github · mcp-server4d12ea104ccb

Item: mcp-server
Rating: 4
Author: MCPSafe

Scanned 5/12/2026, 9:15:50 PM·Cached result·Fast Scan·48 rules·How we decide ↗

2 of 2 findings

medium (2)

2 findings

medium (2)

LLM summary— mcp-server:4d12ea104ccb

This package earns a B grade with a safety score of 90/100, but carries two medium-severity findings related to insecure container images that could expose it to vulnerabilities if deployed in containerized environments. While no critical or high-severity issues were detected, you should review and update the container configuration before production use to mitigate the identified risks.

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

1	# Copyright 2025 SUSE LLC
2	# SPDX-License-Identifier: Apache-2.0
3
4	FROM ollama/ollama:latest
5
6	# Listen on all interfaces, port 8080
7	ENV OLLAMA_HOST 0.0.0.0:8080

1	# Copyright 2025 SUSE LLC
2	# SPDX-License-Identifier: Apache-2.0
3
4	FROM ollama/ollama:latest
5
6	# Listen on all interfaces, port 8080
7	ENV OLLAMA_HOST 0.0.0.0:8080
8
9	# Store model weight files in /models
10	ENV OLLAMA_MODELS /models
11
12	# Reduce logging verbosity
13	ENV OLLAMA_DEBUG false
14
15	# Never unload model weights from the GPU
16	ENV OLLAMA_KEEP_ALIVE -1
17
18	# Store the model weights in the container image
19	ENV MODEL qwen3:8b
20	RUN ollama serve & sleep 5 && ollama pull $MODEL
21
22	# Start Ollama
23	ENTRYPOINT ["ollama", "

1	# Copyright 2025 SUSE LLC
2	# SPDX-License-Identifier: Apache-2.0
3
4	FROM ollama/ollama:latest
5
6	# Listen on all interfaces, port 8080
7	ENV OLLAMA_HOST 0.0.0.0:8080

1	# Copyright 2025 SUSE LLC
2	# SPDX-License-Identifier: Apache-2.0
3
4	FROM ollama/ollama:latest
5
6	# Listen on all interfaces, port 8080
7	ENV OLLAMA_HOST 0.0.0.0:8080
8
9	# Store model weight files in /models
10	ENV OLLAMA_MODELS /models
11
12	# Reduce logging verbosity
13	ENV OLLAMA_DEBUG false
14
15	# Never unload model weights from the GPU
16	ENV OLLAMA_KEEP_ALIVE -1
17
18	# Store the model weights in the container image
19	ENV MODEL qwen3:8b
20	RUN ollama serve & sleep 5 && ollama pull $MODEL
21
22	# Start Ollama
23	ENTRYPOINT ["ollama", "

github · mcp-server4d12ea104ccb

medium (2)

medium (2)

LLM summary— mcp-server:4d12ea104ccb

Signal scores

LLM judge panel

CVE check

Community trust

Scan details

MCP Server Information

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

medium (2)

medium (2)

Severity breakdown