Nemus
Graph-based task manager that AI agents can read and update via MCP
The server answered yesterday with a sign-in request for OAuth (HTTP 401), so we could not list its tools.
Nemus is an MCP server for productivity. It runs as a hosted remote server, so there is nothing to install locally.
- Platforms
- Web, API
- Runs
- Remotely
- Access
- Needs sign-in (OAuth)
- Version
- 1.0.0
- Listing updated
Similar MCP servers
Install
Run in a terminal
claude mcp add --transport http nemus https://api.nemus.fyi/mcpAdd to Settings → Connectors → Add custom connector
https://api.nemus.fyi/mcpAdd to ~/.cursor/mcp.json
{
"mcpServers": {
"nemus": {
"url": "https://api.nemus.fyi/mcp"
}
}
}Add to .vscode/mcp.json
{
"servers": {
"nemus": {
"type": "http",
"url": "https://api.nemus.fyi/mcp"
}
}
}Add to ~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"nemus": {
"serverUrl": "https://api.nemus.fyi/mcp"
}
}
}Add to Grok Bot desktop app → Connect apps → Add a custom connector
https://api.nemus.fyi/mcpEnter a Name (for example "Nemus"), choose Type: Remote HTTPS, paste this as the Server URL and choose Add plugin. When we checked, this server asked for OAuth sign-in. If its docs give you an OAuth client ID and secret, enter them in the form's OAuth Client ID and Client Secret fields.
Add to your client's MCP settings (most use this shape)
{
"mcpServers": {
"nemus": {
"type": "http",
"url": "https://api.nemus.fyi/mcp"
}
}
}Using several servers? Build one config file with the MCP config generator.
About Nemus
Nemus models work as a graph of tasks linked by dependencies and blockers, so a team can see what depends on what before anything gets started. The MCP registry entry describes a streamable HTTP endpoint that lets an AI agent read that graph and update tasks directly.
The website positions the product as a project management portal where people and agents share one connected project and can switch between different views of the same work. Because the agent works against the same task structure as the humans, changes it makes show up in the same place as everyone else's.
It suits teams that already use AI assistants for planning and want those assistants to keep task status and blockers current rather than working from a stale copy.
What it does
- Dependency graph of tasks
- Tasks are linked by dependencies so the relationships between pieces of work are visible.
- Blocker tracking
- Blockers can be recorded against tasks so stalled work is easy to identify.
- Agent read and write access
- An MCP endpoint lets an AI agent read tasks and update them.
- Multiple project views
- The same connected project can be viewed in different ways, according to the website.
- Shared human and agent workspace
- People and AI agents work in the same project rather than in separate tools.
Good for
- Letting an AI assistant update task status after work is completed
- Mapping which tasks are blocked by other tasks before planning a sprint
- Having an agent flag blockers while reviewing project progress
- Keeping a shared project graph current across people and agents
Nemus FAQ
How does an AI client connect to Nemus?
The MCP registry entry lists a streamable HTTP remote at https://api.nemus.fyi/mcp.
What can an agent do with Nemus?
The registry entry says an agent can read and update tasks, dependencies and blockers.
How do I add Nemus to Claude Code?
Run this command in your terminal: claude mcp add --transport http nemus https://api.nemus.fyi/mcp
What are the best alternatives to Nemus?
The closest alternatives to Nemus are Nuto, Cronum Work, Nusk, Todo MCP and Nodary.
Where this comes from
- Description: written from the project's website and its MCP Registry entry.
- Status: checked automatically by AIPoweredBot on 21 November 2026.
- Install steps: from the official MCP Registry entry.