Security + bug + perf + refactor audit for Python. Returns 0-10 score + MD report.
Scored across 2 tools
The two tools have clearly distinct purposes: python_code_review provides a full structured report, while python_quality_score returns only a score and rating. There is no overlap or ambiguity.
Both tool names use a consistent snake_case style with the `python_` prefix, and follow a verb_noun or [action]_[result] pattern (code_review, quality_score). The naming is predictable and uniform.
With only two tools, the server feels slightly thin for a code review domain. While the tools cover core needs, a typical server of this scope would benefit from 3-5 tools (e.g., separate linting or style checks). The count is borderline but not overly minimal.
The server covers a full review and a quick score, but lacks specialized tools for specific checks (e.g., security-only, formatting) or batch processing. The depth parameter in the review tool partially compensates, but the overall surface is limited to two operations, leaving some gaps in flexibility.
Review Python code and output a structured report: security vulnerabilities, bug detection, performance optimization suggestions, code standards, and refactoring advice.
Args:
code: The Python code to review
depth: Review depth (quick/standard/deep)
| Name | Required | Description | Default |
|---|---|---|---|
| code | Yes | ||
| depth | No | standard |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses the output categories but fails to mention behavioral traits such as expected execution time for different depths, whether it is a read-only operation, or if any external calls are made. For a tool that could be expensive (deep review), this is a gap.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise—two sentences plus an argument list. It front-loads the tool's purpose and output categories. The argument section is efficient but adds needed detail since the schema lacks descriptions. No wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (code review) and the presence of an output schema, the description does not need to detail return values. However, it omits details like output format (JSON, markdown), behavior on invalid code, and any limitations. Compared to the sibling, it lacks context for choosing between tools.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must compensate. It explains 'code' as 'The Python code to review' and 'depth' as 'Review depth (quick/standard/deep)', which adds value over the raw schema. However, it does not specify the expected format of the code string (e.g., snippet, file path) or elaborate on what 'quick/standard/deep' entails.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states the tool reviews Python code and produces a structured report covering security, bugs, performance, standards, and refactoring. The verb and resource are specific, and the sibling tool python_quality_score implies a different scope, but explicit differentiation is absent.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives like python_quality_score, nor any conditions such as code size limits or required dependencies. The description simply states what it does without contextual usage advice.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Return only the code quality score and brief rating, without a full report.
Args:
code: The Python code to score
| Name | Required | Description | Default |
|---|---|---|---|
| code | Yes |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It states the output is a 'score and brief rating' but does not detail what the rating categories are, whether the tool is read-only, or any error behaviors. This is adequate but lacks depth.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise, consisting of a single sentence plus an Args section. It is front-loaded with the core purpose. However, it could be slightly more structured, e.g., by separating behavioral notes from parameter docs.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has 1 parameter, no annotations, an output schema (though not detailed in context), and a sibling 'python_code_review', the description is minimally complete: it states what it returns and what the parameter is. However, it lacks guidance on output format/range and when to use the sibling.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0%, so the description must compensate. It describes the 'code' parameter as 'The Python code to score', which adds slight context beyond the schema's type definition but does not explain expected format, size limits, or encoding. The baseline for 0% coverage and 1 param is 4, but the added value is minimal, so 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool returns 'the code quality score and brief rating' for a given Python code input. The verb 'Return' and resource 'code quality score' are specific, and the tool distinguishes itself from the sibling 'python_code_review' by omitting a full report.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implicitly suggests this tool is for obtaining a quick score without a full report, which contrasts with typical code review tools. However, it does not explicitly say when to use this versus the sibling 'python_code_review', nor does it provide any exclusions or prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
python_code_reviewpython_quality_scoreAudit and repair any public GitHub repo. Free survey; paid source, unified diffs and a pull request.
Audit GitHub repos for malicious and supply-chain code before you depend on them.
Scan code for quantum-vulnerable cryptography and get NIST post-quantum migration guidance.
Risk-scan a diff, flag AI-generated-code tells, find secrets. 5 of 7 tools need no account.
Add one secure layer between your agents and this server.