About LTD MCP
LTD MCP connects AI agents to an LTD project-management workspace to inspect project health, search tasks, and manage tasks and comments. Writes require preview and confirmation, while scoped API tokens control access.
Key features
- 01View project health and analytics
- 02Search tasks and read details and comments
- 03Create, update, and assign tasks
- 04Preview writes before confirmation
- 05Separate read and write token scopes
Use cases
- 01Summarize project health and risks
- 02Find open tasks assigned to the token owner
- 03Preview a task creation or update before applying it
- 04Provide project visibility with a read-only token
MCP support
This remote MCP server uses Streamable HTTP at https://api.eshway.com/mcp/. Clients authenticate with a Bearer API token; write tools return a preview and short-lived confirmation token before applying changes.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://api.eshway.com/mcp/claude mcp add --transport http eshller-ltd https://api.eshway.com/mcp/{"mcpServers":{"eshller-ltd":{"type":"http","url":"https://api.eshway.com/mcp/"}}}Open in Cursor{"servers":{"eshller-ltd":{"type":"http","url":"https://api.eshway.com/mcp/"}}}Open in VS Code{"mcpServers":{"eshller-ltd":{"type":"http","url":"https://api.eshway.com/mcp/"}}}{"mcpServers":{"eshller-ltd":{"serverUrl":"https://api.eshway.com/mcp/"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
https://api.eshway.com/mcp/Auth requiredTools
Details
From the project READMELTD MCP
Project management MCP for AI agents.
LTD MCP lets AI agents connect to an LTD workspace over MCP and safely operate project work: inspect project health, search tasks, create tasks, update tasks, assign owners, and add comments using scoped API tokens and preview-confirm writes.
Status: early public preview. Read tools are available. Write tools use a two-step preview-confirm safety flow.
Why this exists
Most project management tools were built for humans clicking dashboards. AI agents need safe, structured tools.
LTD MCP is the agent-native interface for LTD, an anti-Jira-style project workspace for teams that want humans and AI agents operating together.
MCP endpoint
https://api.eshway.com/mcp/
Transport: Streamable HTTP / HTTP MCP
Authentication: Bearer token
Authorization: Bearer <LTD_API_TOKEN>
Capabilities
Read tools
ltd_list_projects- list projects the token can accessltd_describe_project- describe statuses, custom fields, and membersltd_search_tasks- search/filter tasksltd_get_task- fetch full task detailltd_my_tasks- list token owner's open tasksltd_get_comments- read task commentsltd_project_pulse- project health rollupsltd_analytics_query- analytics aggregationsltd_drilldown_tasks- drill into analytics datapoints
Write tools
ltd_create_task- create a taskltd_update_task- update fields on a taskltd_add_comment- add a comment
Write tools are intentionally two-step:
mode="preview"returns the exact proposed change and a short-lived confirm token. Nothing is written.mode="confirm"with the same arguments plusconfirm_tokenperforms the write.
Token scopes
Create an LTD API token from LTD Settings → API tokens.
Recommended scopes:
mcp:readfor read-only project visibilitymcp:writefor task creation, updates, assignment, and comments
Keep tokens secret. Revoke and rotate them from LTD settings when needed.
Quickstart
Generic MCP HTTP config
{
"mcpServers": {
"ltd": {
"transport": "http",
"url": "https://api.eshway.com/mcp/",
"headers": {
"Authorization": "Bearer ${LTD_API_TOKEN}"
}
}
}
}
Hermes
mcp add ltd --transport http \
--url https://api.eshway.com/mcp/ \
--header "Authorization: Bearer $LTD_API_TOKEN"
Smithery
smithery mcp add https://api.eshway.com/mcp/ --id ltd
Example prompts
Show me all LTD projects I can access.
Give me a project pulse for PS - Mini and list the top risks.
Create a low-priority test task in PS - Mini assigned to Eshu, but show me the preview before confirming.
Find stale tasks assigned to me, group them by status, and suggest next actions.
Safety model
LTD MCP is designed for human-controlled agent operations:
- Scoped PATs limit access.
- Read and write scopes are separate.
- Write actions use preview-confirm.
- Preview explicitly returns
nothing_changed_yet: true. - Confirm tokens are short-lived and single-use.
- Invalid assignees/statuses are rejected before write.
Example write flow
Preview:
{
"project_id": 168,
"title": "Test task created by ZERO",
"description": "Verify LTD MCP task creation.",
"status": "To Do",
"assignees": ["Eshu"],
"priority": "Low",
"mode": "preview"
}
Confirm:
{
"project_id": 168,
"title": "Test task created by ZERO",
"description": "Verify LTD MCP task creation.",
"status": "To Do",
"assignees": ["Eshu"],
"priority": "Low",
"mode": "confirm",
"confirm_token": "<token from preview>"
}
Supported clients
Any MCP client that supports remote HTTP / Streamable HTTP MCP servers should work.
Planned docs:
- Claude Desktop
- Cursor
- Cline
- Windsurf
- Hermes / ZERO
- Smithery
Links
- MCP endpoint: https://api.eshway.com/mcp/
- Website: https://ltd.eshway.com/
- Product: LTD by Eshway
Roadmap
- Public hosted docs
- Demo workspace
- Client-specific setup guides
- Official MCP Registry listing
- Smithery listing
- MCP.so listing
- Audit log docs
- OAuth support
License
MIT for documentation and examples in this repository. LTD server implementation and hosted service are owned by Eshway.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.