Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

PostgreSQL CVE & Release Intelligence

PYPI · PG-CVE-MCP · SCANNED SEP 20

PostgreSQL security for AI agents: CVEs, yanked releases, exploits, and upgrade paths

Available components

−15 this week 64 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security50
  • Malware scan not yet available for this package.Unverified
  • No known CVEs affecting this package version or its production dependencies.Pass
  • Runs setuptools.build_meta at install time, a recognised native-build step with no shell scripting around it. View diagnostics → Pass
  • 0 of 30 dependencies flagged as unhealthy. View diagnostics → Pass
Provenance & Transparency45
Schema Quality & AI Usability69
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 440 tokens (~88/item across 5 items; 5 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management87
  • Stability observed for 26 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage67
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 0% of tool parameters carry a description.Fail
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 5 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 5 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

How do I install the PostgreSQL CVE & Release Intelligence MCP server?

PostgreSQL CVE & Release Intelligence runs locally as a PyPI package, launched with uvx pg-cve-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

pypi · pg-cve-mcp

# add to Claude Code
claude mcp add meob-pg-cve-mcp -- uvx pg-cve-mcp
// .cursor/mcp.json
{
  "mcpServers": {
    "meob-pg-cve-mcp": {
      "command": "uvx",
      "args": [
        "pg-cve-mcp"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "meob-pg-cve-mcp": {
      "command": "uvx",
      "args": [
        "pg-cve-mcp"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add meob-pg-cve-mcp -- uvx pg-cve-mcp
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "meob-pg-cve-mcp": {
      "type": "local",
      "command": [
        "uvx",
        "pg-cve-mcp"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add meob-pg-cve-mcp --command uvx --arg pg-cve-mcp
# ~/.hermes/config.yaml
mcp_servers:
  meob-pg-cve-mcp:
    command: "uvx"
    args: ["pg-cve-mcp"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "meob-pg-cve-mcp": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "pg-cve-mcp"
      ]
    }
  }
}
# add to Vellum
assistant mcp add meob-pg-cve-mcp -t stdio -c uvx -a pg-cve-mcp
// mcp.json
{
  "mcpServers": {
    "meob-pg-cve-mcp": {
      "command": "uvx",
      "args": [
        "pg-cve-mcp"
      ]
    }
  }
}
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 20 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

  • 18 Sept 26 −3
    • Stability: pass → 0.80 functional
  • 17 Sept 26 −14
    • Malware scan: pass → unverified security
    • Stability: 0.97 → pass security
  • 15 Sept 26 +16
    • Malware scan: unverified → pass security
  • 14 Sept 26 −15
    • Malware scan: pass → unverified security
  • 13 Sept 26 −2
    • Stability: pass → 0.87 functional
  • 12 Sept 26 +1
    • Stability: 0.97 → pass security
    • Package version: 1.0.2 → 1.0.4 functional
  • 11 Sept 26 +15
    • Malware scan: unverified → pass security
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 20 Sept 2026 · Analysed pypi/pg-cve-mcp@1.0.4

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem pypi

Background: How many MCP packages publish verified provenance →

Install scripts 1 script
Hook Tier Command
build_backend allowlisted setuptools.build_meta

Background: Why install scripts are a supply-chain risk →

Dependencies 30 packages
Packages resolved 30
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 5 exposed · ~440 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
compare_versions ~126

Compare the CVE profiles of two PostgreSQL versions side by side. Shows CVEs fixed in v2 (present in v1 but not v2), new CVEs in v2, and CVEs still present in both, all sorted by CVSS score. Flags whether either version is yanked or end-of-life. Args: v1: First PostgreSQL version (e.g. "16.3"). v2: Second PostgreSQL version (e.g. "16.4").

NameTypeReqDescription
v1stringyes
v2stringyes

No output schema declared.

No examples provided.

get_cves ~131

Get the complete security report for a PostgreSQL version. Returns EOL and yanked status, the latest minor in the branch, summary stats (CVE count, max CVSS, exploit count) and the full list of CVEs sorted by CVSS score (highest first). For end-of-life releases a synthetic CVE-EOL-WARNING entry (CVSS 10.0) is prepended. Args: version: A PostgreSQL version string (e.g. "16.4", "15.8", "14.0").

NameTypeReqDescription
versionstringyes

No output schema declared.

No examples provided.

get_exploits ~26

List all CVEs with known public exploits, sorted by CVSS score.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

get_summary ~53

Get an overview of the tracked PostgreSQL CVE database. Returns total unique CVEs, known exploits, yanked releases (with reasons), the next major to reach EOL, and active/EOL major counts.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

get_upgrade_path ~104

Suggest the recommended upgrade target for a PostgreSQL version. Returns the latest minor in the same branch (the safe, low-effort upgrade) with the CVEs it fixes. If the branch is end-of-life or the next one to reach end-of-life, a major upgrade to a supported version is also recommended. Args: from_version: The currently installed PostgreSQL version (e.g. "16.3").

NameTypeReqDescription
from_versionstringyes

No output schema declared.

No examples provided.

Common questions

What is the PostgreSQL CVE & Release Intelligence MCP server?

PostgreSQL CVE & Release Intelligence is an MCP server listed in the public MCP registry as io.github.meob/pg-cve-mcp. PostgreSQL security for AI agents: CVEs, yanked releases, exploits, and upgrade paths. This page covers its PyPI package (pg-cve-mcp).

Is the PostgreSQL CVE & Release Intelligence MCP server safe to use?

PostgreSQL CVE & Release Intelligence scores 64 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the PostgreSQL CVE & Release Intelligence MCP server expose?

PostgreSQL CVE & Release Intelligence exposes 5 tools: get_cves, compare_versions, get_upgrade_path, get_exploits, get_summary. Their descriptions and schemas cost roughly 440 tokens of context every time the server is loaded.

Is the PostgreSQL CVE & Release Intelligence MCP server still maintained?

PostgreSQL CVE & Release Intelligence is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the PostgreSQL CVE & Release Intelligence MCP server under?

PostgreSQL CVE & Release Intelligence declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.