Skip to main content

MCP Server

Every AI coding agent works better with rich context.

Run a local endpoint that answers questions about your codebase with real metrics, real history, and real file paths. Your agent cites the file and the metric instead of guessing.

Start free, no license required

The Vipr CLI ships its own MCP server. It runs live analysis on demand, with no desktop app, no database, and no account. 

npm install -g @vipr/cli
vipr mcp

Point any MCP client at it: { "mcpServers": { "vipr": { "command": "vipr", "args": ["mcp"] } } }

Download the desktop app See the free CLI

Live analysis is free in the CLI. History, snapshots, branch comparison, and the AI tools come from the desktop database and are included with Vipr Desktop Pro. Both run offline and bind to 127.0.0.1.

Works with

ClaudeCodexVSCodeCursorVSCodiumAntigravityWindsurfKilo

Tools

Sixteen tools. One local endpoint.

Every tool returns structured JSON an agent can parse, rather than prose.

tools/callPOST /mcp

Request

{
  "name": "search_issues",
  "arguments": {
    "severity": "high",
    "pluginId": "react"
  }
}

Response

{
  "issues": [
    {
      "rule": "prop-drilling",
      "file": "src/UserList.tsx",
      "line": 42,
      "severity": "high"
    },
    {
      "rule": "missing-key",
      "file": "src/Feed.tsx",
      "line": 118,
      "severity": "high"
    }
  ],
  "total": 7
}

Workspace regressions Desktop Pro

Match the live workspace before comparing a branch with persisted evidence.

get_workspace_context

Verify repository identity, branch, working tree, and analysis freshness.

investigate_branch_regression

Build a bounded regression summary against an explicit, evidence-backed base.

get_evidence_details

Expand one cited finding without flooding the agent context window.

Per file Free · CLI

Hand the agent context about the file it is working on right now.

The free CLI server exposes these as vipr_analyze_file, vipr_search_issues, vipr_get_recommendations, and vipr_get_health_summary, computed live rather than read from the desktop database.

get_file_analysis

Every metric and issue for a single file. React anti-patterns, type-safety gaps, server/client boundary findings, plus complexity scores and every rule hit.

search_issues

Filter issues by severity, rule, file pattern, or analyzer.

get_recommendations

Suggested fixes ranked by payoff. Includes the file, the metric, and why it was chosen.

get_health_summary

One-shot snapshot of the repo: overall score, top-5 worst files, last-run metadata.

Analysis reference Free · CLI

Let the agent discover analyzer-owned meaning instead of guessing at a metric.

vipr_list_analyses

List the installed analysis definitions and their stable identifiers.

vipr_get_analysis_docs

Read the canonical documentation for a specific Vipr analysis.

History & trends Desktop Pro

Walk the repo across time. Find the commit that moved the number.

get_complexity_trends

Time-series of health, complexity, and issue counts across commits. Inflection points included.

compare_branches

Delta between two branches: health change, issue additions and removals, per-file diffs.

get_file_history

Per-commit change history for a file with metric snapshots at each point.

get_metrics_at_commit

Snapshot the repo at any commit and read the metrics as they were.

compare_commits

Diff metrics between two commits. Same shape as branch comparison, finer granularity.

find_regression

Walk history backward to find the commit that introduced a metric regression.

get_high_churn_files

Files changed most often, ranked by churn and complexity. Effectively a refactor queue.

Snapshots & admin Desktop Pro

Saved labels for A/B comparisons, plus a health check.

ping is the exception in this group: it answers on the free CLI server too.

list_snapshots

All saved repo snapshots, with timestamps and labels.

get_snapshot

Read a single snapshot.

compare_snapshots

Delta between any two snapshots. Useful for A/B comparisons.

ping

Health check for the MCP server itself.

AI & clarification Desktop Pro

Hand the agent a grounded explanation when it needs to disambiguate Vipr metrics.

clarify_vipr_context

Use the desktop app’s active local coding model to clarify Vipr metrics, file analysis, and snapshot context. Optionally focused on a specific file or snapshot.

One chat, every client

The same grounded assistant, everywhere.

Tool calls cite the file and metric they used. The same chat surface is available everywhere your agent runs.

Vipr ChatConnected via MCP
Why is UserList.tsx showing up in the hotspot list this week?

Let me check the current metrics for that file.

get_file_analysis(filePath: "clients/desktop/src/renderer/UserList.tsx")

The file is appearing in hotspots because its complexity has risen 32% over the last 5 commits. Two anti-patterns were introduced in that window that are compounding the cyclomatic score.

⌗clients/desktop/src/renderer/UserList.tsx:42-58
What anti-patterns?

Two patterns were flagged:

  • Prop drilling through 4 levels. Consider extracting a context or a dedicated hook.
  • Implicit any in callback signature: the onSelect handler is untyped.
Ask about your code…

Privacy

Vipr analysis stays local.

The authenticated endpoint binds to 127.0.0.1, and Vipr does not proxy or retain agent requests. A hosted agent or model provider may still receive the context you authorize under that provider's privacy terms; choose a local model when the inference itself must stay on-device.

~ viprzsh

$ lsof -iTCP -sTCP:LISTEN | grep vipr

vipr-mcp 28412 127.0.0.1:3100 (LISTEN)

$ vipr mcp status

port 3100 (bound to 127.0.0.1)

outbound connections 0

telemetry events 0

tools available 15

$ curl -s http://127.0.0.1:3100/health

{"status": "ok", "network": "localhost-only"}

$

Get started

One license. Desktop and MCP.

Install the desktop app, point your editor at the local endpoint, run your first tool call in minutes.

Download the desktop app See the Desktop app