15,549 mods in this category, of every kind an
agent can take. Each one carries what it costs per session, what the
scan found, and whether it is the original.
Scientific method expert for systematic bug investigation and root cause analysis. Use when users report bugs, crashes, unexpected behavior, or debugging requests. Applies hypothesis-driven investigation, controlled experiments, and rigorous validation across any programming language or platform.
MCP server for debugging React Native apps — screenshots, UI hierarchy, interactions, JS console, and more. Runs locally from the react-native-devtools-mcp npm package.
★not rated 4 9mo agoA
tokens not measured
originalMIT
Tool that create a graph of code to show dependencies between code entities (methods, classes and etc). Runs locally from the codegraph Python package.
★not rated 4 25d agoA
tokens not measured
originalMIT
Cross-platform Chrome MCP with real-time request interception, response modification, network capture, HAR recording/replay, accessibility testing, anti-detection, and 91 tools. Includes smart workflows for common tasks. Works on Windows, Mac, and Linux. Runs locally from the chrome-devtools-advanced-mcp npm package.
★not rated 4 3d agoA
tokens not measured
originalMIT
Graph-based MCP server for systematic debugging using Problem-Solution Trees and Hypothesis-Experiment-Learning cycles. Runs locally from the mcp-server-debug-thinking npm package.
★not rated 4 7mo agoA
tokens not measured
originalMIT
Podium — the mobile + canvas automation MCP for AI agents: iOS & Android control, native UI automation, Maestro E2E, React Native debugging, and a no-vision canvas/WebGL brain that taps game UIs like DOM elements — for Claude Code.
★not rated 4 2mo agoA
tokens not measured
originalMIT
PageRank-curated code intelligence for coding agents. Bundles the oxcode MCP server over stdio (self-updating from v0.1.2): oxcodewatch builds the index and keeps it current as files change — a file lock elects a single writer per folder while other instances serve reads; explore/search/callers/callees/symbol/files/st.
★not rated 4▲
+1 3d agoA
tokens not measured
originalMIT
Improve and verify agent work after repeated failures, in dependency-heavy tasks, or when optimization claims need baseline and regression evidence. Use for DAGx/Perfectify requests, failed retries, risky multi-step work, or requests to verify an improvement. Exclude routine questions, drafting, one-step edits, and…
Evidence-first codebase audit for correctness, security, privacy, data, integration, operational, test, and docs-vs-reality risks. Use when the user asks for a Fable-5 audit, exhaustive audit, bug hunt, risk review, codebase audit, security/integration audit, or asks Codex to find issues before changing code.
Instructions for writing and debugging dsh-hooks-plugin scripts, which run during tool or session events such as before a tool call or after it finishes. These scripts return JSON decisions such as allowing, asking about, or denying an action.
A virtual-machine network troubleshooting workflow based on ZStack support procedures, using commands on the host machine to investigate why a VM cannot connect to the network.
★not rated 4▲
+1 20d agoA45 tokens
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: