Loading…
Cross-agent artifact workspace with provenance tracking across Claude Code, Codex, Cursor, and LangGraph.
Do not connect
A critical issue was found. Do not connect this server as-is.
Scanned 6 days ago
A server can change after it's graded. Re-run the automated scan to refresh this report.
This grade is deterministic and reproducible: the same server surface always yields the same grade under a given algorithm version. It is a real automated assessment computed by the MCPGrade engine from what the probe actually observed — not a fabricated or opinion score. It is not a manual human pentest, so it can miss context-specific risks.
Every signal below was measured directly by the automated probe. The grade is derived only from evidence like this — nothing is assumed.
The agentdrive MCP server exposes 20 tools, focused primarily on developer capabilities. Its published description reads: "Cross-agent artifact workspace with provenance tracking across Claude Code, Codex, Cursor, and LangGraph". It communicates over Streamable HTTP using the 2026-07-28 protocol revision, and does not require authorization to connect. MCPGrade currently rates agentdrive F — a critical issue was found and the server should not be connected as-is. Its most notable findings include "Unguarded destructive tools" and "Unguarded destructive tools". This report is a deterministic, reproducible automated assessment: the same observed surface always yields the same grade under a given algorithm version, and it is refreshed as new scans arrive and free to read — but it is not a substitute for a manual human security review. Always re-check agentdrive's advertised tools, transport security, and authorization posture before connecting an autonomous agent or sharing sensitive context with it.
Add agentdrive to an MCP client using the endpoint below. Review the grade and findings above before granting an autonomous agent access.
MCP endpoint
https://mcp.agentdrive.sh/mcpStreamable HTTP transport. This is the MCP endpoint, not a website — paste it into your MCP client server list rather than a browser.
Captured passively during the read-only scan. Click any value to find servers that match it.
The tools this server advertises via tools/list — names, purposes, and the parameters each accepts, exactly as enumerated read-only.
Write a markdown file to a workspace. Creates or updates the file with automatic versioning.
Read a file's content from a workspace.
List files in a workspace, optionally filtered by path prefix.
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.
Sorted worst-first. Each finding shows its severity, what it means, its OWASP MCP Top-10 mapping, and a recommended fix — the check id links to the exact methodology row that produced it.
tool: drive_write
Tools that execute commands / write files / make arbitrary requests are exposed without annotations or guards.
drive_write Write a markdown file to a workspace. Creates or updates the file witRecommendationAnnotate destructive tools and require human approval.
tool: drive_delete
Tools that execute commands / write files / make arbitrary requests are exposed without annotations or guards.
drive_delete Delete a file from a workspace. {"type":"object","properties"RecommendationAnnotate destructive tools and require human approval.
tool: drive_sandbox_clone
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "url"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: drive_sandbox_exec
Tools that execute commands / write files / make arbitrary requests are exposed without annotations or guards.
RIMENTAL] Run a shell command inside the per-workspace Linux sandbox.RecommendationAnnotate destructive tools and require human approval.
tool: drive_sandbox_exec
An exec/shell/run-code tool exposes a command/code/args parameter that is a free-form string with no enum/pattern guard — a direct command-injection / RCE surface. A tool constraining the command to an `enum` of allowed operations does not fire.
unconstrained command parameter "cmd"RecommendationReplace the free-form command with a fixed `enum` of allowed operations (or structured, escaped arguments) and require explicit human approval.
tool: drive_sandbox_commit
A tool description tries to alter the model’s use of another tool.
RecommendationDescriptions must describe only their own tool.
tool: (server instructions)
A tool description tries to alter the model’s use of another tool.
g work:** call `drive_write` for any artifact worth keeping so the next aRecommendationDescriptions must describe only their own tool.
The server accepts tool enumeration (and likely invocation) with no authentication.
RecommendationRequire OAuth 2.1 authorization for any server exposing non-public tools.
tool: drive_write
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "drive_write"RecommendationScope tools to the minimum needed.
tool: drive_write
A filesystem tool exposes a path parameter that is a free-form string with no pattern/enum/format constraint, so it accepts absolute paths and "../" traversal. A tool that constrains its path (a rooted `pattern` or an `enum`) does not fire.
unconstrained path parameter "path"RecommendationConstrain the path parameter to a rooted allow-list and reject absolute/traversal paths server-side.
tool: drive_read
A filesystem tool exposes a path parameter that is a free-form string with no pattern/enum/format constraint, so it accepts absolute paths and "../" traversal. A tool that constrains its path (a rooted `pattern` or an `enum`) does not fire.
unconstrained path parameter "file_id"RecommendationConstrain the path parameter to a rooted allow-list and reject absolute/traversal paths server-side.
tool: drive_share
A filesystem tool exposes a path parameter that is a free-form string with no pattern/enum/format constraint, so it accepts absolute paths and "../" traversal. A tool that constrains its path (a rooted `pattern` or an `enum`) does not fire.
unconstrained path parameter "file_id"RecommendationConstrain the path parameter to a rooted allow-list and reject absolute/traversal paths server-side.
tool: drive_feedback
A filesystem tool exposes a path parameter that is a free-form string with no pattern/enum/format constraint, so it accepts absolute paths and "../" traversal. A tool that constrains its path (a rooted `pattern` or an `enum`) does not fire.
unconstrained path parameter "file_id"RecommendationConstrain the path parameter to a rooted allow-list and reject absolute/traversal paths server-side.
tool: drive_activity
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "drive_activity"RecommendationScope tools to the minimum needed.
tool: drive_roles
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "drive_roles"RecommendationScope tools to the minimum needed.
tool: drive_delete
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "drive_delete"RecommendationScope tools to the minimum needed.
tool: drive_delete
A filesystem tool exposes a path parameter that is a free-form string with no pattern/enum/format constraint, so it accepts absolute paths and "../" traversal. A tool that constrains its path (a rooted `pattern` or an `enum`) does not fire.
unconstrained path parameter "file_id"RecommendationConstrain the path parameter to a rooted allow-list and reject absolute/traversal paths server-side.
tool: drive_sandbox_read
A filesystem tool exposes a path parameter that is a free-form string with no pattern/enum/format constraint, so it accepts absolute paths and "../" traversal. A tool that constrains its path (a rooted `pattern` or an `enum`) does not fire.
unconstrained path parameter "path"RecommendationConstrain the path parameter to a rooted allow-list and reject absolute/traversal paths server-side.
Vantaj uptime monitoring via MCP — manage monitors, heartbeats, incidents, and status pages.
Unified gateway to Algeria's TKAWEN ecosystem: commerce, certification, and AI tools.
Provides access to the Cohereon Doctrine AI safety framework with governance components, tiered access, and agent onboarding.
Agentic rails for complex workflows with receipts, fees, and MCP tool access.
Structural TC39 spec lookup for ECMA-262 and ECMA-402 in AI agents, SHA-pinned and offline-first.
Structural TC39 spec lookup for ECMA-262 and ECMA-402 in AI agents, SHA-pinned and offline-first.
Add a comment to a file.
Read human comments on a file. Use this to check if humans have left feedback.
Get recent activity in a workspace (file writes, comments, shares).
Invite a human to your organization by email. They will receive a verification code to join.
Manage per-workspace role delegation. Assign, list, or remove access for specific emails (view/comment/edit).
View your organization details: agents, members, plan, and usage.
Delete a file from a workspace.
View version history for a file in a workspace.
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.
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 ent
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 retriev
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
[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.
[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.
[EXPERIMENTAL] Read a file from the per-workspace sandbox filesystem (build artifacts, test output, logs). Requires Cloudflare Containers; degrades to 503 otherwise.
[EXPERIMENTAL] Stage + commit the current sandbox worktree. Surfaces as an AgentDrive artifact at commits/<sha>.json. Requires Cloudflare Containers; degrades to 503 otherwise.