Tracked packageView full profile for pg-aiguide

MCPSafe.io

Security pre-install checks for MCP servers.

Mostly safe — a couple of notes worth reading.

Compare to another server

github · pg-aiguideHEAD

Item: pg-aiguide
Rating: 4
Author: MCPSafe

Scanned 5/3/2026, 7:07:26 PM·Cached result·Fast Scan·45 rules·How we decide ↗

AIVSS Score

3.2/ 10

Low

Severity Breakdown

critical

high

medium

low

MCP Server Information

Packagepg-aiguide

VersionHEAD

SourceGITHUB

LicenseApache-2.0

Publishertimescale

Package age9mo

Stars1.7K

Downloads/wk—

Dependencies0

Repositoryhttps://github.com/timescale/pg-aiguide

Findings

2 of 2 findings

medium (2)

2 findings

medium (2)

AIVSS 2.3CVSS 3.5

MCP tool input schema exposes an unconstrained string/any field with a risky name (command/query/sql/code/script/url/path/expr/ eval). Any caller can pass arbitrary values, which typically widens the tool's blast radius well beyond its intent. Narrow the schema with `.enum()`, `.regex()`, `.max()`, `Literal[...]`, Pydantic `Field(max_length=..., pattern=...)`, or a JSON Schema `enum` / `pattern` / `maxLength`.

Evidence

class Page:
    id: int
    version: int
    url: str
    domain: str
    filename: str
    title: str = ""

Remediation

Shape the schema to the tool's actual intent: - Zod: chain `.enum([...])`, `.regex(/.../)`, or `.max(n)`; prefer `z.enum([...])` or `z.literal(...)` when the value set is small. - Pydantic: use `Literal["a", "b"]` or `Field(max_length=..., pattern=r"...")`. - JSON Schema: add `"enum"`, `"pattern"`, or `"maxLength"` to the property. An overbroad schema is an "overpowered tool" — the model has nothing to prevent it from calling the tool with input far beyond what the tool's prose contract

Report false positive

AIVSS 3.2CVSS 4.4

Dockerfile never sets a non-root `USER` directive, so the CMD runs as root by default. Any RCE or library-level vulnerability exploited inside this container gets full privileges (MCP Top-10 R3). Add `USER <non-root>` before CMD / ENTRYPOINT in the final stage — e.g. `USER 1000`, `USER nobody`, or `USER nonroot` on distroless.

Evidence

FROM oven/bun:1.3.5
LABEL io.modelcontextprotocol.server.name="io.github.timescale/pg-aiguide"

WORKDIR /app

COPY package.json bun.lock ./
RUN bun ci --production

COPY tsconfig.json ./
COPY src ./src
COPY skills ./skills
COPY skills.yaml ./
COPY migrations ./migrations

ENV NODE_ENV=production

CMD ["bun", "run", "src/index.ts", "http"]
EXPOSE 3001

Remediation

Create and switch to a non-root user before the CMD / ENTRYPOINT: RUN adduser --system --uid 1000 app USER 1000 Or reuse the base image's shipped non-root account (e.g. `USER nobody`, `USER nonroot` on distroless). Multi-stage builds only need the USER directive in the final stage.

Report false positive

LLM summary— pg-aiguide:HEAD

This package earns a B grade with a safety score of 89/100 but has two medium-severity issues: one related to server configuration and another involving an insecure container image. While no critical or high-severity vulnerabilities were detected, you should review and address these configuration concerns before deployment, particularly the container image security issue which could expose the server to supply chain risks.

Signal scores

Static100

Publisher identity50

Permissions100

Supply chain92

Typosquat100

Package health75

Community82

Secrets & exfil100

Injection risks92

Destructive ops100

LLM judge panel

Community trust

No community reports

Security policy: Not found
Advisories: 0

Scan details

Total findings: 2
Affected tools: 0 / 1
Scan type: Fast Scan
Rules run: 45
LLM consensus score: N/A
Scanned: 51d ago
Source: GITHUB

MCP Server Information

Source: GITHUB
Package: pg-aiguide
Version: HEAD
License: Apache-2.0
Publisher: timescale
Verified: No
Account age: 11y 7m
Added: 9 months ago
Versions: 1709
Repository: https://github.com/timescale/pg-aiguide
Ecosystem: GitHub
Stars: 1.7K
Forks: 88
Open issues: 26
Dependencies: 0

aiai-agentsai-codingclaude-code-pluginclaude-code-pluginsclaude-code-plugins-marketplaceclaude-marketplaceclaude-plugin

AIVSS Score

3.2/ 10Low

Internal score: 89/100

Severity breakdown

Scan Details

Total findings2

Affected tools0 / 1

Scanned51d ago

Scan modeFAST

SourceGITHUB

Scan IDpubfast39d529d0e0082fb1e163

Want deeper analysis?

Fast scan found 2 findings using rule-based analysis. Upgrade for LLM consensus across 5 judges, AI-generated remediation, and cross-file taint analysis.

View plans Scan another package

Building your own MCP server?

Run this exact engine on your private repo — before users see it on /scan.

Same rules, same LLM judges, same grade. Private scans stay isolated to your account and never appear in the public registry. Required for code your team hasn’t shipped yet.

See plans with Private scans How private scans stay private

2 of 2 findings

medium (2)

2 findings

medium (2)

AIVSS 2.3CVSS 3.5

Evidence

class Page:
    id: int
    version: int
    url: str
    domain: str
    filename: str
    title: str = ""

Remediation

Report false positive

AIVSS 3.2CVSS 4.4

Evidence

FROM oven/bun:1.3.5
LABEL io.modelcontextprotocol.server.name="io.github.timescale/pg-aiguide"

WORKDIR /app

COPY package.json bun.lock ./
RUN bun ci --production

COPY tsconfig.json ./
COPY src ./src
COPY skills ./skills
COPY skills.yaml ./
COPY migrations ./migrations

ENV NODE_ENV=production

CMD ["bun", "run", "src/index.ts", "http"]
EXPOSE 3001

Remediation

Report false positive

6	class Page:
7	id: int
8	version: int
9	url: str
10	domain: str
11	filename: str
12	title: str = ""

1	FROM oven/bun:1.3.5
2	LABEL io.modelcontextprotocol.server.name="io.github.timescale/pg-aiguide"
3
4	WORKDIR /app
5
6	COPY package.json bun.lock ./
7	RUN bun ci --production
8
9	COPY tsconfig.json ./
10	COPY src ./src
11	COPY skills ./skills
12	COPY skills.yaml ./
13	COPY migrations ./migrations
14
15	ENV NODE_ENV=production
16
17	CMD ["bun", "run", "src/index.ts", "http"]
18	EXPOSE 3001