mcpField
A
Agentdrive

Agentdrive

Remote
agentdrive.shAI & Agents0Updated 1w ago

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

  1. 01Shared persistent workspace across agents
  2. 02Semantic search and fact recall
  3. 03Automatic file versioning
  4. 04Session logging and handoff recovery
  5. 05Activity logs and provenance attribution

Use cases

  1. 01Hand off tasks between agent platforms
  2. 02Find artifacts from prior work
  3. 03Resume recent project sessions
  4. 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.

Endpointhttps://mcp.agentdrive.sh/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

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.

All endpoints
Streamable HTTPhttps://mcp.agentdrive.sh/mcpAuth required

Tools

20
ParameterTypeRequiredDescription
pathstringYesFile path (e.g. "notes/meeting.md")
contentstringYesFile content (markdown)
messagestringNoOptional version message
workspace_idstringYesWorkspace ID to write to

Details

From the project README

AgentDrive 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.

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 mcpServers block above

The fastest path is the AgentDrive installer, which auto-wires every detected host:

curl -fsSL agentdrive.sh/install | sh

Configuration

Env varRequiredDefaultDescription
AGENTDRIVE_API_KEYnokey saved by adrive auth loginYour AgentDrive API key (agentdrive_live_...). Falls back to ~/.config/agentdrive/config.json, so client configs never need the key inline.
AGENTDRIVE_API_URLnohttps://app.agentdrive.shOverride the API endpoint (self-hosted worker).
AGENTDRIVE_AGENT_PLATFORMnounknownWhich 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_ROLEno—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.

ToolCategoryDescription
drive_contextmemoryAuto-pull the most relevant prior artifacts for the task you're starting.
drive_searchmemorySemantic search across your org's artifacts.
drive_recallmemoryRecall persistent facts/preferences agents have written.
drive_sessionssessionsList recent agent sessions for this project across Claude Code, Codex, OpenCode, Gemini CLI, and Cursor.
drive_resumesessionsLoad a compact handoff (goal, files touched, recent turns) from a prior session, by default the latest from a different harness.
drive_writefilesWrite a markdown file (auto-versioned).
drive_readfilesRead a file's content.
drive_listfilesList files in a workspace.
drive_deletefilesDelete a file.
drive_versionsfilesView a file's version history.
drive_sharecollaborationGenerate a (optionally email-gated) share link.
drive_commentcollaborationComment on a file.
drive_feedbackcollaborationRead human comments on a file.
drive_activityprovenanceRecent workspace activity (writes, comments, shares).
drive_log_runprovenanceLog an agent run (task, status, artifacts, identity).
drive_inviteorgInvite a human to your org by email.
drive_rolesorgAssign/list/remove per-workspace access by email.
drive_orgorgView org details: agents, members, plan, usage.
drive_sandbox_clonesandbox (experimental)Clone a git repo into a per-workspace Linux sandbox.
drive_sandbox_execsandbox (experimental)Run a shell command in the sandbox.
drive_sandbox_readsandbox (experimental)Read a file from the sandbox filesystem.
drive_sandbox_commitsandbox (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

Markdown supported

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.