// SCAN REPORT

Algorithmaide

23 tools. 12 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated: 12 Jun 2026

12 can modify or destroy data

11 read-only

23 tools total

Community server · catalogue entry verified 12/06/2026

How to control Algorithmaide ↓

TOOL MAP

What Algorithmaide exposes to your agents

Read (11) Write / Execute (11) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Algorithmaide tools

Destructive · High reset_target_config Resetting a configuration to an empty template is an irreversible destructive action — it overwrites the existing configuration with a blank/empty state, losing all previously configured settings. Execute · High run_verified_workflow This tool executes a sequence of operations on a real Android device including process management (stopping/starting apps), state writes, system service coordination (LSPosed sync), and optional app launching. Execute · High add_custom_hooks This tool does more than just write data — it triggers a chain of external operations: syncing configuration across multiple subsystems (AppSwitch, LSPosed), and optionally relaunching the target application. Execute · High add_r0capture_hooks This tool generates and applies network hooks using the r0capture framework on a real Android device.

12 of Algorithmaide's 23 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Algorithmaide

PolicyLayer is an MCP gateway — it sits between your AI agents and Algorithmaide, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "reset_target_config": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "sync_appswitch_state": {
    "limits": [
      {
        "counter": "sync_appswitch_state_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "collect_exported_logs": {
    "limits": [
      {
        "counter": "collect_exported_logs_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Algorithmaide — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON ALGORITHMAIDE →

Free to start. No card required.

FULL CATALOGUE

All 23 Algorithmaide tools

DESTRUCTIVE 1 tools

Destructive reset_target_config Reset the target config to an empty template and apply it through the verified workflow.

EXECUTE 5 tools

Execute run_verified_workflow Run the minimal verified loop: stop apps, write state, start AlgorithmAide, sync LSPosed, then optionally laun Execute inject_frida_script Enable one Frida script for a target package and sync config, AppSwitch, and LSPosed in one step. Execute add_custom_hooks Add or replace custom hook entries, then sync config, AppSwitch, LSPosed, and optionally relaunch the target. Execute add_r0capture_hooks Generate the built-in r0capture-style network hooks and apply them with the verified workflow. Execute apply_hook_profile Load a saved profile and apply it with the verified workflow.

WRITE 6 tools

Write sync_appswitch_state Sync AppSwitch.json and logList.json, then verify both storage layers. Write sync_lsposed_scope Sync the LSPosed scope for AlgorithmAide and return the readback. Write apply_algorithm_aide_config Write files/config/<pkg>.json safely and verify the config provider readback. Write import_hook_json Low-level config import for compatibility. Prefer apply_algorithm_aide_config for normal use. Write replace_frida_script Replace a Frida script under /data/system/junge/<pkg>/frida and verify the write. Write save_hook_profile Save a hook configuration profile locally.

READ 11 tools

Read collect_exported_logs Compatibility tool for pulling legacy exported log files only. Read collect_runtime_logs Collect runtime logs, prioritizing the SQLite database and frida.log. Read get_hook_log_context Expand one structured hook log entry into a short surrounding time-window context. Read inspect_hook_candidate Summarize one dynamic candidate into short hits, short context, jadx-ai-mcp hints, and draft add_custom_hooks Read list_hook_packs List built-in hook templates that can be applied to a target app. Read list_hook_profiles List locally saved hook configuration profiles. Read query_agent_logs Build a short unified log view from sqlite hits, short context, and frida.log supplements. Read query_frida_logs Pull frida.log and view a short keyword or time-window slice. Read query_hook_logs Pull runtime logs and query recent hook records from algorithmAidePro.db and frida.log. Read read_target_state Read the current target state, including config, AppSwitch, log sources, and LSPosed scope. Read search_hook_logs Search the structured hook log database by keyword across class, method, details, and call stack fields.

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Algorithmaide

Can an AI agent delete data through the Algorithmaide MCP server? +

Yes. The Algorithmaide server exposes 1 destructive tools including reset_target_config. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Algorithmaide? +

The Algorithmaide server has 6 write tools including sync_appswitch_state, sync_lsposed_scope, apply_algorithm_aide_config. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Algorithmaide.

How many tools does the Algorithmaide MCP server expose? +

23 tools across 4 categories: Destructive, Execute, Read, Write. 11 are read-only. 12 can modify, create, or delete data.

How do I enforce a policy on Algorithmaide? +

Register the Algorithmaide MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Algorithmaide tool call.

Deterministic rules across all 23 Algorithmaide tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON ALGORITHMAIDE →

Free to start. No card required.

23 Algorithmaide tools catalogued and risk-classified — across an index of 43,000+ MCP servers.