M
MCP Directory CURATED DIRECTORY
911 MCP servers indexed
中文
← Back to directory
D

DreamGraph

Community
A graph-governed architecture cognition layer for MCP-enabled software projects.
How to install ↓ Compare GitHub source repository ↗
Category
Dev Tools #147 of 438
Stars
★ 126 Popular
Transport
stdio (local process) · Streamable HTTP
Runtime
Node.js 20+
Credentials
No credential needed
License
Other / unspecified
Last commit
58FMRS · C

DreamGraph is a complex, feature-rich MCP server that provides graph-based architecture cognition. It is well-suited for growing projects requiring persistent memory and governance, but has a steep learning curve. It is recommended to test in an isolated environment and pay attention to security configuration.

Strongest · Documentation 16/20 Weakest · Reliability 8/20

Reliability
8/20
Security and permissions
8/20
Maintenance
14/20
Documentation
16/20
Setup experience
12/20
Why each score
Reliability 8/20
Evidence: The repository contains substantial TypeScript source code and standard Node.js project structure (package.json, tsconfig), indicating buildability. README explicitly states startup commands (npm run build, node dist/index.js) and has src/server and src/tools directories implying MCP server implementation. However, no CI workflow or test files were directly observed, declared tool functionality is unverified by execution, error handling and dependency specifics are opaque, limiting the score.
Security and permissions 8/20
Evidence: The repo declares a source-available license and lists 'security-scanner' topic, hinting at security features. No overt signs of malware, credential theft, or exfiltration were found. However, permission model, data boundaries, external network behavior, and confirmation mechanisms for dangerous operations are not clear from static review, and least-privilege principle cannot be confirmed. Thus a moderate score.
Maintenance 14/20
Evidence: The repository shows recent release v12.6.0 and a long version history, indicating continuous maintenance. There is a clear license and sponsor mechanism, showing ownership. However, open issues count is 0 which may be due to disabled issues or lack of public discussion, and dependency update path and security response channel are not explicitly documented, deducting points.
Documentation 16/20
Evidence: README is highly detailed covering installation, quick start, architecture, and links to documentation, with a user guide and auto-generated reference docs. Documentation quality is high, providing layered docs (guide, reference, troubleshooting). However, some parts like license terms, tool-specific parameters, and cost details require external docs not fully embedded in README, so not full marks.
Setup experience 12/20
Evidence: Clear installation scripts for Windows and Linux/macOS are provided, along with step-by-step CLI commands, indicating a clear install path. However, no specific configuration examples for mainstream MCP clients (e.g., Claude Desktop, Cursor) are given, and requires Node.js 20+ and additional components, making setup non-trivial. Static review lacks execution evidence but install scripts provide consistency clues, so setup score capped below 15.

Static review · not runListed 2026-08-07

Read the FMRS scoring method →

Fit and risk

What it can accessReads local filesWrites / deletes local filesRuns commands or codeConnects to a database

Best for

  • Developers whose codebases have grown beyond short-term memory, seeking AI that understands the system and explains changes.
  • Architects, system engineers, and product builders needing an architecture intelligence layer.
  • Projects using MCP clients like Claude Desktop or VS Code that benefit from persistent graph memory.

Not for

  • Users seeking a lightweight chat assistant rather than a complex knowledge graph system.
  • Projects preferring simple tooling without persistent state or architecture governance.
  • Environments without Node.js 20+ or a compatible shell.

Required permissions

  • Read project files to build the knowledge graph (scan, enrich).
  • Read and write instance configuration and database (SQLite by default, optional PostgreSQL).
  • Execute `dg` CLI commands to manage daemon lifecycle.
  • VS Code extension permissions: file access, editor integration, daemon connection.
  • Potential network access (via HTTP daemon) and LLM API or local model server connections.

Risks and side effects

  • Cognitive outputs are advisory until backed by governed evidence or explicit review; expired or rejected ideas remain inspectable but not authoritative.
  • Ensure instance configuration is secured, especially when using HTTP transport; do not expose the daemon on untrusted networks.
  • Plugins (when enabled) must be trusted; untrusted plugins may pose risks, but mechanisms for gating and trust banners exist.
  • Backup data before major upgrades, as migration scripts may be needed for older versions (e.g., pre-v8.2.6).

Setup

Before you start

Runtime：Node.js 20+

DATABASE_URL optionalsecret Database connection string (e.g. PostgreSQL) enabling Datastore-as-Hub live schema introspection via scan_database; the feature is inert if unset.
Other optional settings (1)
DG_ALLOW_INPROCESS_PLUGINS optional Set to true to enable the in-process plugin runtime; also requires per-plugin trusted: true in instance..

To install from source:

  1. Clone the repository: git clone https://github.com/mmethodz/dreamgraph.git
  2. Change directory: cd dreamgraph
  3. Run the installer script:
  • Windows PowerShell: ./scripts/install.ps1 -Force
  • Linux/macOS Bash: bash scripts/install.sh --force
  1. Or manually build: npm install and npm run build.
  2. Create an instance with dg init, and start the daemon with dg start my-project --foreground for stdio or --http for HTTP.

Check that it works

Run dg init to create an instance and dg start my-project --http to launch the daemon, then run dg status my-project; if it reports instance identity, transport/port, and graph/ADR counts, the install works. When connecting an MCP client via stdio (dg start my-project --foreground), DreamGraph's graph tools should appear in the client's tool list.

Troubleshooting

  1. Verify Node.js 20+ and npm are installed: `node --version`, `npm --version`.
  2. Check daemon status: `dg status my-project`, ensure the port is available and not occupied.
  3. Restart the daemon and reload VS Code window if connection issues occur.
  4. For LLM setup, verify environment variables (e.g., Ollama/LM Studio URL) are correctly configured.
  5. Check firewall or proxy settings if connections fail.

Things to try

Once connected, you can ask your AI assistant things like:

  • Scan this repository and bootstrap the knowledge graph
  • Where does auth actually happen in this codebase?
  • What breaks if I change this module?
  • Show me the current instance status

Use cases

Understanding large codebases: ask 'Where does auth really happen?', 'What breaks if I change this?'
Making large changes safer by using graph context, ADRs, tool traces, and multi-repo awareness.
Bridging vibe coding and serious engineering: prototype quickly while accumulating structure, provenance, and lifecycle history.
Multi-repo systems: build graph links across repositories that share workflows, APIs, databases, and ownership.
Architect work: project-bound chat, selected-plan scope, runtime provenance, and auditable tool traces.

Supported clients

Claude Desktop
VS Code

Listed from the project's documentation, not tested by this site.

Overview

DreamGraph is a governed architecture cognition layer for MCP-enabled software projects. It combines an instance-scoped daemon, CLI, architect beta, VS Code extension, dashboard, and a persistent knowledge graph so project understanding is grounded in source, ADRs, workflows, tests, runtime observations, and human review rather than any single file read or isolated chat turn. It maintains a structured graph of features, workflows, data-model entities, architecture decisions, UI registry elements, tensions, and candidate hypotheses, enabling cross-repo reasoning, live database schema introspection, dream cycles, temporal/causal analysis, and an Adaptive Future Engine.

Similar servers

Context7 80 · B

Upstash's official server providing up-to-date third-party library docs for AI coding assistants

★ 62.9k · Tools 2 Compare with this →
Compare with other MCP servers

Source revision 41f65091746b Data synced 2026-10-11 Read the FMRS scoring method