Skip to main content
Glama
deenesjakoruzh
barissozudogru

test-intel-mcp

by barissozudogru
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

test-intel-mcp

TypeScript および JavaScript プロジェクト向けのテストカバレッジインテリジェンス MCP サーバーです。カバレッジレポートを解析し、未テストの関数を検出し、循環複雑度をローカルでスコアリングします。外部サービスや認証は不要です。

ツール

ツール

説明

analyze_test_coverage

lcov、istanbul JSON、または cobertura XML レポートを解析し、カバーされていないファイル、関数、行、ブランチを明らかにします

find_untested_functions

ソースディレクトリをスキャンして、対応するテストファイルがない関数を探します

get_function_complexity

関数ごとの循環複雑度を計算して、何を最初にテストすべきかを優先順位付けします

suggest_test_cases

特定の関数を分析し、カテゴリ別のテストケースの提案を生成します

Related MCP server: Chisel

セットアップ

オプション A: stdio（ローカル）

Claude Desktop

設定ファイル: ~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "test-intel": {
      "command": "npx",
      "args": ["-y", "@barissozudogru/test-intel-mcp"]
    }
  }
}

Claude Code

claude mcp add test-intel -- npx -y @barissozudogru/test-intel-mcp

Cursor

設定ファイル: ~/.cursor/mcp.json

{
  "mcpServers": {
    "test-intel": {
      "command": "npx",
      "args": ["-y", "@barissozudogru/test-intel-mcp"]
    }
  }
}

Windsurf

設定ファイル: ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "test-intel": {
      "command": "npx",
      "args": ["-y", "@barissozudogru/test-intel-mcp"]
    }
  }
}

VS Code + Copilot

設定ファイル: .vscode/mcp.json

{
  "servers": {
    "test-intel": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@barissozudogru/test-intel-mcp"]
    }
  }
}

Cline

{
  "mcpServers": {
    "test-intel": {
      "command": "npx",
      "args": ["-y", "@barissozudogru/test-intel-mcp"]
    }
  }
}

Continue.dev

設定ファイル: ~/.continue/config.yaml

mcpServers:
  - name: test-intel
    command: npx
    args:
      - -y
      - "@barissozudogru/test-intel-mcp"

Zed

設定ファイル: ~/.config/zed/settings.json

{
  "context_servers": {
    "test-intel": {
      "command": {
        "path": "npx",
        "args": ["-y", "@barissozudogru/test-intel-mcp"]
      }
    }
  }
}

JetBrains (IntelliJ, WebStorm, etc.)

{
  "mcpServers": {
    "test-intel": {
      "command": "npx",
      "args": ["-y", "@barissozudogru/test-intel-mcp"]
    }
  }
}

オプション B: HTTP（リモートクライアント）

サーバーを起動します:

npx @barissozudogru/test-intel-mcp --http
# or
PORT=3000 TRANSPORT=http npx @barissozudogru/test-intel-mcp

サーバーは http://0.0.0.0:3000/mcp で待ち受けます。ヘルスチェックは /health で利用できます。

Cursor (HTTP)

{
  "mcpServers": {
    "test-intel": {
      "url": "http://localhost:3000/mcp"
    }
  }
}

VS Code + Copilot (HTTP)

{
  "servers": {
    "test-intel": {
      "type": "http",
      "url": "http://localhost:3000/mcp"
    }
  }
}

Windsurf (HTTP)

{
  "mcpServers": {
    "test-intel": {
      "serverUrl": "http://localhost:3000/mcp"
    }
  }
}

Continue.dev (HTTP)

mcpServers:
  - name: test-intel
    url: http://localhost:3000/mcp

オプション C: Docker

docker build -t test-intel-mcp .
docker run -p 3000:3000 -v $(pwd):/project -w /project test-intel-mcp

その後、任意の HTTP クライアントが http://localhost:3000/mcp を指すように設定します。

対応カバレッジ形式

形式

拡張子

ジェネレーター

lcov

.info

Jest, Vitest, nyc, Istanbul

istanbul

.json

Jest, nyc, Istanbul

cobertura

.xml

Jest, pytest-cov, JaCoCo

format が省略された場合、形式はファイル拡張子から自動検出されます。

要件

  • Node.js >= 18

  • 認証やネットワークアクセスは不要です

  • すべてのファイル分析はローカルで実行されます

ライセンス

MIT

Available Tools

4 tools
analyze_test_coverageAnalyze Test CoverageA

Parse a coverage report (lcov, istanbul JSON, or cobertura XML) and return uncovered files, functions, lines, and branch gaps.

ParametersJSON Schema
NameRequiredDescriptionDefault
formatNoCoverage format. Auto-detected from file extension if omitted.
coverage_pathYesPath to the coverage file (lcov.info, coverage-summary.json, coverage.xml, etc.)

TDQS

A3.7/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden. It states what inputs it accepts and what it returns, but does not disclose side effects (though it's likely a read-only operation), error handling, or format auto-detection details (though that's in the schema). It adds some value by listing the output types (files, functions, lines, branch gaps) but lacks deeper behavioral context like return structure or failure modes.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, well-formed sentence that conveys the key information without fluff: what it parses, which formats, and what it returns. It is efficiently front-loaded and every word earns its place, making it highly concise and well-structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is relatively simple (2 params, one required, no output schema). The description covers the core function but omits details like error behavior, output structure, and how it handles unsupported formats. Given the absence of annotations and output schema, the description could be more complete, but it is adequate for a basic analysis tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%: both coverage_path and format have descriptions in the schema. The tool description does not add extra meaning beyond what's in the schema. Per the rubric, baseline is 3 when the schema covers all parameters, and since the description adds no additional parameter semantics, a 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool parses coverage reports in specific formats (lcov, istanbul JSON, cobertura XML) and returns uncovered files, functions, lines, and branch gaps. This specific verb+resource+output distinguishes it from sibling tools like suggest_test_cases or find_untested_functions, which focus on different aspects of test coverage.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage when a developer has a coverage report and wants to identify gaps, but it does not explicitly discuss when NOT to use it or mention alternative tools. Sibling tools like find_untested_functions might be better for per-function analysis, but this is not stated. There is clear scope but no explicit exclusions or alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

find_untested_functionsFind Untested FunctionsA

Scan source files for function/method declarations and identify those with no corresponding test file.

ParametersJSON Schema
NameRequiredDescriptionDefault
test_dirNoDirectory containing test files. Defaults to same directory as source.
extensionsNoFile extensions to include, e.g. [".ts", ".js"]. Defaults to [".ts", ".tsx", ".js", ".jsx"].
source_dirYesDirectory containing source files to scan.

TDQS

A3.5/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description bears full responsibility for behavioral disclosure. It clearly conveys a read-only scanning action, but it omits important behaviors such as how 'corresponding test file' is defined (e.g., naming convention, directory structure) and whether it actually parses code or just checks file existence. This leaves room for misinterpretation in edge cases.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, focused sentence that immediately states the action and the criterion for identification. Every word adds value, and it is front-loaded with the primary verb 'Scan.' This is a model of conciseness—no unnecessary detail or redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no annotations and no output schema, the description must convey the tool's full operational context. It states the high-level action but does not specify what qualifies as a 'corresponding test file,' nor does it describe the return format. For a tool of this simplicity, the description is adequate but leaves some operational nuances ambiguous.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% with each parameter clearly documented (source_dir, test_dir, extensions). However, the tool description itself adds no additional parameter-level context beyond what the schema provides. Per rubric, high schema coverage sets a baseline of 3, and the description does not exceed this.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's function: 'Scan source files for function/method declarations and identify those with no corresponding test file.' This uses a specific verb and resource, and it differentiates from sibling tools like suggest_test_cases (which generates tests) and analyze_test_coverage (which measures coverage), making its unique purpose distinct.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this tool versus alternatives. The description does not mention scenarios, exclusions, or point to any sibling tools for other tasks. Without this context, an agent has no explicit direction on when to select this over other test-related tools, leaving usage unclear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_function_complexityGet Function ComplexityA

Analyze a file's functions for cyclomatic complexity to prioritize which functions need tests most urgently.

ParametersJSON Schema
NameRequiredDescriptionDefault
file_pathYesPath to the source file to analyze.

TDQS

A3.7/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of disclosing behavior. It states that it analyzes cyclomatic complexity, but it does not mention whether the operation is read-only, whether it modifies anything, what the return format is, or error/edge-case behavior. The word 'Analyze' implies a read operation, but this is not explicit.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence with no filler. It states the action, the target, and the motivation efficiently.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is simple with one parameter and no output schema, but the description does not explain what the tool returns or how results are presented. The stated purpose mitigates this somewhat, but the absence of output details leaves a gap for the agent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema has 100% coverage with a single file_path parameter already described as 'Path to the source file to analyze.' The description adds the context of analyzing functions and complexity, but it does not add meaning beyond the schema's existing parameter documentation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies a specific verb ('Analyze'), a specific resource ('a file's functions'), and a specific metric ('cyclomatic complexity'), with a clear purpose ('prioritize which functions need tests most urgently'). This distinguishes it from sibling tools like analyze_test_coverage or find_untested_functions.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies when to use the tool: when you need complexity-based prioritization for testing. It does not explicitly mention alternatives or exclusions, but the stated purpose gives clear contextual guidance for selection.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

suggest_test_casesSuggest Test CasesA

Analyze a specific function and generate structured test case suggestions based on its logic, branches, and type signatures.

ParametersJSON Schema
NameRequiredDescriptionDefault
file_pathYesPath to the source file containing the function.
function_nameYesName of the function to analyze.

TDQS

A3.7/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the burden of behavioral disclosure. It implies a static analysis ('analyze') and mentions 'logic, branches, and type signatures' as inputs, but does not explicitly state that it does not modify code, does not execute the function, or what the output structure looks like beyond 'structured test case suggestions.'

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence that clearly conveys the action and output. Every part adds value, with no redundant or unnecessary words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is simple with two well-documented parameters, but there is no output schema and no annotations. The description hints at 'structured test case suggestions' but does not specify the return format, side effects, or any limitations, leaving some gaps for a complete understanding.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema already provides full descriptions for both parameters (file_path and function_name) with 100% coverage. The description does not add additional meaning or clarify parameter format, so the baseline score of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool analyzes a specific function and generates structured test case suggestions based on logic, branches, and type signatures. This distinguishes it from sibling tools like analyze_test_coverage or get_function_complexity, which focus on coverage and complexity metrics.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides context that it works on a 'specific function' and produces test case suggestions, but it does not explicitly state when to use this tool over alternatives. No exclusions or alternative tool mentions are provided, leaving some ambiguity for the agent.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 4 tool updatesv0.6.1
    • First observedanalyze_test_coverage
    • First observedfind_untested_functions
    • First observedget_function_complexity
    • First observedsuggest_test_cases
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A3.9/5.0

Scored across 4 tools

Disambiguation4/5

Each tool has a distinct focus: generating test cases, parsing coverage reports, finding untested functions, and analyzing complexity. However, find_untested_functions and get_function_complexity both aim at identifying functions that need testing, which could cause some initial confusion.

Naming Consistency5/5

All tool names follow a consistent snake_case verb_noun pattern, e.g., suggest_test_cases, analyze_test_coverage, find_untested_functions, get_function_complexity. This makes the toolset predictable and easy for an agent to navigate.

Tool Count5/5

Four tools is well-scoped for a testing intelligence server, with each tool serving a clear and non-redundant purpose. There is no bloat, and the count feels sufficient for the stated domain.

Completeness4/5

The set covers a natural workflow of testing intelligence: generating tests, assessing coverage, identifying untested functions, and prioritizing via complexity. This is a solid read-only surface, though additional tools like listing existing test files or summarizing coverage trends could round it out further.

Maintenance

ActivityActive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • Chisel

    IronAdamant
    A
    license
    Not graded
    quality
    C
    maintenance
    MCP server for test impact analysis and code intelligence. Maps tests to code and git history to determine impacted tests, risk scores, and ownership for AI coding agents.
    42 PyPI
    3
    MIT

  • coverage-mcp

    ProgrammerDream
    F
    license
    A
    quality
    C
    maintenance
    MCP server for Java branch coverage analysis using JaCoCo. Enables agent-style coverage feedback with per-test-class granularity and uncovered line identification.
    2
    -

  • test-coverage-mcp

    goldbergyoni
    A
    license
    Not graded
    quality
    D
    maintenance
    MCP server that provides instant, token-efficient test coverage data for any programming language, allowing agents to query coverage summaries and track session progress.
    54 npm
    42
    MIT