About Agentdrive
AgentDrive is a shared artifact workspace for cross-agent workflows, with persistent files, semantic recall, session handoffs, and provenance. It is intended for teams that need to carry context across agent platforms.
Key features
- 01Shared persistent workspace across agents
- 02Semantic search and fact recall
- 03Automatic file versioning
- 04Session logging and handoff recovery
- 05Activity logs and provenance attribution
Use cases
- 01Hand off tasks between agent platforms
- 02Find artifacts from prior work
- 03Resume recent project sessions
- 04Track agent runs and file activity
MCP support
As an MCP server, it exposes file, memory, session, collaboration, organization, and provenance tools to clients over stdio or a hosted Streamable HTTP endpoint.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://mcp.agentdrive.sh/mcpclaude mcp add --transport http agentdrive https://mcp.agentdrive.sh/mcp{"mcpServers":{"agentdrive":{"type":"http","url":"https://mcp.agentdrive.sh/mcp"}}}Open in Cursor{"servers":{"agentdrive":{"type":"http","url":"https://mcp.agentdrive.sh/mcp"}}}Open in VS Code{"mcpServers":{"agentdrive":{"type":"http","url":"https://mcp.agentdrive.sh/mcp"}}}{"mcpServers":{"agentdrive":{"serverUrl":"https://mcp.agentdrive.sh/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://mcp.agentdrive.sh/mcpAuth requiredTools
20| Parameter | Type | Required | Description |
|---|---|---|---|
| path | string | Yes | File path (e.g. "notes/meeting.md") |
| content | string | Yes | File content (markdown) |
| message | string | No | Optional version message |
| workspace_id | string | Yes | Workspace ID to write to |
Details
From the project READMEAgentDrive MCP Server
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.
- Website: https://agentdrive.sh
- Docs: https://agentdrive.sh/docs
- npm:
@adrive/mcp-server - Hosted endpoint:
https://mcp.agentdrive.sh/mcp
Claude Code plugin
This repo is also the Claude Code plugin marketplace. The plugin captures every session in the background and resumes it from Codex, OpenCode, Gemini CLI, or Cursor:
/plugin install agentdrive --marketplace Rakesh1002/agentdrive-mcp
On Claude Code older than 2.1.275, run /plugin marketplace add Rakesh1002/agentdrive-mcp
then /plugin install agentdrive@agentdrive. Sign in with /agentdrive:login.
Get an API key (free)
Create one at https://app.agentdrive.sh — no credit card. The free tier (1 workspace, 1 GB storage, 10k embeddings) is free indefinitely.
Two ways to connect
1. Hosted (no install) — Streamable HTTP
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.
2. Local (stdio) — via npx
{
"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:
claude_desktop_config.json - Cursor:
~/.cursor/mcp.json - Claude Code: install the plugin (see above), which also captures sessions
- Codex / Cline / Continue / Zed: the standard
mcpServersblock above
The fastest path is the AgentDrive installer, which auto-wires every detected host:
curl -fsSL agentdrive.sh/install | sh
Configuration
| Env var | Required | Default | Description |
|---|---|---|---|
AGENTDRIVE_API_KEY | no | key saved by adrive auth login | Your AgentDrive API key (agentdrive_live_...). Falls back to ~/.config/agentdrive/config.json, so client configs never need the key inline. |
AGENTDRIVE_API_URL | no | https://app.agentdrive.sh | Override the API endpoint (self-hosted worker). |
AGENTDRIVE_AGENT_PLATFORM | no | unknown | Which agent runtime is calling — drives cross-agent provenance. One of claude-code, codex, opencode, gemini-cli, cursor, langgraph, crewai, autogen, hermes, openclaw, unknown. |
AGENTDRIVE_AGENT_ROLE | no | — | Free-text role label (e.g. planner, reviewer) to distinguish multiple agents on the same platform. |
Tools
22 tools across files, memory, sessions, collaboration, org, and provenance. The stdio server derives the current project from its working directory (git remote, else repo path), which scopes drive_sessions and drive_resume.
| 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_sessions | sessions | List recent agent sessions for this project across Claude Code, Codex, OpenCode, Gemini CLI, and Cursor. |
drive_resume | sessions | Load a compact handoff (goal, files touched, recent turns) from a prior session, by default the latest from a different harness. |
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.
Why AgentDrive
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.
Develop
npm install
npm run build # tsc -> dist/
npm test # vitest
License
Apache-2.0. See LICENSE.
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.