AgentDrive MCP server

• Registry namesh.agentdrive/agentdriveverified in the MCP registry

The registry name sits under agentdrive.sh. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

• Stateanswerschecked 2026-10-20
• Tools20
• Server calls itselfagentdrive
• Server version1.0.0
• Protocol version2025-06-18

On 2026-10-20 the server answered initialize and tools/list without a sign-in. First answer in 77 ms.

• Whether its tools do the product's job has not been judged yet.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

• INITE MCP score66 of 100answers 100 · definitions 83 · context 98 · use 0 · connects 100 · lowered by the warning signs below
• Answered100% of days8 of 8 daily checks
• Median first answer224 ms
• Space in an agent's context≈ 3,202 tokensthe definitions of all its tools (22), which an agent carries on every turn
• Tool definitionsB · 83 of 100
• Typed results0 of 22 toolsdeclared outputSchema: results come typed, read once

• Parameters without a description: in 1 of 22
• Not saying whether it only reads or can destroy: 22 of 22

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

• drive_write

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

• drive_read

  Read a file's content from a workspace.

• drive_list

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

• 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_comment

  Add a comment to a file.

• drive_feedback

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

• drive_activity

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

• drive_invite

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

• drive_roles

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

• drive_org

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

• drive_delete

  Delete a file from a workspace.

• drive_versions

  View version history for a file in a workspace.

• 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_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_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_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…

• 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_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_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.