codescene-mcp-server benchmark report
codescene-mcp-server has a benchmark score of 37/100 based on installability, startup reliability, MCP capability discovery, documentation quality, and safety signals.
Benchmark score
37
Docs score
0
Config score
0
Safety score
0
Benchmark status
| Install | unknown |
|---|---|
| Startup | unknown |
| Capability discovery | passed |
| Last tested | Jul 27, 2026 |
Installability
- npxconfidence: medium
npx @codescene/codehealth-mcp - npmconfidence: medium
npm install -g @codescene/codehealth-mcp
Capabilities
prompt
plan_code_health_refactoring
Plan a prioritized, low-risk refactoring to remediate detected Code Health issues.
prompt
review_code_health
Review Code Health and assess code quality for the current open file. The file path needs to be sent to the code_health_review MCP tool when using this prompt.
resource
configuring-codescene-mcp
Use when the user wants to view, set, or troubleshoot CodeScene MCP configuration such as access tokens, on-prem URLs, default projects, or SSL certificates.
resource
configuring-codescene-mcp manifest
File manifest for the configuring-codescene-mcp skill
resource
explaining-code-health
Use when a user asks what Code Health means, how to interpret scores, or why Code Health matters in daily development.
resource
explaining-code-health manifest
File manifest for the explaining-code-health skill
resource
guiding-refactoring-with-code-health
Use when refactoring unhealthy code and needing Code Health findings to choose small safe steps and verify improvement.
resource
guiding-refactoring-with-code-health manifest
File manifest for the guiding-refactoring-with-code-health skill
resource
installing-and-activating-codescene-mcp
Use when installing the CodeScene MCP Server binary or package, registering it in an AI assistant, or copying agent guidance files into a repository.
resource
installing-and-activating-codescene-mcp manifest
File manifest for the installing-and-activating-codescene-mcp skill
resource
making-the-business-case-for-code-health
Use when a user asks for ROI, stakeholder justification, delivery impact, or defect-risk reduction from improving Code Health in a file.
resource
making-the-business-case-for-code-health manifest
File manifest for the making-the-business-case-for-code-health skill
resource
prioritizing-technical-debt
Use when users with a CodeScene instance ask what to improve first across a project, which hotspots matter most, or how to rank refactoring candidates.
resource
prioritizing-technical-debt manifest
File manifest for the prioritizing-technical-debt skill
resource
risk-based-testing-with-code-health
Use when a user asks what to test first based on CodeScene findings, especially for high-risk hotspots or pull-request change sets.
resource
risk-based-testing-with-code-health manifest
File manifest for the risk-based-testing-with-code-health skill
resource
routing-work-with-code-ownership
Use when choosing reviewers, domain experts, or likely owners for a file or directory from CodeScene project data.
resource
routing-work-with-code-ownership manifest
File manifest for the routing-work-with-code-ownership skill
resource
safeguarding-ai-generated-code
Use when AI-generated or AI-modified changes need a Code Health gate before commit, handoff, or pull request.
resource
safeguarding-ai-generated-code manifest
File manifest for the safeguarding-ai-generated-code skill
Related pages
Frequently asked questions
What does the codescene-mcp-server benchmark score include?
It combines install status, startup status, capability discovery, documentation score, configuration score, and safety score into a 0-100 benchmark_score.
Does MCP Server Finder call codescene-mcp-server tools during discovery?
No. Capability discovery lists tools, resources, and prompts when possible, but does not invoke tools or read sensitive resources.
Why are some checks skipped?
Checks are skipped when they cannot be run safely without credentials, local configuration, or non-destructive execution guarantees.
Last updated