Model Context Protocol · Free

GanttFather MCP Server

The GanttFather MCP server is a Model Context Protocol endpoint at mcp.ganttfather.com that lets AI agents read and write Gantt project data — tasks, dependencies, members, resources, critical path — through standard MCP tools. Free for any GanttFather user. Works with Claude Desktop, Cursor, Windsurf, VS Code Copilot, Gemini CLI, Antigravity, and Claude Code.

Generate agent token Per-editor snippets

Endpoint summary

Server name

gantt-lite-remote

URL

https://mcp.ganttfather.com

Transport

Streamable HTTP with Server-Sent Events (SSE)

Auth

OAuth flow or Bearer agent token (per-project scope)

Rate limit

60 requests/minute per token

Pricing

Free for any GanttFather user · no per-call fees

Tech stack

.NET 10 · ASP.NET Core · ModelContextProtocol.AspNetCore · PostgreSQL

How do I set up the GanttFather MCP server?

Two install methods depending on whether your MCP client supports OAuth. Both connect to the same hosted server at mcp.ganttfather.com.

Option 1 — OAuth (Claude Desktop, Cursor, Windsurf)

Recommended for client apps that support browser-based authorization. The first call triggers an OAuth flow where you grant the agent access to a specific GanttFather project.

mcp_config.json OAuth — no token needed

{
  "mcpServers": {
    "ganttfather": {
      "url": "https://mcp.ganttfather.com"
    }
  }
}

Option 2 — Agent token (any MCP client)

Open your project in GanttFather.
Go to Settings → Agent Tokens and generate a token.
Add the snippet below to your MCP client config, replacing YOUR_AGENT_TOKEN.

mcp_config.json Token-based — works with any MCP client

{
  "mcpServers": {
    "ganttfather": {
      "url": "https://mcp.ganttfather.com",
      "headers": {
        "Authorization": "Bearer YOUR_AGENT_TOKEN"
      }
    }
  }
}

Tokens are scoped to a single project. Generate one per project the agent should access. Need editor-specific config paths and snippets? See the per-editor snippets page.

What tools does the MCP server expose?

The server exposes 14 tools across 4 categories. AI clients discover this list automatically through MCP's tools/list handshake — you do not need to register them manually.

Project tools

Tool	Description
list_projects	List projects accessible by this token (returns the scoped project for token-based auth).
get_project	Get full project details including members, resources, and metadata.

Task tools

Tool	Description
list_tasks	List all tasks in a project. Filter by status, assignee, or parent.
get_task	Get detailed task info: dependencies, assignments, audit trail, dates, progress.
create_task	Create a new task with name, dates, status, priority, parent, and assignees.
update_task	Partial update — only the fields you pass are changed; rest preserved.
delete_task	Delete a task plus all subtasks, dependencies, and assignments.
reorder_tasks	Batch reorder and reparent tasks in one call (JSON updates array).

Analysis tools

Tool	Description
get_project_summary	High-level stats: task count, completion %, overdue count, health score.
get_critical_path	Compute the critical path through all dependencies using CPM.
list_overdue_tasks	Tasks that are past their end date and not yet completed.

Members & resources

Tool	Description
list_members	All project members including agent tokens and their roles.
list_resources	All non-human resources (equipment, software, virtual assets, rooms).
add_resource	Add a resource with type (Human or Virtual) and cost (Hour, Use, or Flat).

What can I do with the MCP server?

Four common conversational flows. Each shows the prompt a user types into their AI client, plus the MCP tools the agent calls behind the scenes.

Plan a project from a brief

"Read this product requirements doc and create a GanttFather plan with milestones, dependencies, and a 6-week timeline."

Behind the scenes: The agent calls create_task repeatedly with computed start/end dates, sets dependencies via update_task, and confirms the schedule via get_critical_path.

Daily standup

"What is the status of the GanttFather project today? Anything overdue?"

Behind the scenes: The agent calls get_project_summary and list_overdue_tasks, then returns a one-paragraph summary in natural language.

Resource reallocation

"Who has bandwidth this week? Reassign the API integration task to whoever is freest."

Behind the scenes: The agent calls list_members and list_tasks filtered by assignee, finds the freest member, then calls update_task with the new assignee.

Critical-path triage

"Show me everything on the critical path that is also overdue, and propose a reschedule."

Behind the scenes: The agent calls get_critical_path and list_overdue_tasks, intersects the two lists, and proposes new dates per task using update_task.

How does authentication scope agent access?

Agent tokens are scoped to a single project. An agent authenticated with a token for Project A cannot read or modify Project B — even if the human owner has access to both. This contains the blast radius of any agent error or prompt-injection attempt.

Per-project tokens. Generate a separate token for each project an agent should manage.
Audit trail. Every tool call is logged with the token identity, timestamp, and the change made — visible in the project audit log.
Instant revocation. Revoke a token from Settings → Agent Tokens; the server rejects subsequent calls within seconds.
Rate limiting. 60 requests per minute per token prevents runaway loops.
No data exfiltration via tools. Tools return scoped data only; there is no read-everything endpoint.

Frequently asked questions

What is the GanttFather MCP server?

The GanttFather MCP server is a Model Context Protocol endpoint at mcp.ganttfather.com that lets AI agents read and write Gantt project data — tasks, dependencies, members, resources, critical path — through standard MCP tools. It is free for any GanttFather user and works with Claude Desktop, Cursor, Windsurf, VS Code Copilot, Gemini CLI, Antigravity, and Claude Code.

Is the MCP server free?

Yes. The MCP server inherits your GanttFather account limits — free tier covers 4 projects with unlimited users, paid project slots start at $1/month annually. There is no per-token, per-call, or per-agent fee for using the MCP server itself.

How does authentication work?

Two methods. (1) OAuth — for clients that support it (e.g. Claude Desktop), just add the URL and the first call triggers a browser-based authorization flow. (2) Agent tokens — generate a token in your project Settings → Agent Tokens, paste it as a Bearer header. Tokens are scoped to a single project; generate one per project the agent should access.

What is the rate limit?

The server enforces 60 requests per minute per token. This is generous for normal interactive use; high-volume batch operations should use the reorder_tasks bulk endpoint instead of looping update_task.

Which AI clients can connect?

Any client that implements MCP. Officially tested: Claude Desktop, Claude Code, Cursor, Windsurf, VS Code (Cline extension), Antigravity, Gemini CLI. Streamable HTTP transport with Server-Sent Events is the only transport mode — clients that require stdio transport are not supported.

What if my AI agent breaks something?

Every change made by an MCP agent goes through the same authorization and audit trail as a human user. The token scope limits the blast radius to one project. If something goes wrong, you can revoke the token instantly from Settings → Agent Tokens, and review the project audit log to see exactly what the agent changed.

Still have questions?

Drop us a line — we usually reply in under a business day.

[email protected]

Connect your AI agent in 30 seconds

Free for any GanttFather user. OAuth or agent token. Works with Claude Desktop, Cursor, Windsurf, VS Code, and any MCP-compatible client.

Generate agent token Per-editor snippets