algorithmaide-mcp
An MCP server for real-device Android reversing workflows, wrapping AlgorithmAide config writes, AppSwitch/logList sync, LSPosed scope sync, Frida script injection, and runtime log queries into a stable MCP toolset.
Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
How we verified
Verified is a snapshot. Live keeps it current, and builds your track record.
⚡ Connect GitHub → continuous verification on every pushwhy connect →Who stands behind it
vwww-droid
Source: Glama
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →
Install from
The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.
These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.
list_hook_packsList built-in hook templates that can be applied to a target app.
read_target_stateRead the current target state, including config, AppSwitch, log sources, and LSPosed scope.
apply_algorithm_aide_configWrite files/config/<pkg>.json safely and verify the config provider readback.
add_custom_hooksAdd or replace custom hook entries, then sync config, AppSwitch, LSPosed, and optionally relaunch the target.
sync_appswitch_stateSync AppSwitch.json and logList.json, then verify both storage layers.
sync_lsposed_scopeSync the LSPosed scope for AlgorithmAide and return the readback.
replace_frida_scriptReplace a Frida script under /data/system/junge/<pkg>/frida and verify the write.
collect_runtime_logsCollect runtime logs, prioritizing the SQLite database and frida.log.
search_hook_logsSearch the structured hook log database by keyword across class, method, details, and call stack fields.
get_hook_log_contextExpand one structured hook log entry into a short surrounding time-window context.
inspect_hook_candidateSummarize one dynamic candidate into short hits, short context, jadx-ai-mcp hints, and draft add_custom_hooks suggestions.
query_hook_logsPull runtime logs and query recent hook records from algorithmAidePro.db and frida.log.
query_agent_logsBuild a short unified log view from sqlite hits, short context, and frida.log supplements.
query_frida_logsPull frida.log and view a short keyword or time-window slice.
inject_frida_scriptEnable one Frida script for a target package and sync config, AppSwitch, and LSPosed in one step.
run_verified_workflowRun the minimal verified loop: stop apps, write state, start AlgorithmAide, sync LSPosed, then optionally launch the target.
add_r0capture_hooksGenerate the built-in r0capture-style network hooks and apply them with the verified workflow.
reset_target_configReset the target config to an empty template and apply it through the verified workflow.
save_hook_profileSave a hook configuration profile locally.
list_hook_profilesList locally saved hook configuration profiles.
apply_hook_profileLoad a saved profile and apply it with the verified workflow.
import_hook_jsonLow-level config import for compatibility. Prefer apply_algorithm_aide_config for normal use.
collect_exported_logsCompatibility tool for pulling legacy exported log files only.
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
@modelcontextprotocol/sdk has cross-client data leak via shared server/transport instance reuse
Anthropic's MCP TypeScript SDK has a ReDoS vulnerability
Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default
Tool annotations
No tools have read-only/destructive annotations
Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.
All four hints declared on every tool
46/46 tools missing one or more hints — list_hook_packs (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); read_target_state (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); apply_algorithm_aide_config (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +43 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.
For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.
Shell command execution
13 child_process calls — runs shell commands
Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.
Production dependencies are patched
0 critical, 3 high severity in production deps — @modelcontextprotocol/sdk@1.17.1 (high), @modelcontextprotocol/sdk@1.17.1 (high)
Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.
Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.
[](https://m8ven.ai/mcp/vwww-droid/algorithmaide-mcp)?variant=verified from the URL.Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.
https://m8ven.ai/api/mcp/tool-check