# AgentDrive

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

- name: sh.agentdrive/agentdrive
- version: 1.0.0
- connection class: R1 (autonomous)
- trust: 88/100
- quality: 79/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/sh.agentdrive%2Fagentdrive
- tools: https://api.protogrid.dev/v1/servers/sh.agentdrive%2Fagentdrive/tools

**An agent can connect on its own if it already holds `AGENTDRIVE_TOKEN`.** Remote endpoint behind a static API key or header. The registry never sees the value; the agent fills the placeholder.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "agentdrive": {
      "type": "http",
      "url": "https://mcp.agentdrive.sh/mcp",
      "headers": {
        "Authorization": "Bearer ${AGENTDRIVE_TOKEN}"
      }
    }
  }
}
```

Placeholders to fill: `${AGENTDRIVE_TOKEN}`.

## Trust

- hygiene: 100
- liveness: 99
- freshness: 65
- provenance: 85
- drivers: +repository +dns-namespace +website +reachable +uptime-98% ~updated-137d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 79/100 (good)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 71 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- fail `tools.annotations`: no tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: drive_write (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); drive_read (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); drive_list (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …
- pass `tools.token_cost`: about 2,650 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 100 (weight 15)

- pass `stability.changes`: no tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 20, about 2,650 tokens to load them all
- tool set hash: edd42681c561669a7e38bc1018c51332
- badge: [![protogrid quality](https://protogrid.dev/badge/sh.agentdrive/agentdrive.svg)](https://protogrid.dev/servers/sh.agentdrive/agentdrive)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

_No tool definition changes recorded._

## Remotes

- https://mcp.agentdrive.sh/mcp (streamable-http, auth api_key ${AGENTDRIVE_TOKEN}, reachable true, uptime30d 0.982906)

## Packages

_none_

## Tools (20)

- `drive_activity`: Get recent activity in a workspace (file writes, comments, shares).
- `drive_comment`: Add a comment to a file.
- `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.
- `drive_delete`: Delete a file from a workspace.
- `drive_feedback`: Read human comments on a file. Use this to check if humans have left feedback.
- `drive_invite`: Invite a human to your organization by email. They will receive a verification code to join.
- `drive_list`: List files in a workspace, optionally filtered by path 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.
- `drive_org`: View your organization details: agents, members, plan, and usage.
- `drive_read`: Read a file's content from a workspace.
- `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).
- `drive_roles`: Manage per-workspace role delegation. Assign, list, or remove access for specific emails (view/comment/edit).
- `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.
- `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.
- `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.
- `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.
- `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.
- `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.
- `drive_versions`: View version history for a file in a workspace.
- `drive_write`: Write a markdown file to a workspace. Creates or updates the file with automatic versioning.