Skip to main content
Glama

npm version License: MIT Node.js

project-graph-mcp

Website and documentation

Maximize your AI agent's context window. An MCP server that lets agents read and edit your codebase in compact mode — minified source with all variable names preserved. .ctx documentation is injected only in the focus zone, so agents can start with structure and request implementation detail when needed.

Expanded view — formatted code with JSDoc, 28+ lines per function

Compact mode — the same example shown in 14 lines. Agents read and edit this directly.

TIP

19 MCP tools, zero config. Add one line to your MCP config and the server downloads itself on the next IDE restart.

Features

  • Project Skeleton — compact AST-based JSON graph of files, symbols, and relationships

  • Compact Code Mode — project-wide compact/beautify; agents read and edit minified source while names remain available for restoration

  • AI Context Layer — one call loads skeleton + docs + compressed files; progressive loading (Overview → Focus)

  • Code Quality Analysis — dead code, complexity, duplicates, large files, legacy patterns, JSDoc consistency, Health Score (0-100)

  • Multi-Language Parsers — JavaScript (AST/Acorn), TypeScript, Python, Go (regex-based)

  • Doc Dialect — auto-generated .ctx documentation with AST signatures, staleness detection, self-enriching @enrich markers

  • Database Analysis — schema extraction from SQL migrations, table usage, dead tables

  • Test Checklists — persistent test state in .ctx.md files, agent-driven mark_test_passed

  • Monorepo Support — auto-discovery of sub-projects in packages/, apps/, services/

  • Framework Rules — 11 rulesets (86 rules) for React, Vue, Next.js, Express, NestJS, TypeScript, Node.js, Symbiote.js

  • Security — path traversal protection on all operations

Related MCP server: Smart Context MCP

Quick Start

Generate the MCP config for your IDE (with correct paths):

npx -y project-graph-mcp config

Copy the output JSON into your IDE's MCP config file, then restart.

IDE

Config path

Antigravity

~/.gemini/antigravity/mcp_config.json

Gemini CLI

~/.gemini/settings.json

Cursor

.cursor/mcp.json

Windsurf

.windsurf/mcp.json

Claude Code

Run: claude mcp add project-graph npx -y project-graph-mcp

See CONFIGURATION.md for all supported IDEs.

git clone --recursive https://github.com/rnd-pro/project-graph-mcp
cd project-graph-mcp
npm install

Note: The source checkout no longer needs the former vendor/symbiote-node submodule.

CLI

npx project-graph-mcp skeleton src/       # Project skeleton
npx project-graph-mcp expand SN           # Expand minified symbol
npx project-graph-mcp deps SNG            # Get dependencies
npx project-graph-mcp deadcode src/       # Find unused code
npx project-graph-mcp complexity src/     # Cyclomatic complexity
npx project-graph-mcp analyze src/        # Full health analysis
npx project-graph-mcp compress src/f.js   # Compress file for AI
npx project-graph-mcp docs src/           # Project docs (doc-dialect)
npx project-graph-mcp generate-ctx src/   # Generate .context/ docs
npx project-graph-mcp compact src/ --dry-run  # Compact all files
npx project-graph-mcp mode .              # Show current editing mode
npx project-graph-mcp help                # All commands

Web Dashboard

NOTE

project-graph-mcp is a pure stdio MCP server — it does not include a web server. For the visual UI (file tree, code viewer, dependency graph, live monitoring, marketplace), install mcp-agent-portal: npx mcp-agent-portal.

MCP Ecosystem

Best used as part of mcp-agent-portal — a unified MCP aggregator that combines all RND-PRO servers behind a single config entry:

{
  "mcpServers": {
    "agent-portal": {
      "command": "npx",
      "args": ["-y", "mcp-agent-portal"]
    }
  }
}
TIP

The Portal runs asingleton backend to prevent resource exhaustion when you open multiple IDE windows. It transparently spawns project-graph-mcp as a public child tool server and keeps agent-pool-mcp as its internal execution runtime. One mcp-agent-portal entry replaces separate public configs for child servers.

Also works standalone when you need only project graph tools:

# Generate a config with the correct path for this server:
npx -y project-graph-mcp config
# Or use mcp-agent-portal as the unified orchestration gateway.
IMPORTANT

Agent workers launched by Agent Portal can use their ownproject-graph-mcp instance to navigate the codebase independently without blocking the primary orchestrator.

Documentation

  • mcp-agent-portal — Unified MCP aggregator + web dashboard + AI agent runtime

  • agent-pool-mcp — Internal execution runtime used by Agent Portal orchestration

  • Symbiote.js — Isomorphic Reactive Web Components framework

  • JSDA-Kit — SSG/SSR toolkit for modern web applications

License

MIT © RND-PRO.com


Made with ❤️ by the RND-PRO team

Available Tools

19 tools
analyzeC

Code quality analysis. Actions: dead_code|similar_functions|complexity|large_files|outdated_patterns|full_analysis|analysis_summary|undocumented

Inputs: path (required), action (required), level, codeOnly, +5 more.

check_custom_rulesB

Run custom rules analysis on a directory. Returns violations found.

Inputs: path (required), ruleSet, severity.

compactD

Compact code operations. Actions: compact_file|edit|compact_all|beautify|expand_file|expand_project|validate_pipeline|get_mode|set_mode

Inputs: action (required), fix, code, mode, +8 more.

dbC

Database analysis. Actions: schema|table_usage|dead_tables

Inputs: path (required), action (required), table.

docsC

Documentation (.ctx) management. Actions: get|generate|check_stale|validate_contracts

Inputs: path (required), action (required), file, scope, +2 more.

filtersC

Filter configuration. Actions: get|set|add_excludes|remove_excludes|reset

Inputs: action (required), dirs, excludeDirs, useGitignore, +2 more.

get_agent_instructionsA

Get coding guidelines, architectural standards, and JSDoc rules for this project.

Inputs: no named parameters.

get_ai_contextA

Boot AI agent context. Two modes:

  1. Default: returns skeleton + docs (2-3k tokens) for structure overview.

  2. includeFiles: ['']: returns ALL compressed source code without skeleton/docs (pure code dump). Filters vendored files via .contextignore (auto-created on first call). Call FIRST when starting work. Use [''] for small/medium projects that fit in context.

Inputs: path (required), includeDocs, includeFiles, includeSkeleton.

get_custom_rulesA

List all custom code analysis rules. Rules are stored in JSON files in rules/ directory.

Inputs: no named parameters.

get_focus_zoneB

Get enriched context for recently modified files. Auto-detects from git or accepts explicit file list.

Inputs: path, useGitDiff, recentFiles.

get_framework_referenceA

Get framework-specific AI reference documentation. Auto-detects framework from project or accepts explicit name. Returns full API reference, patterns, and common mistakes as agent context.

Inputs: path, framework.

get_skeletonA

Get compact minified project overview (10-50x smaller than source). Returns legend, stats, node summaries, file imports, and W web component summaries when present.

Inputs: path (required).

get_usage_guideA

Get the comprehensive usage guide for project-graph with examples and best practices. Call this FIRST when planning how to analyze, navigate, or audit a codebase. Returns practical examples and recommended workflow for each feature area.

Available topics: navigation, analysis, testing, documentation, rules, workflow. Omit topic to get the full guide.

Inputs: topic.

graph_metadataC

Read and validate project-local graph metadata sidecar. Actions: get|validate

Inputs: path (required), action (required), metadata.

invalidate_cacheA

Invalidate the cached graph. Use after making code changes.

Inputs: no named parameters.

jsdocC

JSDoc operations. Actions: check_consistency|check_types|generate

Inputs: path (required), action (required), name, files, +1 more.

set_custom_ruleA

Add or update a custom code analysis rule. Creates ruleset if it does not exist.

Inputs: rule (required), ruleSet (required).

testingC

Test checklist management. Actions: pending|pass|fail|summary|reset

Inputs: action (required), path, reason, testId.

Tool Schema Changelog

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

Loading tool schema changelog…

    TDQS

    B3.2/5.0

    Scored across 19 tools

    Disambiguation5/5

    Each tool targets a distinct functional area: context provision, navigation, analysis, documentation, custom rules, testing, and caching. Even similar tools like get_skeleton and get_ai_context have clearly differentiated purposes (skeleton-only vs. full context), eliminating ambiguity.

    Naming Consistency3/5

    Tool names mix single-word domain identifiers (docs, compact, db, jsdoc, navigate, analyze, testing, filters) with snake_case verb phrases (get_focus_zone, invalidate_cache, set_custom_rule). While descriptive, the lack of a uniform verb_noun or noun_verb pattern across all tools makes naming slightly inconsistent.

    Tool Count4/5

    The 19 tools are slightly above the ideal 3-15 range, but the server's broad scope (code graph navigation, analysis, documentation, testing, custom rules, AI context) justifies the count. Each tool serves a clear purpose, and no tool feels redundant.

    Completeness5/5

    The tool set provides comprehensive coverage of codebase analysis and AI assistance: navigation, quality analysis, test tracking, documentation management, custom rules, and context generation. Minor gaps like a missing delete_custom_rule are workable and do not create dead ends.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      B
      maintenance
      Enables AI coding agents to reduce token usage by condensing source code into AST skeletons, extracting specific symbols, compressing logs, and estimating token budgets.
      4
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables AI coding agents to quickly find relevant code, focus reads on important parts of large files, and pick relevant items from long lists, reducing token usage and search time.
      7
      MIT