CVE-2026-126198 pgEdge Postgres MCP Server custom tools performed writes without user confirmation
Custom MCP tools in pgEdge Postgres MCP Server ran writes without user confirmation, letting models or instructions modify database data.
- Exploited in the wild
- Not known
- Login needed
- Not needed
- Attackable
- Over the internet
- Victim action needed
- A user has to click or open something
- Harmful if only installed
- No
- Needs a specific call
- No
- Fix
- None listed
What is CVE-2026-126198?
CVE-2026-126198 is a low-severity missing authorization vulnerability in pgedge-postgres-mcp, published on 12 Nov 2026. An attacker can exploit it over the internet without logging in, and only if a user opens a file or follows a link.
Official description
pgEdge Postgres MCP Server enables SQL queries against PostgreSQL databases through Model Context Protocol compatible clients. Prior to 1.1.0, the bundled clients, including the CLI and web client, decided whether to request write confirmation by checking only for the query_database tool name instead of server-published write annotations. Custom pl-do, pl-func, and writing sql tools therefore ran without confirmation on allow_writes connections, including when a model followed instructions in retrieved content. The affected control is a bundled-client warning rather than a server authorization boundary, and other MCP clients do not inherit that prompt. This issue is fixed in 1.1.0.
Weakness: CWE-357
Which versions are affected by CVE-2026-126198?
An affected version is exposed as installed. No special setting or call is needed.
How do I fix CVE-2026-126198?
No fix has been published for CVE-2026-126198 yet. Limit exposure of the affected software until one is available.
Upgrade, and check permissions on every request on the server, not only in the interface. More about Missing authorization.
Is CVE-2026-126198 being exploited?
There is no known exploitation of CVE-2026-126198 in the wild and no public exploit code.
Sources
Also known as GHSA-v44x-hxg7-5cgc.