How does Casemgr Mcp handle authentication?
Browser-capable clients authenticate via OAuth automatically when you add the server URL. Headless clients use an API token set in the `CASEMGR_TOKEN` environment variable.
@mstang
Basic information
Shared workspace your AI agents write to. CMMN case management with 184+ MCP tools: cases, tasks, event-driven workflows with sentries, persistent memory with semantic search, billing and invoicing. OAuth or token auth; cloud-hosted remote MCP endpoint.
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"casemgr": {
"type": "http",
"url": "https://casemgr.systems/mcp"
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
This server requires authentication. Tool discovery may require signing in or credentials from the provider.
Fetch the live tool list directly from this server's endpoint using the button above.
Casemgr Mcp gives AI agents a shared, persistent workspace built on CMMN (Case Management Model and Notation). It provides 184+ MCP tools covering cases, tasks, notes, files, workflows, billing, and calendar, with event-driven CMMN workflows, persistent memory with semantic search, and multi-agent coordination.
Browser-capable clients (Claude Code, Claude Desktop) authenticate via OAuth automatically — just add the server URL https://casemgr.systems/mcp. For headless clients, set the CASEMGR_TOKEN environment variable. Install via npx casemgr-mcp.
Browser-capable clients authenticate via OAuth automatically when you add the server URL. Headless clients use an API token set in the `CASEMGR_TOKEN` environment variable.
CMMN stands for Case Management Model and Notation, the standard that Casemgr Mcp’s event-driven workflows are built on.
Casemgr Mcp provides over 184 MCP tools covering cases, tasks, notes, files, workflows, billing, and calendar.
Yes. Casemgr Mcp supports multi-agent coordination: agents can register their presence, leave handoffs, and see each other’s state.
The server is cloud-hosted at `casemgr.systems/mcp`. There is no mention of a self-hosted option in the README.

Orcha is a unified context layer for AI tools and agents. It stores and indexes and exposes organizational, team, or individual knowledge. Files, structured databases, and connected sources live in one workspace, and age

Local AI agent for your Mac with a built-in MCP server: 18 tools for your notes and PDFs, a temporal memory graph, an on-device LLM and a neural voice. No account, no telemetry. No data centers required.
Groundwork: company memory for your AI tools. Docs public. Source closed. Public proof needs no account.

Exact, shared memory for AI agents: a hierarchical database where totals always add up, every write is attributed to the agent and person behind it, and any figure traces back to its source file. Agents create databases,

Mess in, magic out: pour in your D&D and TTRPG notes and LoreKeeper keeps them as a private store for your world. Ask Claude or ChatGPT about it, or build a sourcebook.
Comments