Mostly safe — a couple of notes worth reading.
Scanned 5/3/2026, 6:48:33 PM·Cached result·Fast Scan·45 rules·How we decide ↗
AIVSS Score
Low
Severity Breakdown
0
critical
0
high
19
medium
0
low
MCP Server Information
Findings
This package receives a B grade with a safety score of 68/100 and scores 2.2/10 on the AIVSS scale, indicating moderate security concerns. All 19 identified findings are medium-severity server configuration issues, which suggests the package lacks hardening in areas like input validation, error handling, or secure defaults that could be exploited if not properly deployed. While no critical or high-severity vulnerabilities were detected, you should review the configuration recommendations before using this in production.
No known CVEs found for this package or its dependencies.
Scan Details
Want deeper analysis?
Fast scan found 19 findings using rule-based analysis. Upgrade for LLM consensus across 5 judges, AI-generated remediation, and cross-file taint analysis.
Building your own MCP server?
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.
19 of 19 findings
19 findings
Service binds to 0.0.0.0 — all network interfaces. For MCP servers that only need to talk to a single parent process, bind to 127.0.0.1 (or a Unix domain socket) instead.
Evidence
| 633 | if __name__ == "__main__": |
| 634 | import uvicorn |
| 635 | |
| 636 | uvicorn.run(app, host="0.0.0.0", port=8000) # noqa: S104 |
Remediation
Bind to 127.0.0.1 for local-only access. If cross-host access is truly required, put the service behind an authenticated reverse proxy rather than exposing it on 0.0.0.0.
Service binds to 0.0.0.0 — all network interfaces. For MCP servers that only need to talk to a single parent process, bind to 127.0.0.1 (or a Unix domain socket) instead.
Evidence
| 26 | echo "📚 API documentation available at http://localhost:8000/docs" |
| 27 | echo "🔍 ReDoc documentation available at http://localhost:8000/redoc" |
| 28 | |
| 29 | python -m uvicorn ddgs.api_server:fastapi_app --host 0.0.0.0 --port 8000 |
Remediation
Bind to 127.0.0.1 for local-only access. If cross-host access is truly required, put the service behind an authenticated reverse proxy rather than exposing it on 0.0.0.0.
Service binds to 0.0.0.0 — all network interfaces. For MCP servers that only need to talk to a single parent process, bind to 127.0.0.1 (or a Unix domain socket) instead.
Evidence
| 31 | USER app |
| 32 | |
| 33 | # Run the application using uvicorn |
| 34 | CMD ["python", "-m", "uvicorn", "ddgs.api_server:fastapi_app", "--host", "0.0.0.0", "--port", "8000"] |
Remediation
Bind to 127.0.0.1 for local-only access. If cross-host access is truly required, put the service behind an authenticated reverse proxy rather than exposing it on 0.0.0.0.
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
| 50 | title: str = "" |
| 51 | image: str = "" |
| 52 | thumbnail: str = "" |
| 53 | url: str = "" |
| 54 | height: str = "" |
| 55 | width: str = "" |
| 56 | source: 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
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
| 63 | date: str = "" |
| 64 | title: str = "" |
| 65 | body: str = "" |
| 66 | url: str = "" |
| 67 | image: str = "" |
| 68 | source: 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
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
| 78 | class NewsSearchRequest(BaseModel): |
| 79 | """Request model for search operations.""" |
| 80 | |
| 81 | query: str = Field(..., description="Search query") |
| 82 | region: str = Field("us-en", description="Region for search (e.g., us-en, uk-en, ru-ru)") |
| 83 | safesearch: str = Field("moderate", description="Safe search setting (on, moderate, off)") |
| 84 | timelimit: str | None = Field(None, description="Time limit (d, w, m, y) or custom date range") |
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
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
| 24 | @dataclass |
| 25 | class CachedResult: |
| 26 | """Cached search result stored in the network.""" |
| 27 | |
| 28 | query_hash: str |
| 29 | query: str |
| 30 | results: list[dict[str, Any]] |
| 31 | timestamp: float |
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
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
| 456 | class CacheRequest(BaseModel): |
| 457 | """Request model for cache operations.""" |
| 458 | |
| 459 | query: str = Field(..., description="Search query") |
| 460 | results: list[dict[str, Any]] = Field(..., description="Search results to cache") |
| 461 | category: str = Field("text", description="Search category") |
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
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
| 114 | class ExtractRequest(BaseModel): |
| 115 | """Request model for URL content extraction.""" |
| 116 | |
| 117 | url: str = Field(..., description="URL to extract content from") |
| 118 | format: str = Field("text_markdown", description="Format: text_markdown, text_plain, text_rich, text, content") |
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
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
| 26 | """Cached search result stored in the network.""" |
| 27 | |
| 28 | query_hash: str |
| 29 | query: str |
| 30 | results: list[dict[str, Any]] |
| 31 | timestamp: float |
| 32 | ttl: int = 14400 |
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
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
| 95 | author: str = "" |
| 96 | publisher: str = "" |
| 97 | info: str = "" |
| 98 | url: str = "" |
| 99 | thumbnail: 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
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
| 56 | class ImagesSearchRequest(BaseModel): |
| 57 | """Request model for image search operations.""" |
| 58 | |
| 59 | query: str = Field(..., description="Image search query") |
| 60 | region: str = Field("us-en", description="Region for search (e.g., us-en, uk-en, ru-ru)") |
| 61 | safesearch: str = Field("moderate", description="Safe search setting (on, moderate, off)") |
| 62 | timelimit: str | None = Field(None, description="Time limit (d, w, m, y) or custom date range") |
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
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
| 105 | class BooksSearchRequest(BaseModel): |
| 106 | """Request model for book search operations.""" |
| 107 | |
| 108 | query: str = Field(..., description="Books search query") |
| 109 | max_results: int | None = Field(10, description="Maximum number of results to return") |
| 110 | page: int = Field(1, description="Page number of results") |
| 111 | backend: str = Field("auto", description="Search backend (auto, or specific engine)") |
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
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
| 44 | # Pydantic models for request/response |
| 45 | class TextSearchRequest(BaseModel): |
| 46 | """Request model for search operations.""" |
| 47 | |
| 48 | query: str = Field(..., description="Search query") |
| 49 | region: str = Field("us-en", description="Region for search (e.g., us-en, uk-en, ru-ru)") |
| 50 | safesearch: str = Field("moderate", description="Safe search setting (on, moderate, off)") |
| 51 | timelimit: str | None = Field(None, description="Time limit (d, w, m, y) or custom date range") |
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
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
| 90 | class VideosSearchRequest(BaseModel): |
| 91 | """Request model for video search operations.""" |
| 92 | |
| 93 | query: str = Field(..., description="Video search query") |
| 94 | region: str = Field("us-en", description="Region for search (e.g., us-en, uk-en, ru-ru)") |
| 95 | safesearch: str = Field("moderate", description="Safe search setting (on, moderate, off)") |
| 96 | timelimit: str | None = Field(None, description="Time limit (d, w, m) or custom date range") |
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
GitHub Actions `uses:` reference is not pinned to a 40-character commit SHA. Tags (`@v4`) and branches (`@main`) are mutable — a compromised maintainer or a tag rewrite can substitute malicious code into your CI pipeline silently. Pin to a SHA: `uses: actions/checkout@8e5e7e5ab8b370d6c329ec480221332ada57f0ab`. For readability, include the version as a trailing comment: `# v4.1.1`. Tools like `pinact` / `ratchet` automate this. Allowed unpinned forms (excluded by the rule): - Local actions `.
Evidence
| 22 | os: [ubuntu-latest, macos-latest, windows-latest] |
| 23 | |
| 24 | steps: |
| 25 | - uses: actions/checkout@v5 |
| 26 | - name: Set up Python ${{ matrix.python-version }} |
| 27 | uses: actions/setup-python@v6 |
| 28 | with: |
Remediation
Pin every `uses:` to a 40-character commit SHA. Trailing comment with the version helps reviewers: `uses: actions/checkout@8e5e7e5ab8b370d6c329ec480221332ada57f0ab # v4.1.1` Automate the migration with `pinact` (https://github.com/suzuki-shunsuke/pinact) or `ratchet` (https://github.com/sethvargo/ratchet). Add a `pinact run --check` pre-commit hook so future PRs stay pinned. Re-pin when the action releases a new version — Dependabot can do this automatically with `version-update-strategy: inc
GitHub Actions `uses:` reference is not pinned to a 40-character commit SHA. Tags (`@v4`) and branches (`@main`) are mutable — a compromised maintainer or a tag rewrite can substitute malicious code into your CI pipeline silently. Pin to a SHA: `uses: actions/checkout@8e5e7e5ab8b370d6c329ec480221332ada57f0ab`. For readability, include the version as a trailing comment: `# v4.1.1`. Tools like `pinact` / `ratchet` automate this. Allowed unpinned forms (excluded by the rule): - Local actions `.
Evidence
| 16 | steps: |
| 17 | - uses: actions/checkout@v5 |
| 18 | - name: Set up Python |
| 19 | uses: actions/setup-python@v6 |
| 20 | with: |
| 21 | python-version: '3.x' |
| 22 | - name: Install dependencies |
Remediation
Pin every `uses:` to a 40-character commit SHA. Trailing comment with the version helps reviewers: `uses: actions/checkout@8e5e7e5ab8b370d6c329ec480221332ada57f0ab # v4.1.1` Automate the migration with `pinact` (https://github.com/suzuki-shunsuke/pinact) or `ratchet` (https://github.com/sethvargo/ratchet). Add a `pinact run --check` pre-commit hook so future PRs stay pinned. Re-pin when the action releases a new version — Dependabot can do this automatically with `version-update-strategy: inc
GitHub Actions `uses:` reference is not pinned to a 40-character commit SHA. Tags (`@v4`) and branches (`@main`) are mutable — a compromised maintainer or a tag rewrite can substitute malicious code into your CI pipeline silently. Pin to a SHA: `uses: actions/checkout@8e5e7e5ab8b370d6c329ec480221332ada57f0ab`. For readability, include the version as a trailing comment: `# v4.1.1`. Tools like `pinact` / `ratchet` automate this. Allowed unpinned forms (excluded by the rule): - Local actions `.
Evidence
| 24 | steps: |
| 25 | - uses: actions/checkout@v5 |
| 26 | - name: Set up Python ${{ matrix.python-version }} |
| 27 | uses: actions/setup-python@v6 |
| 28 | with: |
| 29 | python-version: ${{ matrix.python-version }} |
| 30 | - name: Install system dependencies (macOS) |
Remediation
Pin every `uses:` to a 40-character commit SHA. Trailing comment with the version helps reviewers: `uses: actions/checkout@8e5e7e5ab8b370d6c329ec480221332ada57f0ab # v4.1.1` Automate the migration with `pinact` (https://github.com/suzuki-shunsuke/pinact) or `ratchet` (https://github.com/sethvargo/ratchet). Add a `pinact run --check` pre-commit hook so future PRs stay pinned. Re-pin when the action releases a new version — Dependabot can do this automatically with `version-update-strategy: inc
GitHub Actions `uses:` reference is not pinned to a 40-character commit SHA. Tags (`@v4`) and branches (`@main`) are mutable — a compromised maintainer or a tag rewrite can substitute malicious code into your CI pipeline silently. Pin to a SHA: `uses: actions/checkout@8e5e7e5ab8b370d6c329ec480221332ada57f0ab`. For readability, include the version as a trailing comment: `# v4.1.1`. Tools like `pinact` / `ratchet` automate this. Allowed unpinned forms (excluded by the rule): - Local actions `.
Evidence
| 14 | runs-on: ubuntu-latest |
| 15 | |
| 16 | steps: |
| 17 | - uses: actions/checkout@v5 |
| 18 | - name: Set up Python |
| 19 | uses: actions/setup-python@v6 |
| 20 | with: |
Remediation
Pin every `uses:` to a 40-character commit SHA. Trailing comment with the version helps reviewers: `uses: actions/checkout@8e5e7e5ab8b370d6c329ec480221332ada57f0ab # v4.1.1` Automate the migration with `pinact` (https://github.com/suzuki-shunsuke/pinact) or `ratchet` (https://github.com/sethvargo/ratchet). Add a `pinact run --check` pre-commit hook so future PRs stay pinned. Re-pin when the action releases a new version — Dependabot can do this automatically with `version-update-strategy: inc