Ganty MCP server
online · 100% uptimeapp.ganty/mcp-server·v1.0.0Gantt chart SaaS with server-side critical path and dependency-aware shift-impact tools, plus CRUD.
0 stars
Reviews
Write oneNobody has reviewed Ganty MCP yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Ganty MCP tools (15, 7 write)
write = sends, deletes, buys or postsadd_dependencyFreeAdd a finish-to-start dependency between two tasks in the same project.
create_milestonewrite actionFreeAdd a milestone (key date) to a project.
create_projectwrite actionFreeCreate a new project in a workspace. Returns the created project. Subject to plan-based project count limits.
create_taskwrite actionFreeCreate a new task in a project. Dates must be in YYYY-MM-DD format. End date is exclusive (a 1-day task has end = start + 1 day).
delete_projectwrite actionFreePermanently delete a project. All tasks, milestones, and dependencies inside the project are also removed. This cannot be undone.
delete_taskwrite actionFreeDelete a task. Child tasks and dependencies are removed as well.
get_critical_pathFreeCalculate the critical path of a project on the Ganty side and return it as data (don't ask the model to reason over raw task lists). Uses forward/backward CPM with progress-aware remaining duration. Returns critical_path tasks in order, per-task earliest/latest start/finish + slack, project_end_date, and total_duration_days. v1 limitations: Finish-to-Start dependencies only (Ganty has no other types), calendar days by default (business_days=true skips Sat/Sun but no holiday table), ignores multi-period segments, no resource calendars. Returns { error: 'cyclic_dependency', cycle } if a cycle is detected.
get_taskFreeGet detailed information about a single task, including assignees and dependencies.
list_milestonesFreeList milestones in a project (key dates such as launch or review gates).
list_projectsFreeList all projects in a workspace (excluding archived).
list_tasksFreeList tasks in a project. Supports optional filtering by name (search), status, and assignee.
list_workspacesFreeGet all workspaces the authenticated user is a member of.
reschedule_and_propagateFreeCompute the downstream impact of shifting a single task. Default is dry_run (no DB writes); set mode='commit' to actually persist the changes. Cascades forward only (no pull): successors are pushed only if their predecessor's new end + lag would violate their current start. Tasks with progress=100 are treated as pinned; pass pinned_task_ids for additional pins. When a pin would be violated, the change is recorded in 'conflicts' and not propagated further. In mode='commit', if any conflicts exist nothing is written (all-or-nothing transaction). Same v1 limitations as get_critical_path: FS only, calendar days by default, no holiday table, ignores multi-period segments.
set_task_progresswrite actionFreeUpdate the progress percentage of a task (0-100). Status is auto-derived: 0=not_started, 1-99=in_progress, 100=done.
update_taskwrite actionFreeUpdate fields of an existing task. Only provided fields will be modified.
Public scan report
scanner v0.1.9 · 2026-09-27 · same rubric, same numbers if you re-run it
- –Code scanremote-only server, no package to scann/a
- Live reliabilityremote reachable in 1546ms20/20
- Tool poisoning15 tool descriptions checked15/15
- Auth qualityopen endpoint exposes 7 write-action tools with no auth3/15
- Maintenancelast push 98 days ago8/15
- Maintainer identitynamespace and repository owner differ; GitHub account older than a year; website matches verified namespace7/10
Findings (1)
- highWrite-action tools reachable without authentication
auth.open-write
How Ganty MCP compares
Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 71/100
- higher than 36% of 48,255 servers
- Tools
- 15
- the typical server has 7
- Tools that change things
- 47%
- typical: 0%. Fewer write tools means less an agent can break
- Uptime
- 100%
- of our recent checks; the typical remote server answers 100%
- Response time
- 710 ms
- faster than 19% of 30,031 servers
What its tools let an agent do: 7 read · 4 create · 2 change · 2 delete
Install Ganty MCP in Claude Code, Cursor or VS Code
claude mcp add --transport http mcp-server https://ganty.app/api/mcp
What the publisher says
From the Ganty MCP repository's README, as published. We do not edit it. Read it on GitHub
Ganty MCP
Ganty is a Gantt chart SaaS with a built-in Model Context Protocol (MCP) server that lets AI clients like Claude Desktop and Claude Code drive your projects in natural language — and computes critical paths and shift-impact server-side rather than asking the LLM to do math.
Status: v1.0.0 — production endpoint at https://ganty.app/api/mcp (Streamable HTTP)
Free on every Ganty plan including Free.
What makes this different
Most MCP servers expose CRUD over an existing API. Ganty's also exposes calculation tools that compute on the server and return JSON — so the LLM never has to reason about dates, dependencies, or critical paths.
- getcriticalpath — forward/backward-pass CPM with progress-aware remaining duration. Returns the critical path tasks in order, per-task earliest/latest start/finish, slack, projected end date. Detects cycles before computing and returns error: 'cyclic_dependency' instead of hanging or guessing.
- rescheduleandpropagate — simulate or commit a task shift. Default mode is dryrun (no DB writes). Push-only cascade respects pinned tasks (anything at progress=100 or in pinnedtask_ids) and reports conflicts instead of overwriting. commit mode wraps everything in an all-or-nothing transaction.
Quick start
- Issue an MCP token in Ganty: dashboard → Settings → MCP Integration → "Issue new token".
- Configure Claude Desktop (claudedesktopconfig.json) or Claude Code (.mcp.json at project root):
{
"mcpServers": {
"ganty": {
"url": "https://ganty.app/api/mcp",
"headers": { "Authorization": "Bearer YOUR_TOKEN" }
}
}
}- Restart Claude and try a prompt:
- "List my Ganty projects"
- "What's the critical path for the e-commerce rebuild project?"
- "If I push the payments task by +3 days, when does release ship?"
Full setup walk-through:
Tools
Read tools (visible to read-only and write tokens)
Write tools (write-scope tokens only)
rescheduleandpropagate is classified as a write tool even in dry_run mode (it shares the same compute path as commit and we don't want read-only tokens running unlimited simulations).
v1 scope and limitations
We prefer explicit non-support over silent wrong answers. Every response from the calculation tools includes a limitations array.
- Dependency types: Finish-to-Start only (Ganty's schema doesn't model SS/FF/SF)
- Calendar: calendar days by default; business_days: true skips Sat/Sun only (no holiday table)
- No resource calendars in v1
- Multi-period tasks (extraSegments) are ignored in v1; calculations use only the main start/end of each task
- Pinned tasks: progress=100 automatically pinned; supply pinnedtaskids for additional pins
- Push-only cascade: successors are pushed back when required, never pulled forward
Architecture
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
Ganty MCP: common questions
- Is Ganty MCP server safe?
- Mostly: it is graded B (71/100). Read the Ganty MCP safety report
- How do I install Ganty MCP?
- It runs remotely at ganty.app. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.
- Does Ganty MCP need an API key?
- Not as far as the registry entry and our scan can tell: no credentials are declared or required.
- Is Ganty MCP maintained?
- The last commit was 136 days ago (2026-06-21). The latest release is v1.0.0.
- Is Ganty MCP up?
- 100% of our last 28 checks got an answer. We check remote servers about four times a day.
- How does Ganty MCP compare with other MCP servers?
- safety score 71/100 (higher than 36% of 48,255 servers); tools 15 (the typical server has 7); tools that change things 47% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.