Skip to main content
Glama
@loopgantt/mcp-server

@loopgantt/mcp-server

@loopgantt/mcp-server

MCP (Model Context Protocol) server for LoopGantt. Turn a plain-language plan into a real Gantt chart from Claude Desktop, Cursor, or any MCP client — no account, no API key.

Remote server (no install)

Point your MCP client at https://loopgantt.com/api/mcp (Streamable HTTP). Nothing to install, no account, no key.

  • Claude (claude.ai / Claude Desktop): Settings → Connectors → Add custom connector → URL https://loopgantt.com/api/mcp.

  • ChatGPT: Settings → Connectors → Create → MCP server URL https://loopgantt.com/api/mcp, authentication None.

  • Cursor and other clients (mcp.json):

{
  "mcpServers": {
    "loopgantt": {
      "url": "https://loopgantt.com/api/mcp"
    }
  }
}

The remote server exposes the keyless tools, resources and prompt below. The account tools (create_project, list_projects) need an API key and are only available on the local server for now.

Related MCP server: gantt-mcp

Local server (npm)

npm install -g @loopgantt/mcp-server

Add to your MCP client config (Claude Desktop: claude_desktop_config.json):

{
  "mcpServers": {
    "loopgantt": {
      "command": "loopgantt-mcp"
    }
  }
}

Restart the client and ask:

  • "Make a Gantt chart for a 6-week website relaunch"

  • "Plan a kitchen renovation with realistic durations and dependencies"

  • "Schedule the launch of our mobile app starting September 1"

Your assistant drafts the tasks, durations and dependencies; LoopGantt schedules them with its critical-path engine and replies with a picture of the chart, the dates, the critical path and a link where you can view the chart, export it (PNG / PDF) and save it to a free account.

Unclaimed charts expire after 7 days (30 days once the link is opened). Saving to an account keeps them forever.

Tools

create_gantt — no key needed

Parameter

Description

name (required)

Project name

description

Optional one-liner

startDate

YYYY-MM-DD, defaults to today

workDays

Working weekdays as ISO numbers 1 (Mon) … 7 (Sun); default Mon–Fri

holidays

Non-working dates, YYYY-MM-DD

tasks (required)

In execution order: { name, duration, isMilestone?, description?, dependencies? } — duration in working days (0 = milestone); dependencies are indices of earlier tasks, or { task, type: FS|SS|FF|SF, lag }

Limits: 300 tasks, 20 dependencies per task, 10 charts per hour and 30 per day per network (the hosted server at loopgantt.com/api/mcp allows 60 per hour and 300 per day per network, because hosted assistants share a few addresses). Dates in replies are the first and last working day of each task.

schedule_project — no key needed

Same input as create_gantt (name optional). Returns dates, critical path, float and the project end without storing anything — for "what's my critical path?" / "when would this finish?" questions. Limit: 60 calls per hour per network.

list_templates / get_template — no key needed

The industry templates (software, construction, marketing, events, IT, HR, finance) with their task lists, ready to adapt and pass to create_gantt. Also exposed as MCP resources (loopgantt://templates/<slug>).

Prompt: plan_project

A guided flow — arguments goal, deadline?, team_size? — that drafts a work breakdown, creates the chart and presents the picture, the critical path and the link.

With an API key — account tools

Get a key at https://loopgantt.com/settings/api-keys and pass it as an environment variable:

{
  "mcpServers": {
    "loopgantt": {
      "command": "loopgantt-mcp",
      "env": { "LOOPGANTT_API_KEY": "sk_live_…" }
    }
  }
}

This enables create_project (creates the project directly in your account) and list_projects.

Environment variables

Variable

Description

Required

LOOPGANTT_API_KEY

Enables the account tools

No

LOOPGANTT_API_URL

API base URL (default https://loopgantt.com/api/v1)

No

API

The server is a thin client over LoopGantt's public API — see the OpenAPI spec at https://loopgantt.com/openapi.json.

License

MIT

Available Tools

4 tools
create_ganttA

Create a Gantt chart from a task list — no account or API key needed. YOU author the plan: list the tasks in execution order with realistic working-day durations and dependencies (0-based positions of earlier tasks; use { task, type, lag } for start-to-start/finish-to-finish links or lag). Milestones have duration 0. LoopGantt schedules it with its critical-path engine and returns a picture of the chart, the dates, the critical path and a link where the user can view, export (PNG/PDF) and save the chart. Always show the user the link.

Inputs: name (required), tasks (required), holidays, workDays, +2 more.

get_templateA

Get one industry template by slug: its task list with durations, ready to adapt and pass to create_gantt.

Inputs: slug (required).

list_templatesA

List LoopGantt's industry project templates with task counts and typical durations. Pick one, fetch it with get_template, adapt it, then create_gantt.

Inputs: no named parameters.

schedule_projectA

Compute a schedule without storing anything: dates, critical path, float and project end for a task list (same input shape as create_gantt; name optional). Use it to answer "what is the critical path?", "when would this finish?", "how much slack does X have?". Use create_gantt when the user wants a chart they can open.

Inputs: tasks (required), name, holidays, workDays, +2 more.

Tool Schema Changelog

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

Loading tool schema changelog…

    TDQS

    A4.1/5.0

    Scored across 4 tools

    Disambiguation4/5

    list_templates and get_template are clearly a list/detail pair, while create_gantt and schedule_project share the same input shape and both surface dates and critical path. The descriptions clearly distinguish them by output and intent—create_gantt for a viewable chart, schedule_project for pure computation—so an agent can disambiguate with careful reading.

    Naming Consistency5/5

    All four tools follow a consistent verb_noun snake_case pattern: list_templates, get_template, create_gantt, schedule_project. There are no mixed conventions or stylistic deviations.

    Tool Count5/5

    Four tools form a tight, well-scoped set: template discovery, template retrieval, chart creation, and schedule computation each have exactly one tool. Nothing feels redundant or missing at the current scope.

    Completeness4/5

    The stated template-to-Gantt workflow is fully covered: list templates, fetch one, create a chart, or compute a schedule. There is no management layer for updating or deleting previously created charts, but the returned link handles viewing/exporting/saving, making this a minor gap rather than a critical one.

    Maintenance

    ActivityStale
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables collaborative project planning by connecting an MCP-capable chat app to a generative AI that manages tasks and dependencies, with a live web UI for visualization.
      1
      GPL 3.0
    • F
      license
      Not graded
      quality
      B
      maintenance
      An OAuth-protected MCP server that converts project descriptions into realistic schedules, handling dependencies, resource leveling, critical path analysis, and generating shareable charts (HTML, SVG, PNG, JSON, CSV).
      -
    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables MCP-compatible AI clients to query, analyze, and mutate Oracle Primavera P6 schedules from XER files or live P6 EPPM, with tools for critical path, DCMA compliance, earned value, resources, baselines, and exports.
      43 PyPI
      2
      MIT
    • A
      license
      B
      quality
      C
      maintenance
      Enables project and program managers to generate plan, forecast, risk, capacity, and flow reports from Jira boards inside MCP-capable AI assistants, including Gantt charts, milestones, dependency maps, workload heatmaps, Monte Carlo finish-date forecasts, and exports. It reads Jira read-only and returns deterministic calculations, charts, and files through natural-language chat.
      10
      MIT