Provides tools for auditing Appwrite project permissions, listing findings, and previewing fixes, enabling security audits from within AI assistants.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@appwrite-security-mcp scan my Appwrite project for security issues"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP server for Appwrite security audits. Scan permissions, get a structured fix proposal, all from inside Claude Code, Cursor, or Cline. Active probe confirms every leak live with an anonymous fetch.
Tool | What it does |
| Scans the Appwrite project, returns findings JSON. Active probe ON by default. Caches result. |
| Lists cached findings by index, optionally filtered by severity. |
| Describes the proposed permission change for a finding (Appwrite PATCH replaces the full perms array, not merges, so the agent constructs the new list manually). |
apply_fix is intentionally not in v0.1 because Appwrite permission updates are full-replacement — a partial agent diff would silently drop perms. Apply manually in the Appwrite console after preview_fix.
Related MCP server: aws-security-mcp
{
"mcpServers": {
"appwrite-security": {
"command": "npx",
"args": ["-y", "@perufitlife/appwrite-security-mcp"],
"env": {
"APPWRITE_ENDPOINT": "https://cloud.appwrite.io/v1",
"APPWRITE_PROJECT_ID": "...",
"APPWRITE_API_KEY": "..."
}
}
}
}API key needs scopes: databases.read, collections.read, projects.read.
MIT. Open source. Built by @Perufitlife.
For the standalone CLI, see https://github.com/Perufitlife/appwrite-security-skill For Supabase MCP, see https://github.com/Perufitlife/supabase-security-mcp For PocketBase MCP, see https://github.com/Perufitlife/pocketbase-security-mcp
Scan an Appwrite project for over-permissive collection/document permissions. Returns findings JSON with active-probe confirmation. Caches result for use by other tools.
Inputs: endpoint, project, key, no_probe.
List findings from the most recent audit, optionally filtered by severity.
Inputs: project, severity.
Describe the proposed permission change for a finding. Appwrite's permission update API replaces the full set, so the agent should output a complete replacement permission list rather than a delta.
Inputs: finding_index (required), project.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 3 tools
Each tool has a clearly distinct purpose: auditing, listing findings, and previewing fixes. No overlap or ambiguity.
All tool names follow a consistent verb_noun pattern in snake_case: audit_project, list_findings, preview_fix.
3 tools is well-scoped for a focused security audit tool; each serves a necessary function without bloat.
Covers the audit, listing, and preview workflow, but lacks an apply_fix tool to execute changes, leaving a notable gap in the lifecycle.
Security scanner for MCP servers. Detect vulnerabilities, prompt injection, and tool poisoning.
Audit your MCP servers for poisoned tools and leaked secrets, and check AI-generated code for flaws.
An MCP server for Arcjet - the runtime security platform that ships with your AI code.
MCP server: static security scanner for MCP servers, agent skills & plugins. 17 attack patterns.
