Skip to main content
Glama
test-intel-mcp

test-intel-mcp

test-intel-mcp

Turn JavaScript and TypeScript coverage artifacts into practical test priorities. The server reads local coverage and source files, identifies gaps, scores function complexity, and suggests focused test cases without sending code to an external service.

Tool page · npm · Listed in the official MCP Registry

test-intel-mcp analyzing real p-limit coverage

Start in one minute

Add one local server entry to any stdio-compatible MCP client:

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

Then ask the client to inspect an existing coverage file:

Use test-intel to analyze coverage/lcov.info, identify the highest-impact gaps,
and suggest tests for the most complex uncovered function.

No account, API key, or hosted service is required. File access is restricted to the directory where the server starts.

Related MCP server: Chisel

Proof on this repository

Running the complexity tool against the real src/paths.ts file produces:

Function complexity analysis for: src/paths.ts
Total functions analyzed: 1

Priority | Function        | Line | Cyclomatic | Branches | Loops
---------|-----------------|------|------------|----------|------
low      | deriveTestPaths | 11   | 3          | 1        | 1

Summary: 0 critical, 0 high, 0 medium, 1 low priority

The same server reads lcov, Istanbul JSON, and Cobertura files to surface uncovered functions, lines, and branches.

A pinned p-limit 7.3.1 case study reproduces coverage from the upstream project's 22 passing tests. test-intel-report reduces its lcov artifact to two uncovered lines and one uncovered branch while preserving the original coverage file for inspection.

If this saves you time, consider starring the repository. It helps other developers find it.

Tools

Tool

What it answers

analyze_test_coverage

Which files, functions, lines, and branches remain uncovered?

find_untested_functions

Which source functions have no corresponding test file?

get_function_complexity

Which functions deserve testing attention first?

suggest_test_cases

Which happy path, boundary, error, async, and type cases should be reviewed?

Supported coverage formats:

Format

Common producers

lcov

Jest, Vitest, nyc, Istanbul

Istanbul JSON

Jest, nyc, Istanbul

Cobertura XML

Jest, pytest-cov, JaCoCo

Heuristic source-to-test matching and complexity scores are prioritization signals. Native coverage data and human review remain the source of truth.

Coverage report command

The package also includes a non-MCP command for CI and terminal use:

npx -y -p @barissozudogru/test-intel-mcp test-intel-report coverage/lcov.info

An explicit format can be supplied when the filename is ambiguous:

test-intel-report coverage/result.xml cobertura

GitHub Action

Generate coverage with the project's own test runner, then pass the resulting artifact to the action:

name: Test priorities

on: [pull_request]

jobs:
  test-intel:
    runs-on: ubuntu-latest
    permissions:
      contents: read
    steps:
      - uses: actions/checkout@v4
      - name: Run tests with coverage
        run: npm ci && npm test -- --coverage
      - uses: barissozudogru/test-intel-mcp@v0.8.1
        with:
          coverage-path: coverage/lcov.info

The report is written to the workflow summary. The action analyzes an artifact that already exists and does not upload source or coverage data.

Client setup

Use the stdio configuration from the quickstart. Config file locations differ by client, but the server entry is the same:

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

Create .vscode/mcp.json:

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

Start the local endpoint:

npx @barissozudogru/test-intel-mcp --http

The MCP endpoint is http://localhost:3000/mcp and the health endpoint is http://localhost:3000/health. Set PORT to use another port.

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

Connect an HTTP client to http://localhost:3000/mcp.

Local development

npm install
npm test
npm run build
node dist/index.js

Requirements: Node.js 18 or newer.

See CONTRIBUTING.md for the development workflow.

Security and limits

  • Analysis runs locally and does not require network access.

  • Paths outside the server's starting directory are rejected.

  • Function discovery, source-to-test matching, and complexity scoring are heuristic.

  • A missing matching test filename does not prove a function is behaviorally untested.

License

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.

Inputs: coverage_path (required), format.

find_untested_functionsFind Untested FunctionsA

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

Inputs: source_dir (required), test_dir, extensions.

get_function_complexityGet Function ComplexityA

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

Inputs: file_path (required).

suggest_test_casesSuggest Test CasesA

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

Inputs: file_path (required), function_name (required).

Tool Schema Changelog

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

Loading tool schema changelog…

    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

    ActivitySlowing
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      B
      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.
      8
      MIT
    • F
      license
      A
      quality
      D
      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
      -
    • 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.
      100 npm
      42
      MIT