AgentDrive MCP server

AgentDrive is an MCP server with 20 tools an agent can call, among them drive_activity, drive_comment, drive_context. It answers at https://mcp.agentdrive.sh/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 6 of 6 times since 12 September 2026; the last check, on 24 October 2026, succeeded.

Status

Answering

Tools

Official

yes, served from agentdrive.sh

Reliability

6 of 6 checks

Response time

426 ms

Transport

streamable HTTP

Last checked

24 October 2026

Cross-agent artifact workspace with provenance across Claude Code, Codex, Cursor, LangGraph.

Description as the publisher wrote it.

The 20 tools AgentDrive offers

Tool	What it does
`drive_activity`	Get recent activity in a workspace (file writes, comments, shares). Inputs: workspace_id
`drive_comment`	Add a comment to a file. Inputs: workspace_id, file_id, body, line_start, line_end
`drive_context`	Auto-pull the most relevant artifacts from prior agent sessions for the task you are about to do. Combines semantic relevance with recency. Call this at the START of any non-trivial task to ground the agent in prior context — replaces manua Inputs: task, workspace_id, limit
`drive_delete`	Delete a file from a workspace. Inputs: workspace_id, file_id
`drive_feedback`	Read human comments on a file. Use this to check if humans have left feedback. Inputs: workspace_id, file_id
`drive_invite`	Invite a human to your organization by email. They will receive a verification code to join. Inputs: email, role
`drive_list`	List files in a workspace, optionally filtered by path prefix. Inputs: workspace_id, prefix
`drive_log_run`	Log an agent run to AgentDrive's provenance store. Captures task, status, referenced/produced artifacts, and cross-platform identity (which agent on which tool). Used for retrospective context retrieval and team-wide audit. Inputs: task, status, run_id, artifacts_referenced, artifacts_produced, duration_ms
`drive_org`	View your organization details: agents, members, plan, and usage.
`drive_read`	Read a file's content from a workspace. Inputs: workspace_id, file_id
`drive_recall`	Recall persistent facts and preferences your agents have written. In v1 this returns semantic search results across artifacts; v1.5 will narrow to auto-extracted facts (preferences, decisions, key entities). Inputs: query, top_k
`drive_roles`	Manage per-workspace role delegation. Assign, list, or remove access for specific emails (view/comment/edit). Inputs: workspace_id, action, email, permission
`drive_sandbox_clone`	[EXPERIMENTAL] Clone a git repo into a per-workspace Linux sandbox. Requires Cloudflare Containers on the AgentDrive worker; gracefully degrades to a 503 with "sandbox not configured" otherwise. Inputs: workspace_id, url, branch, depth
`drive_sandbox_commit`	[EXPERIMENTAL] Stage + commit the current sandbox worktree. Surfaces as an AgentDrive artifact at commits/<sha>.json. Requires Cloudflare Containers; degrades to 503 otherwise. Inputs: workspace_id, message, author_name, author_email
`drive_sandbox_exec`	[EXPERIMENTAL] Run a shell command inside the per-workspace Linux sandbox. Captures stdout/stderr (64 KB cap), exit code, duration. Requires Cloudflare Containers; degrades to 503 otherwise. Inputs: workspace_id, cmd, cwd, timeout_ms
`drive_sandbox_read`	[EXPERIMENTAL] Read a file from the per-workspace sandbox filesystem (build artifacts, test output, logs). Requires Cloudflare Containers; degrades to 503 otherwise. Inputs: workspace_id, path
`drive_search`	Semantic search across your org's artifacts in AgentDrive. Returns the top-N most relevant files. Use this BEFORE writing similar artifacts to avoid duplication and surface prior context. Inputs: query, workspace_id, top_k, filter
`drive_share`	Generate a share link for a workspace or specific file. Optionally email-gate the link so only a specific person can access it. Humans open this link to view, comment, or edit files. Inputs: workspace_id, permission, file_id, expires_in, max_uses, email
`drive_versions`	View version history for a file in a workspace. Inputs: workspace_id, file_id
`drive_write`	Write a markdown file to a workspace. Creates or updates the file with automatic versioning. Inputs: workspace_id, path, content, message

Add AgentDrive to your AI client

Every block below points at https://mcp.agentdrive.sh/mcp. Pick your client and copy.

Claude Code: one command in your terminal

claude mcp add --transport http agentdrive https://mcp.agentdrive.sh/mcp

Claude Desktop: claude_desktop_config.json

{
  "mcpServers": {
    "agentdrive": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://mcp.agentdrive.sh/mcp"]
    }
  }
}

Cursor: ~/.cursor/mcp.json, or .cursor/mcp.json in a project

{
  "mcpServers": {
    "agentdrive": {
      "url": "https://mcp.agentdrive.sh/mcp"
    }
  }
}

VS Code and GitHub Copilot: .vscode/mcp.json

{
  "servers": {
    "agentdrive": {
      "type": "http",
      "url": "https://mcp.agentdrive.sh/mcp"
    }
  }
}

Zed: Zed settings.json

{
  "context_servers": {
    "agentdrive": {
      "url": "https://mcp.agentdrive.sh/mcp"
    }
  }
}

Windsurf: ~/.codeium/mcp_config.json

{
  "mcpServers": {
    "agentdrive": {
      "serverUrl": "https://mcp.agentdrive.sh/mcp"
    }
  }
}

JetBrains AI Assistant: Settings, Tools, AI Assistant, MCP, New MCP Server, as JSON

{
  "mcpServers": {
    "agentdrive": {
      "url": "https://mcp.agentdrive.sh/mcp"
    }
  }
}

Continue: .continue/mcpServers/neuronto.yaml

name: AgentDrive
version: 0.0.1
schema: v1
mcpServers:
  - name: AgentDrive
    type: streamable-http
    url: https://mcp.agentdrive.sh/mcp

Gemini CLI: ~/.gemini/settings.json

{
  "mcpServers": {
    "agentdrive": {
      "httpUrl": "https://mcp.agentdrive.sh/mcp"
    }
  }
}

Codex CLI: MCP server config

{
  "mcpServers": {
    "agentdrive": {
      "type": "http",
      "url": "https://mcp.agentdrive.sh/mcp"
    }
  }
}

Warp: MCP servers, + Add, paste JSON

{
  "mcpServers": {
    "agentdrive": {
      "url": "https://mcp.agentdrive.sh/mcp"
    }
  }
}

Goose: a one-click extension link

goose://extension?url=https%3A%2F%2Fmcp.agentdrive.sh%2Fmcp&type=streamable_http&id=agentdrive&name=AgentDrive

Is AgentDrive up right now?

It answered our last check on 24 October 2026 in 426 ms. Over 6 checks since 12 September 2026 it answered 6. Status here comes from Neuronto's own probes, not from the publisher.

MCP servers similar to AgentDrive

Axis0 tools Sprawl0 tools AgentDrive0 tools AgentSite10 tools mFlow0 tools Contextflo0 tools

Questions about AgentDrive

Is there an official AgentDrive MCP server?

Yes. It is published by agentdrive.sh and served from mcp.agentdrive.sh, the vendor's own domain: https://mcp.agentdrive.sh/mcp.

How many tools does AgentDrive have?

20, as returned by the server's own tools/list on 23 September 2026: drive_activity, drive_comment, drive_context, drive_delete, drive_feedback, drive_invite, drive_list, drive_log_run, and 12 more.

Is AgentDrive down?

It answered our last check on 24 October 2026 in 426 ms. Over 6 checks since 12 September 2026 it answered 6.

How do I add AgentDrive to Cursor?

Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://mcp.agentdrive.sh/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.

Does AgentDrive need an API key?

It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.

Where this comes from

Publisher: sh.agentdrive. Endpoint host: mcp.agentdrive.sh. ARD identifier: urn:air:sh.agentdrive:mcp:agentdrive. First indexed 10 September 2026. The tools are exactly what the server returned; nothing on this page is inferred from its name. Ranking in Neuronto search is never for sale.

Is this your server? Get a message the day it stops answering or its tools change: monitoring, 14 days free. Or claim the domain to manage how it is listed.