Connects Claude to a persistent graph workspace where your agent can create notes, plan tasks, and mark them done across sessions. Exposes 184 tools spanning semantic search, file management with versioning, multi-agent task queues, CMMN workflows, and time tracking. Nothing resets between conversations. The agent writes, you edit, and everything stays searchable. Works via stdio bridge for Claude Desktop and Cursor, or native HTTP for Claude Code with OAuth. Reach for this when you want your AI to build institutional memory instead of forgetting everything after each chat, or when coordinating work across multiple agent sessions with shared state.
A shared workspace your AI agent actually writes to — 184 MCP tools.
It creates notes when it finds things, plans tasks when work appears, and marks them done. You review and edit. Persistent memory + semantic search across a graph of notes, tasks, and files.
This package is the stdio-to-HTTP bridge for the CaseMgr MCP server — use it with any MCP client that supports stdio transport (Claude Desktop, Cursor, etc.). For Claude Code, see below — it supports HTTP natively and does not need this bridge.
npm install -g casemgr-mcp
Get an API token at casemgr.systems/tokens.
Add to your MCP settings:
{
"mcpServers": {
"casemgr": {
"command": "casemgr-mcp",
"env": {
"CASEMGR_API_TOKEN": "your_token_here"
}
}
}
}
Claude Code authenticates via OAuth automatically — no token needed. Just add the server URL:
{
"mcpServers": {
"casemgr": {
"url": "https://casemgr.systems/mcp"
}
}
}
If you prefer token auth, add "headers": { "Authorization": "Bearer your_token_here" }.
Install directly via Smithery — one-click setup for Claude Code, Cursor, Codex, and more.
A shared, persistent workspace for you and your AI agent — 184 MCP tools across a graph of notes, tasks, files, calendar, and agent presence.
Your agent creates notes when it finds things. Plans tasks when there's work to do. Marks them done as it finishes. You review, edit, and add your own. Nothing is ephemeral — every session resumes exactly where the last one left off, and semantic search spans everything either of you ever wrote.
What's in the workspace:
| Variable | Required | Default | Description |
|---|---|---|---|
CASEMGR_API_TOKEN | Yes (stdio) | — | API token from casemgr.systems/tokens. Required for stdio clients (Claude Desktop, Cursor). Not needed for Claude Code, which uses OAuth. |
CASEMGR_URL | No | https://casemgr.systems/mcp | MCP endpoint URL (for self-hosted instances) |
MIT
CASEMGR_API_TOKEN*secretAPI token from casemgr.systems/tokens
io.github.ericm1018/skillfm-llm-cost-optimizer-openai-anthropic-usage
io.github.mikerawsonnz/llm-orchestration-agent
io.github.mikerawsonnz/authenticated-llm-agent
labforgedev/copilot-memory-mcp
csoai-org/agent-prompt-injection-firewall-mcp
io.github.mikerawsonnz/authenticated-multi-llm-agent