MCP Server that bridges LCOV coverage reports to AI agents
Analyze Coverage MCP MCP server is a locally run integration for AI assistants that speak the Model Context Protocol. MCP Server that bridges LCOV coverage reports to AI agents.
MCP server that bridges LCOV coverage reports to AI agents. It runs locally and gives agents precise, structured visibility into test coverage — which lines are hit, which branches are missed, and where to focus testing efforts.
LCOV is a standard text format for code coverage data. It records which lines, functions, and branches were executed during tests. The format is widely supported by test runners (Vitest, Jest, Istanbul, etc.) and is typically written to lcov.info. Each record describes coverage for a source file: line hits, branch hits, and function hits.
Once Analyze Coverage MCP is connected, these are the calls the assistant has available:
get_coverage_overview — Aggregated and per-file coverage stats (lines, functions, branches %). Supports filtering by directory prefix, threshold, and sort orderlist_uncovered_regions — Uncovered lines (merged into ranges) and uncovered branches for a specific fileget_annotated_source — Full source file annotated line-by-line with [COVERED], [NOT COV], or [NO DATA]. Supports start_line/end_line windowingVitest — export default defineConfig({ test: { coverage: { provider: 'v8', reporter: ['text', 'lcov'], reportsDirectory: './coverage', }, }, })Jest — The Jest tool exposed by this serverMonorepos — In monorepos, project_root is often the repo root (e.g. /repo), but LCOV paths are relative to the package root (e.g. apps/app-api). The MCP handlesSetup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client. The configuration blocks on this page cover the common clients.
All MCP tools (get_coverage_overview, list_uncovered_regions, get_annotated_source) require these parameters in every call. They identify which coverage report to load and how to resolve source file paths. | Parameter | Requirement | |-----------|-------------| | lcov_path | Must be an absolute path. The file must exist on disk. | | project_root | Must be an absolute path. In
Plenty of file and storage access servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Analyze Coverage MCP's toolset — get_coverage_overview, list_uncovered_regions, get_annotated_source and 3 more — is a fair guide to whether it matches your workflow. It is maintained by sofia-open-source; worth a glance at recent repository activity before you build anything load-bearing on it.
We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.
| Tool | What it does |
|---|---|
| get_coverage_overview | Aggregated and per-file coverage stats (lines, functions, branches %). Supports filtering by directory prefix, threshold, and sort order. |
| list_uncovered_regions | Uncovered lines (merged into ranges) and uncovered branches for a specific file. |
| get_annotated_source | Full source file annotated line-by-line with [COVERED], [NOT COV], or [NO DATA]. Supports start_line/end_line windowing. |
| Vitest | export default defineConfig({ test: { coverage: { provider: 'v8', reporter: ['text', 'lcov'], reportsDirectory: './coverage', }, }, }) |
| Jest | The Jest tool exposed by this server. |
| Monorepos | In monorepos, project_root is often the repo root (e.g. /repo), but LCOV paths are relative to the package root (e.g. apps/app-api). The MCP handles this automatically: |
{
"mcpServers": {
"analyze-coverage": {
"command": "npx",
"args": [
"-y",
"@sofia-open-source/analyze-coverage-mcp"
]
}
}
}Configuration as documented by the project. Restart the client after saving.
All MCP tools (get_coverage_overview, list_uncovered_regions, get_annotated_source) require these parameters in every call. They identify which coverage report to load and how to resolve source file paths. | Parameter | Requirement | |-----------|-------------| | lcov_path | Must be an absolute path. The file must exist on disk. | | project_root | Must be an absolute path. In
Scoped local file access — read, write, search and reorganise files in directories you explicitly allow.
Search and read your Drive — Docs, Sheets and files become context your assistant can actually use.
Query, modify and analyse local SQLite databases in conversation — the fastest way to chat with a data file.
Build a programmable telecommunications stack for connecting telephony services with the Internet via a cloud-based utility.
Chat with your second brain — search, read and write vault notes through the Local REST API.
Connects AI models to an Obsidian knowledge base for direct access and manipulation of notes and folders.