# AgentDrive (remote · mcp.agentdrive.sh)

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

- Trust score: 62/100 (medium)
- Change this week: +2
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `mcp.agentdrive.sh`: 62/100 (this document), [markdown](https://verifymcp.io/servers/sh-agentdrive-agentdrive/mcp.md), [page](https://verifymcp.io/servers/sh-agentdrive-agentdrive/mcp)

## Channel facts

- Endpoint: `https://mcp.agentdrive.sh/mcp`
- Transports: `streamable-http`
- Auth: `required`
- Version: `1.0.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Endpoint Security**: 46/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 20 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS not yet verified: we couldn't determine whether a plaintext access path exists.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 71/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 1805 tokens (~90/item across 20 items; 20 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 99/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 98% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

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

### Codex

```toml
[mcp_servers.sh-agentdrive-agentdrive]
url = "https://mcp.agentdrive.sh/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "sh-agentdrive-agentdrive": {
      "type": "remote",
      "url": "https://mcp.agentdrive.sh/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add sh-agentdrive-agentdrive --url https://mcp.agentdrive.sh/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  sh-agentdrive-agentdrive:
    url: "https://mcp.agentdrive.sh/mcp"
```

### Other

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

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-03 (score 62, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-01 (score 61, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-31 (score 60, −2)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 62, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-28 (score 61, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-27 (score 60, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-26 (score 59)

First indexed and scored.

## MCP tools (20)

### `drive_write` (~78 tokens)

Write a markdown file to a workspace. Creates or updates the file with automatic versioning.

Input parameters:

- `content` (string, required): File content (markdown)
- `message` (string): Optional version message
- `path` (string, required): File path (e.g. "notes/meeting.md")
- `workspace_id` (string, required): Workspace ID to write to

### `drive_read` (~39 tokens)

Read a file's content from a workspace.

Input parameters:

- `file_id` (string, required): File ID to read
- `workspace_id` (string, required): Workspace ID

### `drive_list` (~46 tokens)

List files in a workspace, optionally filtered by path prefix.

Input parameters:

- `prefix` (string): Path prefix filter (e.g. "notes/")
- `workspace_id` (string, required): Workspace ID

### `drive_share` (~143 tokens)

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.

Input parameters:

- `email` (string): Email-gate: only this email can access the link (requires email verification). Leave empty for public access.
- `expires_in` (number): Expiry in seconds (optional)
- `file_id` (string): Scope to a specific file (optional)
- `max_uses` (number): Maximum number of uses (optional)
- `permission` (string, required): Permission level for the share link
- `workspace_id` (string, required): Workspace ID

### `drive_comment` (~73 tokens)

Add a comment to a file.

Input parameters:

- `body` (string, required): Comment text
- `file_id` (string, required): File ID to comment on
- `line_end` (number): End line number (optional)
- `line_start` (number): Start line number (optional)
- `workspace_id` (string, required): Workspace ID

### `drive_feedback` (~49 tokens)

Read human comments on a file. Use this to check if humans have left feedback.

Input parameters:

- `file_id` (string, required): File ID to read comments from
- `workspace_id` (string, required): Workspace ID

### `drive_activity` (~32 tokens)

Get recent activity in a workspace (file writes, comments, shares).

Input parameters:

- `workspace_id` (string, required): Workspace ID

### `drive_invite` (~59 tokens)

Invite a human to your organization by email. They will receive a verification code to join.

Input parameters:

- `email` (string, required): Email address of the human to invite to your organization
- `role` (string): Role in the organization (default: member)

### `drive_roles` (~88 tokens)

Manage per-workspace role delegation. Assign, list, or remove access for specific emails (view/comment/edit).

Input parameters:

- `action` (string, required): Action: assign a role, list all roles, or remove a role
- `email` (string): Email address (required for assign/remove)
- `permission` (string): Permission level (required for assign)
- `workspace_id` (string, required): Workspace ID

### `drive_org` (~22 tokens)

View your organization details: agents, members, plan, and usage.

### `drive_delete` (~37 tokens)

Delete a file from a workspace.

Input parameters:

- `file_id` (string, required): File ID to delete
- `workspace_id` (string, required): Workspace ID

### `drive_versions` (~38 tokens)

View version history for a file in a workspace.

Input parameters:

- `file_id` (string, required): File ID
- `workspace_id` (string, required): Workspace ID

### `drive_search` (~96 tokens)

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.

Input parameters:

- `filter` (object)
- `query` (string, required): Search query
- `top_k` (integer): Max hits to return (default 10, max 50)
- `workspace_id` (string): Scope to a single workspace; omit for org-wide search

### `drive_recall` (~89 tokens)

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).

Input parameters:

- `query` (string, required): Recall query — what fact, preference, or decision are you trying to remember?
- `top_k` (integer): Max results (default 5, max 20)

### `drive_log_run` (~156 tokens)

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.

Input parameters:

- `artifacts_produced` (array): Paths of artifacts the run wrote
- `artifacts_referenced` (array): Paths of artifacts the run read
- `duration_ms` (integer): Wall-clock duration in milliseconds
- `metadata` (object): Free-form key/value metadata
- `run_id` (string): Existing run ID to update; omit to let server allocate
- `status` (string): Run outcome (default success)
- `task` (string, required): What the agent did or is doing (free text)

### `drive_context` (~124 tokens)

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.

Input parameters:

- `limit` (integer): Max artifacts to return (default 5, max 20)
- `task` (string, required): What you are about to do — used to rank prior artifacts by relevance
- `workspace_id` (string): Scope to a single workspace; omit for org-wide context

### `drive_sandbox_clone` (~118 tokens)

[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.

Input parameters:

- `branch` (string): Branch to check out (default: repo default)
- `depth` (integer): Shallow clone depth (default: full clone)
- `url` (string, required): Git repository URL to clone
- `workspace_id` (string, required): Workspace to clone into. The sandbox persists across MCP sessions per workspace.

### `drive_sandbox_exec` (~124 tokens)

[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.

Input parameters:

- `cmd` (string, required): Shell command to run inside the per-workspace Linux sandbox
- `cwd` (string): Working directory (default: workspace root)
- `timeout_ms` (integer): Max runtime in ms (default 30000, hard cap 60000)
- `workspace_id` (string, required): Workspace whose sandbox to run in

### `drive_sandbox_read` (~84 tokens)

[EXPERIMENTAL] Read a file from the per-workspace sandbox filesystem (build artifacts, test output, logs). Requires Cloudflare Containers; degrades to 503 otherwise.

Input parameters:

- `path` (string, required): Path inside the sandbox (e.g., src/index.ts or /tmp/build.log)
- `workspace_id` (string, required): Workspace whose sandbox to read from

### `drive_sandbox_commit` (~107 tokens)

[EXPERIMENTAL] Stage + commit the current sandbox worktree. Surfaces as an AgentDrive artifact at commits/<sha>.json. Requires Cloudflare Containers; degrades to 503 otherwise.

Input parameters:

- `author_email` (string): Override git author email (default: agent identity)
- `author_name` (string): Override git author name (default: agent identity)
- `message` (string, required): Commit message
- `workspace_id` (string, required): Workspace whose sandbox to commit

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/sh-agentdrive-agentdrive/mcp#diagnostics

## Score history

- 2026-08-03: 62
- 2026-08-02: 61
- 2026-08-01: 61
- 2026-07-31: 60
- 2026-07-30: 62
- 2026-07-29: 61
- 2026-07-28: 61
- 2026-07-27: 60
- 2026-07-26: 59

## Links

- Remote endpoint: https://mcp.agentdrive.sh/mcp
- Authorisation metadata: https://mcp.agentdrive.sh/.well-known/oauth-protected-resource/mcp
- Repository: https://github.com/Rakesh1002/agentdrive-mcp
- Website: https://agentdrive.sh/
- Changelog RSS feed: https://verifymcp.io/servers/sh-agentdrive-agentdrive/mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/sh-agentdrive-agentdrive/mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/sh-agentdrive-agentdrive/mcp