbinden. Wähle eine andere App.
Deine Auswahl bleibt in einem Cookie auf diesem Gerät; kein Konto nötig.
Diese Einstellungen werden aus dem Registry-Eintrag des Entwicklers erzeugt. Wenn in der README etwas anderes steht, folge der README.
Läuft auf deinem Computer; die Tool-Liste erscheint nach der Installation in deiner KI-App.
Wir prüfen Informationen, die jeder sehen kann; den Code haben wir nicht gelesen. Checks, die nicht zutreffen, werden nicht mitgezählt. · Geprüft am 8. Nov. 2026
Der Registry-Name wurde mit dem GitHub-Konto gouranshul bestätigt, dem das Repo gehört
Dieses Repo haben wir noch nicht von GitHub gelesen
Dieses Repo haben wir noch nicht von GitHub gelesen
Dieser Server läuft auf deinem Computer; es gibt keinen Endpunkt im Internet
Läuft auf deinem Computer und nutzt stattdessen lokale Einstellungen
Läuft auf deinem Computer; Tool-Listen können wir nur von Endpunkten im Internet lesen
Verglichen mit allen aktiven Servern dieser Kategorie in der Registry. Sterne zählen nur, wenn dem Herausgeber das Repo gehört.
Er hat 1 von 1 zutreffenden Basischecks bestanden. Den Code haben wir nicht gelesen. Bevor du einen Schlüssel oder Token hinzufügst, sieh nach, welche Zugriffe der Server verlangt, und nutze einen Schlüssel, der nur die Berechtigungen hat, die du brauchst.
Das musst du eintragen: PGPERF_DB_URL, PGPERF_DB_USER, PGPERF_DB_PASSWORD, MCP_API_KEY
Er läuft auf deinem Computer. Deine KI-App startet ihn bei Bedarf, und die Daten laufen nicht über die Server des Entwicklers (außer der Server ruft selbst einen Onlinedienst auf).
Das GitHub-Repo wurde zuletzt – geändert, und die neueste Version (0.1.0) kam vor 28 Tagen in die Registry.
Apps, die MCP unterstützen, etwa Claude Desktop, Claude Code, Cursor und VS Code. Außerdem brauchst du Docker auf deinem Computer.
In derselben Kategorie: Supabase, MongoDB MCP Server, Elasticsearch MCP Server
Server derselben Kategorie von anderen Entwicklern, sortiert nach Sternen.
So liest du eine Karte:★ GitHub-SterneiDrei Säulen: Bewertungen · Checks · NutzungiAktualisiert = neueste Version in der Registry veröffentlichti
MCP server for interacting with the Supabase platform
MongoDB Model Context Protocol Server
MCP server for interacting with Elasticsearch
Unverändert aus dem Repo des Entwicklers übernommen. PopNx MCP hat den Inhalt weder geprüft noch empfiehlt es ihn. HTML, Bilder und Skripte wurden entfernt. Links führen von dieser Website weg.
An MCP server that lets AI assistants diagnose PostgreSQL performance problems safely: slow queries, EXPLAIN plans, index suggestions, table health and lock contention. It is read-only by design.
*A real Claude Code session against the demo shop, sped up. First it finds which database functions are slow and why. Then it explains a slow catalog query and estimates the fix with a hypothetical index. Asked to create the index, it says it can't: every tool is read-only.*
When a page is slow, developers paste a query into a chat and ask "why is this slow?". The assistant then guesses, because it cannot see the plan, the table sizes, the existing indexes or which queries actually dominate the load.
pg-perf-mcp gives the assistant real numbers from `pg_stat_statements`, `EXPLAIN` and the catalogs, through a narrow, audited, read-only interface. It cannot change data, cannot run DDL, and never creates the indexes it recommends.
A condensed, illustrative session against the demo shop (docker compose up, then ./demo/workload.sh). Exact numbers vary from run to run:
You: The shop database feels slow. What's going on?
Claude: [top_slow_queries orderBy=total_time] The top statement by total time is SELECT id, status, total, created_at FROM shop.orders WHERE customer_id = $1 ORDER BY created_at DESC (thousands of calls, the largest share of total execution time).
[explain_query sql="... WHERE customer_id = 42 ORDER BY created_at DESC"] HIGH SEQ_SCAN_ON_LARGE_TABLE Seq Scan on shop.orders reads all ~1.0M rows of shop.orders to apply filter (customer_id = 42); only a handful match.
[suggest_indexes] CREATE INDEX CONCURRENTLY idx_orders_customer_id ON shop.orders (customer_id); hypopg: the planner would use it; estimated cost drops by well over 90%. Not executed. Review it and run it yourself, ideally off-peak.
[table_health table=shop.orders] Autovacuum is disabled on shop.orders and ~20% of rows are dead. Re-enable autovacuum and VACUUM.
Prioritized actions: 1) add the index above (orders.customer_id is a foreign key with no index),
flowchart LR
A["AI assistant (Claude Code, Claude Desktop, ...)"] -- "MCP over streamable HTTP Authorization: Bearer key" --> F["API key filter (constant-time)"] F --> M["MCP tools / resources / prompt Spring AI 2.0 annotations"] M --> R["ToolRunner audit log · metrics · safe errors"] R --> G["SqlGuard PG lexer + JSqlParser"] G --> E["ReadOnlyExecutor READ ONLY tx · always rollback statement/lock timeout · row cap"] R --> AN["analysis PlanAnalyzer · IndexAdvisor (pure functions)"] E --> P[("PostgreSQL 18 role mcp_readonly pg_stat_statements · hypopg")]
| Tool | What it does | Safety notes |
|---|---|---|
top_slow_queries | Most expensive statements from pg_stat_statements: normalized text, calls, total/mean/max ms, rows, cache hit ratio, share of total time. Order by total_time, mean_time, calls or rows. | Fixed SQL; sort column chosen from an enum. Excludes the server's own statements. |
explain_query | Summarized plan: 5 costliest nodes, seq scans on large tables, 10x row misestimates, disk sorts/hash spills, nested loops with many iterations. analyze=true adds real timings. $1 placeholders get a generic plan. | SQL guard first. ANALYZE runs in a read-only transaction that is rolled back and cancelled after the timeout. |
suggest_indexes | CREATE INDEX CONCURRENTLY candidates from filtered seq scans, join keys and ORDER BY ... LIMIT, each with a reason; validated with hypothetical indexes when hypopg is installed. | Never executed. Hypothetical indexes are reset in a savepoint so they cannot leak to other calls. |
unused_indexes | Indexes with idx_scan = 0, largest first, excluding primary key, unique and constraint indexes; includes size, definition and a DROP INDEX CONCURRENTLY to review. | Nothing is dropped. Reports when stats were last reset. |
table_health | Live/dead tuples, dead ratio, last (auto)vacuum/analyze, rows changed since analyze, seq vs index scans, sizes, with plain-language warnings. | Catalog reads only. |
blocking_sessions | Blocked/blocking pairs via pg_blocking_pids, truncated query texts, wait time, lock type/mode/table, blocker state, root blockers. | Never cancels or terminates anything. |
slow_functions | User-defined functions (PL/pgSQL, SQL, ...) ranked by total, self or mean time or calls, from pg_stat_user_functions, with language and volatility. | Catalog reads only. Needs track_functions. |
explain_function | Looks inside the functions a query calls: time per function, every statement executed inside them with calls, time and its own analyzed plan, and findings such as a seq scan inside a function, a function called once per row, or a read-only function left VOLATILE. Includes the function source. | SQL guard first; runs in the same rolled-back read-only transaction as explain_query, so functions that write fail. auto_explain is switched on for that transaction only, with generic plans so no data values appear. |
Resources: pg://schema/overview (tables, row estimates, sizes, indexes) and pg://schema/{table} (columns, indexes with scan counts, foreign keys flagged when unindexed). Prompt: diagnose_slow_database, a guided workflow: slow queries, then explain, suggest indexes, table health, functions, then a prioritized summary.
EXPLAIN shows a function call as one opaque expression, and charges its time to whichever plan node evaluates it. On the demo catalog page (20 products, each calling shop.product_rating), explain_query blames the index scan on products (184 ms self time) and finds nothing else serious. explain_function on the same query, against the full demo data:
shop.product_rating plpgsql 20 calls 99% of execution time
SELECT avg(rating) FROM shop.reviews WHERE product_id = p_product_id 20 calls 175 ms 96% of execution time HIGH FUNCTION_DOMINATES_QUERY shop.product_rating takes 99% of the query's execution time HIGH FUNCTION_CALLED_PER_ROW ran 20 times for one query (9.0 ms per call) HIGH SEQ_SCAN_ON_LARGE_TABLE inside shop.product_rating: Seq Scan on shop.reviews reads all ~250k rows to apply filter (reviews.product_id = $1)
How it works (ADR 0006): the query runs once with auto_explain enabled for that transaction only, so the plan of each nested statement comes back as a notice; per-function time comes from pg_stat_xact_user_functions and per-statement calls from pg_stat_statements, both as before/after differences.
Five independent layers stand between the assistant and a write (details in ADR 0001):
SELECT. It is checked by a PostgreSQL-faithful lexer *and* JSqlParser, and both must agree. Blocks DML/DDL, multiple statements, data-modifying CTEs, SELECT INTO, FOR UPDATE/SHARE, COPY, DO, and dangerous functions (pg_sleep*, *_file, lo_*, dblink*, set_config, pg_terminate_backend, query_to_xml, ...). It fails closed.mcp_readonly has SELECT plus pg_read_all_stats/pg_monitor, with default_transaction_read_only = on and statement_timeout = 5s set on the role.readOnly=true and a read-only session default.statement_timeout/lock_timeout set locally, standard_conforming_strings forced on, always rolled back.Around those layers: a bearer API key (constant-time comparison; only /actuator/health is open), a JSON audit line per call (SQL stored as a SHA-256 hash plus an 80-character preview), error messages with no stack traces or connection details, and metrics mcp.tool.duration and mcp.guard.rejections.
Requirements: Docker. There are two ways to start:
Either way, finish with connecting your AI client.
1. Pull the image (public on GHCR, built for amd64 and arm64):
docker pull ghcr.io/gouranshul/pg-perf-mcp:0.1.0
2. Prepare the database (once). Create a read-only role like mcp_readonly (see docker/init.sql) and make sure pg_stat_statements is in shared_preload_libraries. Prefer a replica or staging database: analyze=true and explain_function execute the query. For the function tools, also enable function tracking.
3. Run it. Put the settings in a file so secrets stay out of your shell history:
cat > pg-perf.env <<'EOF'
PGPERF_DB_URL=jdbc:postgresql://host.docker.internal:5432/mydb PGPERF_DB_USER=mcp_readonly PGPERF_DB_PASSWORD= MCP_API_KEY=<32+ random characters> EOF
docker run --rm --env-file pg-perf.env -p 127.0.0.1:8080:8080 ghcr.io/gouranshul/pg-perf-mcp:0.1.0
host.docker.internal reaches a database on your machine (Docker Desktop; on Linux add --add-host=host.docker.internal:host-gateway). The MCP endpoint is now http://localhost:8080/mcp.
4. Connect your AI client: see below.
To build and test from source you also need Java 25.
git clone https://github.com/gouranshul/pg-perf-mcp && cd pg-perf-mcp
cp .env.example .env # then replace the placeholder secrets docker compose up --build # Postgres 18 + seeded demo shop (~4.5M rows) + the MCP server on :8080
Generate some slow-query statistics (optional, but makes top_slow_queries interesting):
./demo/workload.sh # 60s of deliberately bad queries via pgbench
./demo/lock-scenario.sh # holds a row lock for 2 minutes so blocking_sessions has something to show ./demo/smoke-test.sh # curl-based end-to-end check of health, auth and two tool calls
claude mcp add --transport http pg-perf http://localhost:8080/mcp --header "Authorization: Bearer $MCP_API_KEY"
In PowerShell, set the key first, or the header goes out empty and the server answers 401:
$env:MCP_API_KEY = "<your MCP_API_KEY>"
claude mcp add --transport http pg-perf http://localhost:8080/mcp --header "Authorization: Bearer $env:MCP_API_KEY"
Or install it as a Claude Code plugin. Claude Code asks for the endpoint (default http://localhost:8080/mcp) and your MCP_API_KEY, which it keeps in secure storage:
/plugin install pg-perf --marketplace gouranshul/pg-perf-mcp
On Claude Code versions before 2.1.275, add the marketplace first: `/plu
Nur der Anfang wird gezeigt; den Rest findest du im Repo