Skip to content
MCP server

LiveGraph

Agent orchestrator with a live canvas: author graphs over MCP, reroute runs mid-flight

Install
Pricing
Freemium
Platforms
Web, API
Runs
Remotely
Version
0.1.1
Listing updated
3 days ago

About LiveGraph

LiveGraph is a freemium MCP server for developer tools. It runs as a hosted remote server, so there is nothing to install locally.

The canvas stays live while a workflow runs, so dragging an edge changes where the next hop goes without a restart; an in-flight model call is not cancelled and the saved graph only changes if you keep the route. Scheduled and webhook-triggered runs are pinned to a snapshot, so a drag never rewrites a job already running.

Other controls described include approval-gated nodes with an approvals queue, per-run dollar budgets that start at a $2 cap, pause and resume mid-hop, nested graphs, isolated git worktrees for code-writing agents, sandboxed code execution and a GitHub tab. It works with Gemini on the included free model, or your own keys for Anthropic, OpenAI, xAI, OpenRouter, OpenAI-compatible endpoints and local Ollama. The site also describes importing an OpenAI Agents SDK export.

The free Solo plan allows unlimited graphs and manual runs and up to 3 schedules and webhooks. Team is $49 per workspace per month with hosted keys, sharing and unlimited triggers. The MCP endpoint lets an agent author graphs on the canvas.

Install

Run in a terminal

claude mcp add --transport http livegraph https://api.livegraph.ai/mcp

Add to Settings → Connectors → Add custom connector

https://api.livegraph.ai/mcp
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "livegraph": {
      "url": "https://api.livegraph.ai/mcp"
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "livegraph": {
      "type": "http",
      "url": "https://api.livegraph.ai/mcp"
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "livegraph": {
      "serverUrl": "https://api.livegraph.ai/mcp"
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "livegraph": {
      "type": "http",
      "url": "https://api.livegraph.ai/mcp"
    }
  }
}

What it does

Live rerouting
Drag an edge and the next hop follows.
Approval gates
Park runs for approve, edit or reject.
Per-run budgets
A $2 cap by default, with automatic downgrade options.
Isolated git worktrees
Agents write code on their own branch.
Nested graphs
One graph can dispatch work into another.
Model-agnostic
Your keys, hosted keys, or local models.
Agents SDK import
Reads an export and lists what does not carry over.

Good for

  • Redirect a run that heads to the wrong step
  • Gate risky actions behind human approval
  • Run a support desk of cooperating agents
  • Schedule agents against a repo or inbox
  • Move an Agents SDK workflow onto a canvas

Pricing

Freemium, from $49 a month

Solo free; Team $49/workspace/mo; managed model usage metered

Prices change. Check livegraph.ai before you buy.

LiveGraph FAQ

Is there a free plan?

Yes, Solo is $0 with unlimited graphs and manual runs and up to 3 schedules and webhooks.

What does Team cost?

$49 per workspace per month, flat and unmetered for runs.

Do I need my own model key?

No; an included free Gemini model works, or bring keys from several providers.

Does a drag change scheduled runs?

No, schedules and webhooks use a snapshot taken at the start.

Is LiveGraph free?

LiveGraph has a free plan, with paid plans for more usage or features. Paid plans start at $49 a month.

How do I add LiveGraph to Claude Code?

Run this command in your terminal: claude mcp add --transport http livegraph https://api.livegraph.ai/mcp

What are the best alternatives to LiveGraph?

The closest alternatives to LiveGraph are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.

Alternatives to LiveGraph

  1. REA

    MCP server

    CLI and MCP server that lets coding agents reverse engineer apps and binaries

    Runs locally
    • Open source
    • 464K GitHub stars
    • Developer tools
  2. Codebase Memory

    MCP server

    Local MCP server that builds a code knowledge graph for AI coding agents

    Runs locally
    • Open source
    • 48.7K GitHub stars
    • Knowledge and memory
  3. GitHub

    MCP server

    Official MCP server connecting AI assistants to GitHub repos, issues and workflows

    Not checked yet
    • Remote
    • Open source
    • 34.5K GitHub stars
    • Developer tools
  4. MCP toolkit giving coding agents symbol-level code retrieval and editing

    Runs locally
    • Open source
    • 31.5K GitHub stars
    • Developer tools
  5. XERJ

    MCP server

    Local search engine for AI agents with cited answers over your code and docs

    Runs locally
    • Open source
    • 19.2K GitHub stars
    • Knowledge and memory
  6. Ouroboros

    MCP server

    Spec-first layer that pins requirements and verifies results of AI coding agent work

    Runs locally
    • Open source
    • 6.4K GitHub stars
    • Developer tools