How we label
Every tool gets two labels: what it can do out of the box, and what it can do with our preset. Both are provisional until we've tested them.
Classes
- Read-only
- Documented as read-only: every tool the vendor lists only reads. Not yet confirmed in our sandbox.
- Can write
- Can create or change things, but not delete.
- Can delete
- Can delete, destroy, or run arbitrary commands.
- Unknown
- We have not found a source for what it can do. Treat it as able to write.
- No read-only mode
- We found no read-only switch. The credential you give it is the only control.
A server gets the class of its most dangerous tool. A Kubernetes server with 40 read tools and one delete_pod is "Can delete".
Flags
- exec
- Can run commands (e.g. exec into a pod or run a CLI).
- secrets
- Can read secrets or sensitive data like logs.
- egress
- Sends data to a third-party service.
- hosted
- Vendor-hosted endpoint; you cannot inspect the server code.
Verification status
- From docs, not tested yet
- We read the project's docs or source and wrote the preset from them. We have not run it. Every preset on the site is in this state today.
- Sandbox-tested
- Planned. We run the preset against a throwaway cluster/account, call each write tool directly (not just check the tool list), and publish the log with the server version and date.
Why call tools directly? Because in CVE-2026-46519 a read-only mode hid write tools from the list but still let clients call them.
The three layers
- Credential: read-only RBAC, IAM role or token scope. The only layer that's a real boundary.
- Server flag: the server's own read-only mode. Our presets set this.
- Agent rules: Claude Code
permissions.deny(mcp__server__tool), Codexdefault_tools_approval_modeanddisabled_tools, CursormcpAllowlistinpermissions.json. Useful, but Cursor's docs call allowlists "not a security boundary". MCP'sreadOnlyHintis a hint, not enforcement.
Client formats we follow
Each preset is written in the format the client documents. These are the pages we checked (Nov 3, 2026):
- Claude Code: MCP :
.mcp.json; remote servers need"type": "http";${VAR}and${VAR:-default}expansion - Claude Code: permissions :
mcp__serverandmcp__server__toolrules in.claude/settings.json - Codex: MCP :
[mcp_servers.name]in~/.codex/config.toml,env_http_headers,bearer_token_env_var,default_tools_approval_mode - Cursor: MCP :
.cursor/mcp.json;${env:NAME}interpolation - Cursor: permissions.json :
mcpAllowlist; "Not a security boundary"
Sources and dates
Every claim links the page we read and the date we read it. GitHub stats come from the GitHub API and are refreshed by a script that flags changes (stars, releases, archived, renamed, license). If a repo hasn't been pushed in 180 days we mark it stale.
What we don't do
- We don't accept payment for labels. Affiliate links, if any, are disclosed on the page and never change a label.
- We don't invent incidents. If a story is disputed, we say so and link both sides.