"Live Order Book on Steam" matching MCP servers:

Enables AI coding tools to run CheckMyLaunch scans on GitHub repos or live URLs and retrieve findings and repair prompts directly within the chat.

Enables an AI agent opened in any git repository to discover every other repository on the machine on its own, through read-only MCP tools covering inventory, tech stack, live git status, context files (CLAUDE.md, AGENTS.md, README.md) and cross-repository text and file search. All work is strictly local and non-modifying, with no writes and no network access.

MCP server that audits npm dependencies against the live registry, providing per-dependency reports on versions behind, deprecation, and license.

Integrates Jira and Sourcegraph, enabling LLMs to retrieve and comment on Jira issues and perform code searches using Sourcegraph.

Enables local, read-only code analysis through the OpenCode CLI, exposing fixed tools that call Cloudflare, MiMo, and Nemotron models in fallback order.

Enables checking project files like Dockerfile, .nvmrc, and CI workflows to determine whether pinned runtime, database, and OS versions are still supported, providing end-of-life dates, latest patches, and upgrade targets for 470+ products.

Professional Gemini API integration for Claude and MCP-compatible hosts with intelligent model selection and advanced file handling capabilities.

Enables Claude to operate Android Studio and the entire Android toolchain: build, test, lint, run on devices/emulators, analyze APKs, scaffold projects, inspect code, and drive the live IDE via 73 tools.

A local MCP server for querying MQL5 documentation, including reference, algo book, and neural networks book, with tools for search, smart query, error diagnosis, and browsing.

Enables LLMs to develop, debug, test, and manage SAP ABAP objects on a live system through the ABAP Development Tools (ADT) protocol.

Enables coding agents to navigate large codebases through a tree-sitter symbol graph, retrieve compact path:line-annotated context, and run a SNIPE fix loop with live dashboard updates on every save.

Enables models to reach all 170 reverse-engineering tools through four meta-tools for searching, schema lookup, calling, and bundle switching, so only a tiny fraction of the tool context is loaded by default. Function bundles can be activated or deactivated at runtime without restarting the host.

Encodes a TypeScript/JavaScript codebase into a deterministic PNG heatmap that vision-capable AI models can read to bypass token limits for codebase-scale audits.

Enables planning safe file or export renames from a caller-supplied module graph, returning direct and indirect referencers, a mechanical edit order, and risk flags without reading, renaming, or executing anything.

Enables source-first orchestration and knowledge indexing with inspectable architectural capabilities through a unified MCP interface, including named-attribute retrieval and atomic knowledge ingestion.

Enables deep, order-independent comparison of JSON files to detect differences including missing keys, value mismatches, and type differences. Provides detailed reports with path tracking for precise identification of variations between JSON structures.

Enables coding agents to analyze monorepo dependency graphs, detect and resolve circular dependencies, and plan a topological build order via Tarjan SCC and Kahn algorithms. It exposes deterministic, zero-dependency Python AST static analysis over MCP for auditing and refactoring codebases.

MCP server for editing Jupyter notebooks (.ipynb) with 23 cell-level tools: create, read, search and restructure cells, manage outputs and metadata, and execute cells on a live Jupyter kernel (python3 built in; R, Julia via installed kernels). Built on nbformat and jupyter_client.

Serves local architectural context to LLM coding agents over MCP, enabling agents to query complexity, coupling, and layer metrics while deterministic quality gates enforce project invariants through hooks.

Routes reverse-engineering requests by intent and target type (native binaries, Android apps, web/JS, Electron, .NET, firmware, protocols, archives, processes, UI, vulnerabilities) to the right analysis chain, orchestrating real backends such as Ghidra, JADX, apktool, adb, Frida, x64dbg, and pe-sieve with capability fallbacks and task-state tracking. Records evidence and claims in a ledger and applies three-layer verification (execution, fact, delivery), backed by an on-demand, book-style skill for guidance.

Token-efficient MCP server for Ghidra-based reverse engineering. Analyze ELF, Mach-O, and PE binaries with Swift, Objective-C, and Hermes support.

This server provides a two-tier autonomous framework for reverse engineering binaries and applications, balancing fast, low-token triage with deep, high-fidelity emulation. It enables agents to perform advanced tasks like decompilation, control flow analysis, and formal security auditing.

Provides live, graph-verified code intelligence for AI agents, including call graphs, dependency awareness, and safety gates on edits to prevent breaking changes.

Enables AI coding assistants to drive live WinDbg/WinDbgX debugging sessions, including crash dump triage, live process attach, kernel debugging, multi-session management, and unrestricted debugger command execution with advanced reverse-engineering analysis tools.

Provides MCP tools for AI-powered code review, research, and book writing via a fleet of coding agents.

Enables AI assistants to access live GitHub repository data without cloning, supporting repo summarization, file explanation, recent changes, and dependency analysis.

Connects MCP clients to radare2, x64dbg, cdb, and Frida for disassembly, control-flow graphs, cross-references, strings, and live debugging over stdio or HTTP.

Enables AI agents to obtain a prioritized reading order for pull request diffs, highlighting high-priority files and findings while redacting sensitive data.

Enables AI assistants to read NinjaTrader 8 accounts, positions, trade history and performance, market data, charts, and NinjaScript code through 37 read-only tools. Placing, changing, or cancelling orders is impossible by design.

Automatically generates and maintains living documentation for codebases by creating hierarchical hivemind.md files and flowchart diagrams at every directory level, enabling AI navigation and real-time or retroactive documentation of code structure, requirements, and dependencies.

Enables agents to extract hardcoded numeric values from supplied text or code across many data and source-code formats, returning values in document order with notation and available line/column positions. Supports deduplication and truncated result sets.

Acts as an on-demand proxy that keeps all 207 reverse-engineering tools callable while shrinking per-request schema cost from ~193,000 tokens to ~415. Agents search for tools, fetch a single tool's schema, then invoke it, so large catalogues fit inside small context windows.

Local-first MCP-style code memory for research repositories: enables file search, Python symbol extraction, import graph, and repo context packs.

Enables AI assistants to audit, migrate, scaffold, and manage TON smart contracts using the TON Dev Skills platform.

Transforms static coding standards into a queryable live data store for AI agents, delivering task-specific rules and fix guidance on demand. This optimizes context window usage through progressive disclosure, ensuring agents apply relevant governance without loading massive documentation.

Enables automated analysis of test suite traces to identify timing races and state pollution, helping developers mitigate flaky tests through MCP-compliant clients.

An MCP (Model Context Protocol) server that exposes a live Outflow architecture graph of a repository as context for AI coding agents — Claude Code, Claude Desktop, or any other MCP-compatible client. Lets an agent ask "what does this file depend on", "what breaks if I change this", or "did my last batch of edits introduce a circular dependency" against your workspace's real, currently-live graph.

Enables AI agents and MCP clients to compute real-time, in-memory unified diffs between versions of live artifacts along with structured change telemetry. It runs as a deterministic, zero-dependency Python MCP server that plugs into Claude Desktop, Cursor, or Windsurf for diff and change-tracking workflows.

A code understanding and generation system designed for Galacean Engine that helps LLMs comprehend the engine architecture and generate high-quality engine code based on user intent.

An MCP server giving coding agents context-window-aware code search and safe, atomic multi-file edits — built to cut token usage on large codebases without sacrificing correctness.