@yawlabs/postgres-mcp 0.5.2 → 0.5.4

package/CHANGELOG.md

@@ -7,6 +7,99 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [0.5.3] - 2026-05-14
+
+### Security
+- Transitive deps patched via `npm audit fix`: in-range bumps to `hono`,
+  `fast-uri`, `express-rate-limit`, and `ip-address`. All four reach us
+  only through `@modelcontextprotocol/sdk`'s HTTP-transport path, which
+  this server doesn't use (stdio only) and which esbuild tree-shakes out
+  of `dist/index.js`. Practical exposure was already nil; this clears the
+  audit noise on future `npm install` runs.
+
+### Infrastructure
+- `release.yml` smoke test now retries the `npx -y --version` call itself
+  (6 x 10s) instead of probing `npm view` once and trusting the result.
+  Registry propagation has two desynchronized CDN cache layers --
+  `npm view` (metadata) and `npx -y` (tarball) can land on different
+  edges and return inconsistent results. Observed on the v0.5.2 publish
+  (2026-05-14): `npm view` returned 0.5.2 immediately but the subsequent
+  `npx -y` got `ETARGET` and turned the Release workflow red despite a
+  successful publish. The retry now covers both layers.
+
+### Changed
+- Dev dependencies bumped via Dependabot (`@biomejs/biome`, `zod`, plus
+  transitives) -- in-range, dev-only.
+
+## [0.5.2] - 2026-05-14
+
+### Fixed
+- `pg_describe_table` now emits a `kind fetch failed, reported as "table"`
+  warning instead of silently defaulting to `"table"` when the kind query
+  fails. The other partial-failure fields already followed this pattern; the
+  `kind` field is reported at the top level so a silent default could
+  mislabel a view or materialized view as a regular table.
+- `pg_advisor` `sequence_exhaustion` divides `last_value / max_value` in
+  `numeric` rather than `float8`. BIGINT sequences past 2^53 lose precision
+  in `float8`, and the danger zone (>= threshold) is exactly where the
+  reported `pct_used` needs to stay accurate. The WHERE filter and the
+  reported value both switched.
+- `pg_explain` `hypothetical_indexes` handler defaults `using` to `"btree"`
+  defensively. The Zod schema already applies this default on the protocol
+  path, but a unit-test-style direct handler call bypasses Zod -- so a
+  missing `using` would render as `USING undefined` in the generated SQL and
+  hypopg_create_index would surface a confusing syntax error. New
+  integration regression test covers the omitted-`using` path against a real
+  HypoPG-installed database.
+
+### Changed
+- `api.ts` `getPool()` docstring spells out the env-var snapshot semantics --
+  which vars are bake-on-first-call (`DATABASE_URL`,
+  `POSTGRES_STATEMENT_TIMEOUT_MS`, `POSTGRES_CONNECTION_TIMEOUT_MS`,
+  `POSTGRES_POOL_MAX`, `POSTGRES_SSL_REJECT_UNAUTHORIZED`) and which are
+  read per-request (`POSTGRES_MAX_ROWS`, `ALLOW_WRITES`). Previously a
+  hidden assumption.
+- `api.ts` `typeNameCache` comment now explains the OID-wraparound staleness
+  bound: a `DROP TYPE` / `CREATE TYPE` in-session gets a new OID and the
+  miss-fill path picks it up; the dead entry under the old OID is wasted
+  memory, not a correctness bug.
+- `scripts/wsl-pg-setup.sh` now carries DEV/CI ONLY warnings on the PG16
+  purge and on the `0.0.0.0/0 md5` pg_hba stanza. Both are safe inside WSL
+  but lethal as a production template -- the warnings prevent silent
+  copy-paste into a real host config.
+- `release.sh` Verify step uses the same 5x5s retry loop as the CI
+  smoke test, instead of a one-shot `sleep 3 && npm view` that flaked on a
+  slow registry.
+
+### Infrastructure
+- `release.yml` concurrency group locked to the literal string
+  `release-npm` instead of an interpolated `${{ github.workflow }}` /
+  `${{ github.ref }}`. The interpolated form fragmented across different
+  tags (each ref-name got its own queue, defeating the serialization the
+  group was meant to provide) and could silently re-fragment on a workflow
+  rename. The literal key serializes all release runs into one queue.
+- `release.yml` integration build step de-duplicated -- the redundant
+  pre-publish `npm run build` was rebuilding the same artifact the
+  `prepublishOnly` hook would build moments later. Removed.
+- `release.sh` now creates annotated tags (`git tag -a`) and the workflow
+  uses `git push --follow-tags`; lightweight tags are silently skipped by
+  `--follow-tags`, which previously left `release.yml` un-triggered on
+  manual tags.
+
+## [0.5.1] - 2026-05-05
+
+### Fixed
+- Type-name lookup failures no longer drop the user's successful query
+  rows. `runReadOnly` / `runReadWrite` / `runReadWriteRollback` now route
+  catalog lookups through a `safeResolveTypeNames` wrapper that logs to
+  stderr and falls back to `{}` on a transient `pg_type` error, instead
+  of letting the catalog failure throw past the user's already-successful
+  result.
+- `release.sh` WSL matrix step uses a sed regex to translate Git Bash
+  drive prefixes (`/c/`, `/d/`, ...) into the WSL form (`/mnt/c/`,
+  `/mnt/d/`, ...). The previous hardcoded `/c/` broke contributors
+  working from any other drive.
+
 ## [0.5.0] - 2026-05-04
 
 ### Changed
@@ -229,7 +322,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
   writes executed by `EXPLAIN ANALYZE`. Previously the write ran inside a
   `BEGIN; ... COMMIT` transaction, so `pg_explain { analyze: true, sql:
   "INSERT ..." }` would actually insert the row. Now writes run inside a
-  `BEGIN; ... ROLLBACK` transaction — the plan (with real row counts and
+  `BEGIN; ... ROLLBACK` transaction - the plan (with real row counts and
   timing) comes back but the mutation is rolled back. This matches the user
   expectation when asking for a plan, and the tool description has been
   updated to reflect it.
@@ -261,7 +354,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - `pg_list_roles` with `includeSystem: false` (the default) now actually
   excludes built-in `pg_*` roles. The previous `LIKE 'pg\_%' ESCAPE '\\'`
   filter ended up as SQL `ESCAPE '\\'` (two backslashes), which Postgres
-  rejects since `ESCAPE` requires a single character — so the whole filter
+  rejects since `ESCAPE` requires a single character - so the whole filter
   was silently being dropped. Replaced with `starts_with(rolname, 'pg_')`.
 - `pg_describe_table` foreign-key `columns` and `foreign_columns` are now
   proper JSON arrays. They were previously returned as the raw postgres
@@ -285,11 +378,11 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 ## [0.3.0] - 2026-04-22
 
 ### Added
-- `pg_list_views` — list views and materialized views with SQL definitions.
-- `pg_list_functions` — list functions, procedures, and aggregates with signatures.
-- `pg_list_extensions` — list installed extensions (pgvector, postgis, etc.) with versions.
-- `pg_search_columns` — find columns by name pattern across all user schemas.
-- `pg_top_queries` — top N queries by total/mean execution time from
+- `pg_list_views` - list views and materialized views with SQL definitions.
+- `pg_list_functions` - list functions, procedures, and aggregates with signatures.
+- `pg_list_extensions` - list installed extensions (pgvector, postgis, etc.) with versions.
+- `pg_search_columns` - find columns by name pattern across all user schemas.
+- `pg_top_queries` - top N queries by total/mean execution time from
   `pg_stat_statements`. Detects extension version and picks the right column
   names (v1.8+ uses `total_exec_time`, older uses `total_time`). Returns clear
   setup instructions if the extension is not installed.
@@ -311,23 +404,23 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
   tool against a real Postgres instance. Gated on `POSTGRES_MCP_INTEGRATION=1`
   so local `npm test` stays fast with no DB required. CI runs it on Linux via
   a `postgres:16` service container with `pg_stat_statements` preloaded.
-- `pg_inspect_locks` — show current blocking locks (blocked PID, blocker PID,
+- `pg_inspect_locks` - show current blocking locks (blocked PID, blocker PID,
   relation, lock type, both queries). First tool to reach for when a session
   hangs or the app feels stuck.
-- `pg_list_roles` — database roles with login/superuser/createdb/createrole
+- `pg_list_roles` - database roles with login/superuser/createdb/createrole
   flags and inherited group memberships.
-- `pg_table_privileges` — who has SELECT/INSERT/UPDATE/DELETE/etc. on a table,
+- `pg_table_privileges` - who has SELECT/INSERT/UPDATE/DELETE/etc. on a table,
   or on all tables in a schema. Useful for pre-migration audits.
-- `pg_seq_scan_tables` — tables with heavy sequential scans relative to index
+- `pg_seq_scan_tables` - tables with heavy sequential scans relative to index
   scans. Missing-index candidates.
-- `pg_unused_indexes` — non-unique, non-primary indexes with low/zero scan
+- `pg_unused_indexes` - non-unique, non-primary indexes with low/zero scan
   counts. Drop candidates (each unused index costs write amplification).
-- `pg_kill` — cancel a running query or terminate a backend by PID. Requires
+- `pg_kill` - cancel a running query or terminate a backend by PID. Requires
   `ALLOW_WRITES=1` since it changes session state. Distinguishes `cancel`
   (SIGINT-equivalent, graceful) from `terminate` (SIGTERM, forceful).
-- `pg_table_bloat` — estimate dead tuples and vacuum-candidate tables from
+- `pg_table_bloat` - estimate dead tuples and vacuum-candidate tables from
   `pg_stat_user_tables`. No extensions required.
-- `pg_replication_status` — replication slots, connected replicas with lag,
+- `pg_replication_status` - replication slots, connected replicas with lag,
   and current WAL position. Returns empty arrays on a standalone DB rather
   than erroring, so it's safe to call unconditionally.
 - New "What can an agent do with this?" README section with concrete example
@@ -359,12 +452,12 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 Initial release.
 
 ### Added
-- `pg_query` — run SQL with read-only-by-default safety. Writes opt in via `ALLOW_WRITES=1`.
-- `pg_list_schemas` — list non-system schemas.
-- `pg_list_tables` — list tables (and optionally views) with estimated row counts.
-- `pg_describe_table` — columns, PK, FKs, indexes.
-- `pg_explain` — `EXPLAIN` / `EXPLAIN ANALYZE` with text or JSON output.
-- `pg_health` — server version, db size, connections, active queries, table count.
+- `pg_query` - run SQL with read-only-by-default safety. Writes opt in via `ALLOW_WRITES=1`.
+- `pg_list_schemas` - list non-system schemas.
+- `pg_list_tables` - list tables (and optionally views) with estimated row counts.
+- `pg_describe_table` - columns, PK, FKs, indexes.
+- `pg_explain` - `EXPLAIN` / `EXPLAIN ANALYZE` with text or JSON output.
+- `pg_health` - server version, db size, connections, active queries, table count.
 - Single-file bundled distribution (zero runtime deps) for fast `npx` cold starts.
 - Result row truncation at `POSTGRES_MAX_ROWS` (default 1000).
 - Parameterized queries via `params` on `pg_query` and `pg_explain`.

package/README.md

@@ -3,37 +3,37 @@
 [![npm version](https://img.shields.io/npm/v/@yawlabs/postgres-mcp)](https://www.npmjs.com/package/@yawlabs/postgres-mcp)
 [![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](https://opensource.org/licenses/MIT)
 
-**Query a PostgreSQL database from Claude Code, Cursor, and any MCP client.** Read-only by default — writes opt in via a single env var — so an agent can't silently drop your tables.
+**Query a PostgreSQL database from Claude Code, Cursor, and any MCP client.** Read-only by default - writes opt in via a single env var - so an agent can't silently drop your tables.
 
 Built and maintained by [Yaw Labs](https://yaw.sh).
 
 ## Backstory
 
-Anthropic's reference Postgres MCP server, `@modelcontextprotocol/server-postgres`, was [archived in May 2025](https://github.com/modelcontextprotocol/servers-archived/tree/main/src/postgres) and [marked deprecated on npm](https://www.npmjs.com/package/@modelcontextprotocol/server-postgres) in July 2025. Anthropic has not shipped a replacement. Despite the deprecation, the last published version (v0.6.2) is still pulled ~20,000 times per week — a lot of agents are pointed at an unmaintained package.
+Anthropic's reference Postgres MCP server, `@modelcontextprotocol/server-postgres`, was [archived in May 2025](https://github.com/modelcontextprotocol/servers-archived/tree/main/src/postgres) and [marked deprecated on npm](https://www.npmjs.com/package/@modelcontextprotocol/server-postgres) in July 2025. Anthropic has not shipped a replacement. Despite the deprecation, the last published version (v0.6.2) is still pulled ~20,000 times per week - a lot of agents are pointed at an unmaintained package.
 
 That unmaintained package also has a known, [publicly documented stacked-query SQL injection](https://securitylabs.datadoghq.com/articles/mcp-vulnerability-case-study-SQL-injection-in-the-postgresql-mcp-server/) (Datadog Security Labs) that bypasses its `BEGIN READ ONLY` wrapper with input like `COMMIT; DROP SCHEMA public CASCADE;`. It has never been patched at npm.
 
 A handful of community forks have appeared, but each fills a narrow slice:
 
-- [`@zeddotdev/postgres-context-server`](https://www.npmjs.com/package/@zeddotdev/postgres-context-server) — Zed's fork, primarily a security patch on the original shape.
-- **Postgres MCP Pro** (Crystal DBA) — focused on index tuning and hypothetical-index / buffer-cache diagnostics.
-- **AWS Labs Postgres MCP** — tied to Aurora / RDS Data API + Secrets Manager.
+- [`@zeddotdev/postgres-context-server`](https://www.npmjs.com/package/@zeddotdev/postgres-context-server) - Zed's fork, primarily a security patch on the original shape.
+- **Postgres MCP Pro** (Crystal DBA) - focused on index tuning and hypothetical-index / buffer-cache diagnostics.
+- **AWS Labs Postgres MCP** - tied to Aurora / RDS Data API + Secrets Manager.
 
 None of them position themselves as a general-purpose daily driver you'd hand to Claude Code or Cursor against an arbitrary Postgres: modern introspection, perf helpers, role/privilege awareness, and a write-safety posture out of the box. That's the gap `@yawlabs/postgres-mcp` fills.
 
 ## Why this one?
 
-- **Read-only by default** — user SQL runs in a `BEGIN READ ONLY` transaction, so postgres itself (not string parsing) blocks writes. Opt in with `ALLOW_WRITES=1`.
-- **Extended query protocol for all user SQL** — `pg_query` sends user input with `queryMode: 'extended'`, which restricts each request to a single statement. This closes the [stacked-query injection class](https://securitylabs.datadoghq.com/articles/mcp-vulnerability-case-study-SQL-injection-in-the-postgresql-mcp-server/) (`COMMIT; DROP SCHEMA x CASCADE;`) that defeated the reference server's `BEGIN READ ONLY` wrapper. Integration test asserts the rejection.
-- **Parameterized queries** — `pg_query` takes a `params` array for `$1`, `$2`, etc. No string-interpolated SQL in our code path.
-- **Written from scratch, actively maintained** — not a fork of the deprecated code. Unit + integration tests (`npm test`, `npm run test:integration`) run against a real Postgres; releases cut via `release.sh`.
-- **Schema introspection built in** — `pg_list_schemas`, `pg_list_tables`, `pg_describe_table` return columns, primary keys, foreign keys, and indexes without the agent having to remember `pg_catalog` joins.
-- **`EXPLAIN` as a first-class tool** — text or JSON format, with optional `ANALYZE`. ANALYZE for non-SELECT statements requires `ALLOW_WRITES=1` and always rolls back, so the plan is real but the write doesn't persist.
-- **Perf diagnostics the deprecated server never had** — `pg_top_queries` (from `pg_stat_statements`), `pg_seq_scan_tables`, `pg_unused_indexes`, `pg_table_bloat`, `pg_inspect_locks`, `pg_replication_status`. Answer "why is this slow?" in one tool call.
-- **Health snapshot** — `pg_health` returns version, db size, connection counts, and the 10 longest-running active queries in one call.
-- **Role and privilege awareness** — `pg_list_roles` and `pg_table_privileges` for the common "who can touch what?" questions.
-- **Instant startup** — ships as a single bundled file with zero runtime dependencies. No multi-minute `node_modules` install on every `npx` cold start.
-- **Result truncation** — large result sets are capped at `POSTGRES_MAX_ROWS` (default 1000) with a `truncated: true` flag, so a stray `SELECT * FROM events` doesn't blow out the model context.
+- **Read-only by default** - user SQL runs in a `BEGIN READ ONLY` transaction, so postgres itself (not string parsing) blocks writes. Opt in with `ALLOW_WRITES=1`.
+- **Extended query protocol for all user SQL** - `pg_query` sends user input with `queryMode: 'extended'`, which restricts each request to a single statement. This closes the [stacked-query injection class](https://securitylabs.datadoghq.com/articles/mcp-vulnerability-case-study-SQL-injection-in-the-postgresql-mcp-server/) (`COMMIT; DROP SCHEMA x CASCADE;`) that defeated the reference server's `BEGIN READ ONLY` wrapper. Integration test asserts the rejection.
+- **Parameterized queries** - `pg_query` takes a `params` array for `$1`, `$2`, etc. No string-interpolated SQL in our code path.
+- **Written from scratch, actively maintained** - not a fork of the deprecated code. Unit + integration tests (`npm test`, `npm run test:integration`) run against a real Postgres; releases cut via `release.sh`.
+- **Schema introspection built in** - `pg_list_schemas`, `pg_list_tables`, `pg_describe_table` return columns, primary keys, foreign keys, and indexes without the agent having to remember `pg_catalog` joins.
+- **`EXPLAIN` as a first-class tool** - text or JSON format, with optional `ANALYZE`. ANALYZE for non-SELECT statements requires `ALLOW_WRITES=1` and always rolls back, so the plan is real but the write doesn't persist.
+- **Perf diagnostics the deprecated server never had** - `pg_top_queries` (from `pg_stat_statements`), `pg_seq_scan_tables`, `pg_unused_indexes`, `pg_table_bloat`, `pg_inspect_locks`, `pg_replication_status`. Answer "why is this slow?" in one tool call.
+- **Health snapshot** - `pg_health` returns version, db size, connection counts, and the 10 longest-running active queries in one call.
+- **Role and privilege awareness** - `pg_list_roles` and `pg_table_privileges` for the common "who can touch what?" questions.
+- **Instant startup** - ships as a single bundled file with zero runtime dependencies. No multi-minute `node_modules` install on every `npx` cold start.
+- **Result truncation** - large result sets are capped at `POSTGRES_MAX_ROWS` (default 1000) with a `truncated: true` flag, so a stray `SELECT * FROM events` doesn't blow out the model context.
 
 ## Quick start
 
@@ -88,7 +88,7 @@ Read-only is the default. If you want the agent to be able to `INSERT`, `UPDATE`
 }
 ```
 
-Prefer scoping this to dev/test databases — for production, leave writes off and use migration tools out-of-band.
+Prefer scoping this to dev/test databases - for production, leave writes off and use migration tools out-of-band.
 
 ## What can an agent do with this?
 
@@ -103,7 +103,7 @@ Once connected, the agent picks tools automatically based on what you ask. A few
 
 The bigger leverage is multi-tool reasoning. A few real workflows:
 
-- **Unstick a hung app.** `pg_inspect_locks` returns blocked PID + blocking PID + the offending query, then `pg_kill` (`ALLOW_WRITES=1` required) cancels the blocker. The agent can run both in one turn — it's the fastest path from "the app is frozen" to "back up."
+- **Unstick a hung app.** `pg_inspect_locks` returns blocked PID + blocking PID + the offending query, then `pg_kill` (`ALLOW_WRITES=1` required) cancels the blocker. The agent can run both in one turn - it's the fastest path from "the app is frozen" to "back up."
 - **Chase a slow page.** `pg_top_queries` ranks the worst queries, `pg_explain` with `analyze: true` shows the plan for the top hit, `pg_seq_scan_tables` and `pg_unused_indexes` say whether the answer is "add an index here" or "drop a dead one there."
 - **Oncall triage.** `pg_health` checks connectivity + active-query count + database size; `pg_inspect_locks` and `pg_replication_status` confirm whether contention or replication lag is in play before paging the on-call DBA.
 
@@ -122,12 +122,12 @@ The bigger leverage is multi-tool reasoning. A few real workflows:
 | `pg_explain` | `EXPLAIN` or `EXPLAIN ANALYZE` for a SQL statement. Text or JSON output. Optional `hypothetical_indexes` (requires the [HypoPG](https://github.com/HypoPG/hypopg) extension) lets you ask "what would the plan be with these indexes?" without creating them on disk. |
 | `pg_health` | Server version, database size, connection count, active queries, table count. |
 | `pg_top_queries` | Top N queries by total/mean execution time. Requires the `pg_stat_statements` extension. |
-| `pg_seq_scan_tables` | Tables with heavy sequential scans — missing-index candidates. |
-| `pg_unused_indexes` | Non-unique, non-primary indexes with low scan counts — drop candidates. |
+| `pg_seq_scan_tables` | Tables with heavy sequential scans - missing-index candidates. |
+| `pg_unused_indexes` | Non-unique, non-primary indexes with low scan counts - drop candidates. |
 | `pg_inspect_locks` | Who is blocking whom right now (blocked PID, blocker PID, lock type, queries). |
 | `pg_list_roles` | Database roles with login/superuser/createdb flags and group memberships. |
 | `pg_table_privileges` | Who has SELECT/INSERT/UPDATE/DELETE/etc. on a table or whole schema. |
-| `pg_table_bloat` | Tables with high dead-tuple ratios — VACUUM candidates. |
+| `pg_table_bloat` | Tables with high dead-tuple ratios - VACUUM candidates. |
 | `pg_replication_status` | Replication slots, connected replicas, and current WAL position. |
 | `pg_advisor` | Rolled-up DBA lints in one call: sequence-exhaustion candidates, tables without a primary key, and (configurable) public tables with RLS disabled. The "what should I be looking at?" starting point. |
 | `pg_kill` | Cancel a running query or terminate a backend connection. Requires `ALLOW_WRITES=1`. |
@@ -171,19 +171,19 @@ This disables certificate chain verification only -- the TCP connection is still
 
 ## Troubleshooting
 
-**`DATABASE_URL is not set`** — Your MCP client is launching the server without the env var. On Windows especially, env vars set in bash / PowerShell profiles are not inherited by MCP servers launched via `cmd`. Put `DATABASE_URL` directly in the `env` block of `.mcp.json`.
+**`DATABASE_URL is not set`** - Your MCP client is launching the server without the env var. On Windows especially, env vars set in bash / PowerShell profiles are not inherited by MCP servers launched via `cmd`. Put `DATABASE_URL` directly in the `env` block of `.mcp.json`.
 
-**`password authentication failed`** — Check the username, password, and that the user has `CONNECT` privilege on the database. URL-encode special characters in the password (`@` → `%40`, `#` → `%23`, `/` → `%2F`).
+**`password authentication failed`** - Check the username, password, and that the user has `CONNECT` privilege on the database. URL-encode special characters in the password (`@` → `%40`, `#` → `%23`, `/` → `%2F`).
 
-**`SASL: SCRAM-SERVER-FIRST-MESSAGE: client password must be a string`** — The password in your connection string is empty or became `null` after URL decoding. Re-check your connection string.
+**`SASL: SCRAM-SERVER-FIRST-MESSAGE: client password must be a string`** - The password in your connection string is empty or became `null` after URL decoding. Re-check your connection string.
 
-**`canceling statement due to statement timeout`** — A single query exceeded `POSTGRES_STATEMENT_TIMEOUT_MS` (default 30s). Increase it, narrow the query with `WHERE`, or add an index. This is working as designed -- the timeout exists so a runaway query cannot hang the agent.
+**`canceling statement due to statement timeout`** - A single query exceeded `POSTGRES_STATEMENT_TIMEOUT_MS` (default 30s). Increase it, narrow the query with `WHERE`, or add an index. This is working as designed -- the timeout exists so a runaway query cannot hang the agent.
 
-**`Write blocked: this server is in read-only mode`** — You asked the agent to write but `ALLOW_WRITES` is not set. Add `ALLOW_WRITES=1` to the `env` block of `.mcp.json` and restart your MCP client. Only do this for dev/test DBs.
+**`Write blocked: this server is in read-only mode`** - You asked the agent to write but `ALLOW_WRITES` is not set. Add `ALLOW_WRITES=1` to the `env` block of `.mcp.json` and restart your MCP client. Only do this for dev/test DBs.
 
-**Connection pool exhaustion with PgBouncer transaction mode or pglite-socket** — These backends don't support concurrent queries on a single connection. Set `POSTGRES_POOL_MAX=1` in the env block.
+**Connection pool exhaustion with PgBouncer transaction mode or pglite-socket** - These backends don't support concurrent queries on a single connection. Set `POSTGRES_POOL_MAX=1` in the env block.
 
-**First query is slow, subsequent queries are fast** — Expected. The pg driver lazily establishes the first connection; subsequent queries reuse the pool.
+**First query is slow, subsequent queries are fast** - Expected. The pg driver lazily establishes the first connection; subsequent queries reuse the pool.
 
 ## Development