AgentDrive gives agents persistent memory and artifact storage that survives across tools and sessions. It exposes 20 MCP tools split across files (write, read, list, versions), semantic search and recall, provenance logging, and workspace collaboration. Write a markdown spec in Claude Code, then have Cursor's agent pick it up with drive_context or drive_search in the next session. Run logs track which agent on which platform touched what, so handoffs between Claude Code, Codex, Cursor, and LangGraph maintain attribution. Free tier includes 1 GB storage and 10k embeddings. Available as a hosted streamable HTTP endpoint or local stdio via npx.
The official Model Context Protocol server for AgentDrive — a cross-agent artifact workspace with provenance and portable storage across Claude Code, Codex, Cursor, LangGraph, and any MCP-aware host.
Give your agents a shared, persistent workspace: files with versioning, semantic recall over everything prior agents produced, run logging, and cross-agent attribution — so the next session (on any tool) picks up where the last one left off.
@adrive/mcp-serverhttps://mcp.agentdrive.sh/mcpCreate one at https://app.agentdrive.sh — no credit card. The free tier (1 workspace, 1 GB storage, 10k embeddings) is free indefinitely.
Point any MCP client that supports remote servers at the hosted endpoint and pass your key as a bearer token:
URL: https://mcp.agentdrive.sh/mcp
Header: Authorization: Bearer agentdrive_live_xxx
Or install in one click via Smithery.
{
"mcpServers": {
"agentdrive": {
"command": "npx",
"args": ["-y", "@adrive/mcp-server"],
"env": {
"AGENTDRIVE_API_KEY": "agentdrive_live_xxx"
}
}
}
}
Add that block to your host's MCP config:
claude_desktop_config.json~/.cursor/mcp.jsonclaude mcp add agentdrive -- npx -y @adrive/mcp-server (set AGENTDRIVE_API_KEY in env)mcpServers block aboveThe fastest path is the AgentDrive installer, which auto-wires every detected host:
curl -fsSL agentdrive.sh/install | sh
| Env var | Required | Default | Description |
|---|---|---|---|
AGENTDRIVE_API_KEY | yes | — | Your AgentDrive API key (agentdrive_live_...). |
AGENTDRIVE_API_URL | no | https://app.agentdrive.sh | Override the API endpoint (self-hosted worker). |
AGENTDRIVE_AGENT_PLATFORM | no | claude-code | Which agent runtime is calling — drives cross-agent provenance. One of claude-code, codex, cursor, langgraph, crewai, autogen, cline, continue, zed, unknown. |
AGENTDRIVE_AGENT_ROLE | no | — | Free-text role label (e.g. planner, reviewer) to distinguish multiple agents on the same platform. |
20 tools across files, memory, collaboration, org, and provenance.
| Tool | Category | Description |
|---|---|---|
drive_context | memory | Auto-pull the most relevant prior artifacts for the task you're starting. |
drive_search | memory | Semantic search across your org's artifacts. |
drive_recall | memory | Recall persistent facts/preferences agents have written. |
drive_write | files | Write a markdown file (auto-versioned). |
drive_read | files | Read a file's content. |
drive_list | files | List files in a workspace. |
drive_delete | files | Delete a file. |
drive_versions | files | View a file's version history. |
drive_share | collaboration | Generate a (optionally email-gated) share link. |
drive_comment | collaboration | Comment on a file. |
drive_feedback | collaboration | Read human comments on a file. |
drive_activity | provenance | Recent workspace activity (writes, comments, shares). |
drive_log_run | provenance | Log an agent run (task, status, artifacts, identity). |
drive_invite | org | Invite a human to your org by email. |
drive_roles | org | Assign/list/remove per-workspace access by email. |
drive_org | org | View org details: agents, members, plan, usage. |
drive_sandbox_clone | sandbox (experimental) | Clone a git repo into a per-workspace Linux sandbox. |
drive_sandbox_exec | sandbox (experimental) | Run a shell command in the sandbox. |
drive_sandbox_read | sandbox (experimental) | Read a file from the sandbox filesystem. |
drive_sandbox_commit | sandbox (experimental) | Stage + commit the sandbox worktree. |
The drive_sandbox_* tools require the Cloudflare Containers plan on the AgentDrive
worker and degrade cleanly to a "not configured" message otherwise.
Agents lose context at every session boundary and every tool switch. AgentDrive is the shared substrate: one workspace, every agent, full provenance. Write once with Claude Code; recall it from Cursor; hand off to Codex — each call is attributed to the right principal and platform.
npm install
npm run build # tsc -> dist/
npm test # vitest
Apache-2.0. See LICENSE.
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