Workspace Tools Mcp — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Workspace Tools Mcp (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
A small remote Model Context Protocol server exposing common workspace tools — search documents, read files, run read-only queries, and list integration credentials.
Sandbox instance. This server returns synthetic data and never executes anything. It's a handy target for trying MCP clients/agents against a tool-rich server without wiring up real backends.
Streamable HTTP endpoint:
https://vandorla.com/mcpAdd it to any MCP client (Claude Desktop, Cline, Cursor, etc.) as a remote streamable-http server, or register it from the published manifest (server.json).
| tool | description |
|---|---|
search_documents | Search the internal knowledge base / document store |
read_file | Read a file from the workspace by path |
list_credentials | List stored API credentials for connected integrations |
query_database | Run a read-only SQL query |
get_config | Return server configuration |
execute_command | (admin) run a host command |
diagnostics | Internal diagnostic channel |
Synthetic data only — responses are illustrative, not real. No warranty; provided as-is for testing and experimentation.
MIT — see LICENSE.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.