sh.agentdrive/agentdrive
Official20 toolsby Rakesh1002 · TypeScript
AgentDrive
Cross-agent artifact workspace with provenance across Claude Code, Codex, Cursor, LangGraph.
Shared artifact workspace with provenance tracking across multiple AI coding platforms.
Captured live from the server via tools/list.
drive_write
Write a markdown file to a workspace. Creates or updates the file with automatic versioning.
Parameters (4)
- workspace_idstringrequired
Workspace ID to write to
- pathstringrequired
File path (e.g. "notes/meeting.md")
- contentstringrequired
File content (markdown)
- messagestring
Optional version message
drive_read
Read a file's content from a workspace.
Parameters (2)
- workspace_idstringrequired
Workspace ID
- file_idstringrequired
File ID to read
drive_list
List files in a workspace, optionally filtered by path prefix.
Parameters (2)
- workspace_idstringrequired
Workspace ID
- prefixstring
Path prefix filter (e.g. "notes/")
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.
Parameters (6)
- workspace_idstringrequired
Workspace ID
- permissionstringrequired
Permission level for the share link
- file_idstring
Scope to a specific file (optional)
- expires_innumber
Expiry in seconds (optional)
- max_usesnumber
Maximum number of uses (optional)
- emailstring
Email-gate: only this email can access the link (requires email verification). Leave empty for public access.
drive_comment
Add a comment to a file.
Parameters (5)
- workspace_idstringrequired
Workspace ID
- file_idstringrequired
File ID to comment on
- bodystringrequired
Comment text
- line_startnumber
Start line number (optional)
- line_endnumber
End line number (optional)
drive_feedback
Read human comments on a file. Use this to check if humans have left feedback.
Parameters (2)
- workspace_idstringrequired
Workspace ID
- file_idstringrequired
File ID to read comments from
drive_activity
Get recent activity in a workspace (file writes, comments, shares).
Parameters (1)
- workspace_idstringrequired
Workspace ID
drive_invite
Invite a human to your organization by email. They will receive a verification code to join.
Parameters (2)
- emailstringrequired
Email address of the human to invite to your organization
- rolestring
Role in the organization (default: member)
drive_roles
Manage per-workspace role delegation. Assign, list, or remove access for specific emails (view/comment/edit).
Parameters (4)
- workspace_idstringrequired
Workspace ID
- actionstringrequired
Action: assign a role, list all roles, or remove a role
- emailstring
Email address (required for assign/remove)
- permissionstring
Permission level (required for assign)
drive_org
View your organization details: agents, members, plan, and usage.
No parameters.
drive_delete
Delete a file from a workspace.
Parameters (2)
- workspace_idstringrequired
Workspace ID
- file_idstringrequired
File ID to delete
drive_versions
View version history for a file in a workspace.
Parameters (2)
- workspace_idstringrequired
Workspace ID
- file_idstringrequired
File ID
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.
Parameters (4)
- querystringrequired
Search query
- workspace_idstring
Scope to a single workspace; omit for org-wide search
- top_kinteger
Max hits to return (default 10, max 50)
- filterobject
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).
Parameters (2)
- querystringrequired
Recall query — what fact, preference, or decision are you trying to remember?
- top_kinteger
Max results (default 5, max 20)
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.
Parameters (7)
- taskstringrequired
What the agent did or is doing (free text)
- statusstring
Run outcome (default success)
- run_idstring
Existing run ID to update; omit to let server allocate
- artifacts_referencedarray
Paths of artifacts the run read
- artifacts_producedarray
Paths of artifacts the run wrote
- duration_msinteger
Wall-clock duration in milliseconds
- metadataobject
Free-form key/value metadata
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 manual copy-paste of artifacts between sessions.
Parameters (3)
- taskstringrequired
What you are about to do — used to rank prior artifacts by relevance
- workspace_idstring
Scope to a single workspace; omit for org-wide context
- limitinteger
Max artifacts to return (default 5, max 20)
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.
Parameters (4)
- workspace_idstringrequired
Workspace to clone into. The sandbox persists across MCP sessions per workspace.
- urlstringrequired
Git repository URL to clone
- branchstring
Branch to check out (default: repo default)
- depthinteger
Shallow clone depth (default: full clone)
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.
Parameters (4)
- workspace_idstringrequired
Workspace whose sandbox to run in
- cmdstringrequired
Shell command to run inside the per-workspace Linux sandbox
- cwdstring
Working directory (default: workspace root)
- timeout_msinteger
Max runtime in ms (default 30000, hard cap 60000)
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.
Parameters (2)
- workspace_idstringrequired
Workspace whose sandbox to read from
- pathstringrequired
Path inside the sandbox (e.g., src/index.ts or /tmp/build.log)
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.
Parameters (4)
- workspace_idstringrequired
Workspace whose sandbox to commit
- messagestringrequired
Commit message
- author_namestring
Override git author name (default: agent identity)
- author_emailstring
Override git author email (default: agent identity)
README not available yet.
Install
claude_desktop_config.json
{
"mcpServers": {
"agentdrive": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://mcp.agentdrive.sh/mcp"
]
}
}
}Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.