mcp server
AgentDrive
Cross-agent artifact workspace with provenance across Claude Code, Codex, Cursor, LangGraph.
Description as published by the maintainer. Source
- version 1.0.0
- active
active — Registry entry last updated 2026-06-04.
What this server can do
20 functions, named and described by the server itself. Parameter names are shown because they say more about what a function does than its name usually does.
drive_activity(workspace_id)- Get recent activity in a workspace (file writes, comments, shares). Required: workspace_id.
drive_comment(body, file_id, line_end, line_start, workspace_id)- Add a comment to a file. Required: workspace_id, file_id, body.
drive_context(task, limit, workspace_id)- 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. Required: task.
drive_delete(file_id, workspace_id)- Delete a file from a workspace. Required: workspace_id, file_id.
drive_feedback(file_id, workspace_id)- Read human comments on a file. Use this to check if humans have left feedback. Required: workspace_id, file_id.
drive_invite(role, email)- Invite a human to your organization by email. They will receive a verification code to join. Required: email.
drive_list(prefix, workspace_id)- List files in a workspace, optionally filtered by path prefix. Required: workspace_id.
drive_log_run(task, run_id, status, metadata, duration_ms, artifacts_produced, artifacts_referenced)- 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. Required: task.
drive_org- View your organization details: agents, members, plan, and usage.
drive_read(file_id, workspace_id)- Read a file's content from a workspace. Required: workspace_id, file_id.
drive_recall(query, top_k)- 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). Required: query.
drive_roles(email, action, permission, workspace_id)- Manage per-workspace role delegation. Assign, list, or remove access for specific emails (view/comment/edit). Required: workspace_id, action.
drive_sandbox_clone(url, depth, branch, workspace_id)- [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. Required: workspace_id, url.
drive_sandbox_commit(message, author_name, author_email, workspace_id)- [EXPERIMENTAL] Stage + commit the current sandbox worktree. Surfaces as an AgentDrive artifact at commits/<sha>.json. Requires Cloudflare Containers; degrades to 503 otherwise. Required: workspace_id, message.
drive_sandbox_exec(cmd, cwd, timeout_ms, workspace_id)- [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. Required: workspace_id, cmd.
drive_sandbox_read(path, workspace_id)- [EXPERIMENTAL] Read a file from the per-workspace sandbox filesystem (build artifacts, test output, logs). Requires Cloudflare Containers; degrades to 503 otherwise. Required: workspace_id, path.
drive_search(query, top_k, filter, workspace_id)- 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. Required: query.
drive_share(email, file_id, max_uses, expires_in, permission, workspace_id)- 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. Required: workspace_id, permission.
drive_versions(file_id, workspace_id)- View version history for a file in a workspace. Required: workspace_id, file_id.
drive_write(path, content, message, workspace_id)- Write a markdown file to a workspace. Creates or updates the file with automatic versioning. Required: workspace_id, path, content.
Last successful function declaration observed on . Source: https://mcp.agentdrive.sh/mcp. We list what the server declared; we do not call any of these functions.
Endpoint status observed on . Source: https://mcp.agentdrive.sh/mcp.
Signals
These are separate measurements of different things. They are deliberately not combined into one score, because a popularity number that mixes website traffic with saves and stars cannot be checked or acted on.
| Signal | Value | What it measures | Window | Observed | Source |
|---|---|---|---|---|---|
| Latest published version | 1.0.0 | Latest version string the maintainer published to the registry. | as of fetch | Model Context Protocol | |
| Registry record last updated | 2026-06-04 | When the registry record was last updated by its maintainer. | point in time | Model Context Protocol | |
| First listed in the MCP Registry | 2026-06-04 | Date this server was first published to the official MCP Registry. Not a usage or quality measure. | point in time | Model Context Protocol | |
| mcp tools declared | 20 tools | Number of functions the server itself declared when asked to list them. This is what the server offers an agent, not a measure of how well any of them work. | as of probe | mcp.agentdrive.sh | |
| mcp endpoint status | ok | The server listed 20 functions when asked. | as of probe | mcp.agentdrive.sh |
Where to get it
Also from rakesh1002
-
io.github.Rakesh1002/namemyapp
Brandable business names with live domain availability + one-click buy URLs.
-
io.github.Rakesh1002/reposcout
Discover, enrich, and rank GitHub repos for an objective with weighted, evidence-based scoring.
This record as data
Every field on this page, with its source and observation date, is in the catalog JSON. Fetch the whole kind at once instead of parsing this HTML.
GET /api/v1/entries/mcp_server.json