Task · Coding
Best AI agents to fix bugs in a codebase
This task needs 2 capabilities. 1 tools cover all of them; 381 cover at least one.
| # | Tool | Coverage | Access | Trust | Seen |
|---|---|---|---|---|---|
| 201 | AvrotizeMCP Schema conversion and schema-driven code generation MCP server. | 50% Code Generation · low match | REMOTELOCAL | DECLARED | 1d ago |
| 202 | statecliMCP State replay and self-debugging for AI agents. Track, replay, undo, checkpoint. | 50% Debugging · low match | REMOTELOCAL | DECLARED | 1d ago |
| 203 | CEDRUSMCP Reasoning scaffolding that supercharges your small AI: an argument-mapping MCP server | 50% Code Generation · low match | REMOTELOCAL | DECLARED | 1d ago |
| 204 | SelfHeal MCPMCP Self-healing proxy for MCP servers with retry, circuit breaker, and observability | 50% Debugging · low match | REMOTELOCAL | DECLARED | 1d ago |
| 205 | memorydetectiveMCP iOS leak/perf debugging via MCP: memgraph cycles, .trace analysis, SourceKit-LSP bridging. | 50% Debugging · low match | REMOTELOCAL | DECLARED | 1d ago |
| 206 | x64dbgMCP MCP server for x64dbg debugger - 23 mega-tools for AI-powered reverse engineering and debugging | 50% Debugging · low match | REMOTELOCAL | DECLARED | 1d ago |
| 207 | BraintrustMCP AI evaluation and observability platform — query experiments, logs, datasets, and prompts. | 50% Debugging · low match | REMOTELOCAL | DECLARED | 1d ago |
| 208 | blinkboxMCP Open-source Zapier/n8n alternative as an MCP server: agents build, run and debug your workflows. | 50% Debugging · low match | REMOTELOCAL | DECLARED | 1d ago |
| 209 | Agent ObservabilityMCP Agent observability: structured logging, cost tracking, and compliance audit trails | 50% Debugging · low match | REMOTELOCAL | DECLARED | 1d ago |
| 210 | stylobridgeMCP Air-gapped Markdown/PDF to Word converter with brand templates and audit logging. | 50% Debugging · low match | REMOTELOCAL | DECLARED | 1d ago |
| 211 | langchain-mcpMCP LangChain/LangGraph/DeepAgents knowledge + LangGraph agent debugging (Polly-like) | 50% Debugging · low match | REMOTELOCAL | DECLARED | 1d ago |
| 212 | webearMCP Give your AI coding assistant ears — capture, analyze, and describe live audio. | 50% Code Generation · low match | REMOTELOCAL | DECLARED | 1d ago |
| 213 | PWA Debug LayerMCP Debug PWAs in your real browser via MCP: service-worker, cache, installability & framework state. | 50% Debugging · low match | REMOTELOCAL | DECLARED | 1d ago |
| 214 | agentlMCP Validate, plan, preview and run YAML data pipelines (ETL with LLM steps) and debug failed runs. | 50% Debugging · low match | REMOTELOCAL | DECLARED | 1d ago |
| 215 | k8scortex-mcpMCP Kubernetes MCP server: 75 tools for GKE, AKS, EKS, RBAC, audit logging, GitOps, multi-cluster. | 50% Debugging · low match | REMOTELOCAL | DECLARED | 1d ago |
| 216 | mcp-portalMCP Cursor CLI delegation for verified bulk reads and reference-driven code generation. | 50% Code Generation · low match | REMOTELOCAL | DECLARED | 1d ago |
| 217 | ArchietMCP Archiet MCP server: scaffold full-stack apps from PRD text and extract capabilities. | 50% Code Generation · low match | REMOTELOCAL | DECLARED | 1d ago |
| 218 | GrayMatterMCP Persistent agent memory as a single Go binary: knowledge graph, TUI observability, zero infra. | 50% Debugging · low match | REMOTELOCAL | DECLARED | 1d ago |
| 219 | ai tag debuggerMCP QA-tests your site analytics, ad and consent tags (GA4, GTM, Ads, Meta, TikTok) from chat. | 50% Debugging · low match | REMOTELOCAL | DECLARED | 1d ago |
| 220 | Research Vault (research decoy)MCP Owned MCP research honeypot: synthetic decoy data with canary markers; digest-only logging. | 50% Debugging · low match | REMOTELOCAL | DECLARED | 1d ago |
| 221 | renforgeMCP Inspect, drive and debug a running Ren'Py game: state, screenshots, guarded clicks, saves, builds. | 50% Debugging · low match | REMOTELOCAL | DECLARED | 1d ago |
| 222 | aidbMCP Debug any supported language with breakpoints, variable/state inspection, and stepping. | 50% Debugging · low match | REMOTELOCAL | DECLARED | 1d ago |
| 223 | Agentic HILMCP Develop firmware on the real board behind a debug probe: flash, reset, UART and CAN, policy-gated. | 50% Debugging · low match | REMOTELOCAL | DECLARED | 1d ago |
| 224 | AgentLensMCP Tamper-evident, SHA-256 hash-chained audit trail and observability for AI agents. | 50% Debugging · low match | REMOTELOCAL | DECLARED | 1d ago |
| 225 | luMCP lu.ma events MCP server with draft+confirm safety, audit logging, and prompt-injection scrubbing.… | 50% Debugging · low match | REMOTELOCAL | DECLARED | 1d ago |
| 226 | SaaS Pro MaxMCP Product analytics, error tracking, feature flags and SaaS operations with scoped OAuth access. | 50% Debugging · low match | REMOTELOCAL | DECLARED | 1d ago |
| 227 | dsh2vs — VS C++ bridge (unofficial)MCP Unofficial, independent (not DeepSeek AI/Microsoft). VS C++ build+debug via MSBuild and cdb. | 50% Debugging · low match | REMOTELOCAL | DECLARED | 1d ago |
| 228 | JS Reverse MCPMCP MCP server for JavaScript reverse engineering and browser debugging. | 50% Debugging · low match | REMOTELOCAL | DECLARED | 1d ago |
| 229 | STM32 GDB DebuggerMCP Debug STM32 firmware on real hardware via GDB + OpenOCD/ST-Link/J-Link with decoded results. | 50% Debugging · low match | REMOTELOCAL | DECLARED | 1d ago |
| 230 | Electron MCP ServerMCP Electron.js MCP server — IPC scaffolding, security auditing, build tooling for AI assistants | 50% Code Generation · low match | REMOTELOCAL | DECLARED | 1d ago |
| 231 | NullWire-MCPMCP RAM-only HTTP debugging proxy and MCP server in Go. AI agents see salted tags, never secrets. | 50% Debugging · low match | REMOTELOCAL | DECLARED | 1d ago |
| 232 | Nanostores MCPMCP Debug and analyze Nanostores apps with AI: scan stores, monitor runtime events, and search docs. | 50% Debugging · low match | REMOTELOCAL | DECLARED | 1d ago |
| 233 | observability-mcpMCP Unified observability gateway for AI agents — Prometheus, Loki & more, with anomaly detection. | 50% Debugging · low match | REMOTELOCAL | DECLARED | 1d ago |
| 234 | The Context CompanyMCP AI agent observability for production traces, natural-language insights, and improvement loops. | 50% Debugging · low match | REMOTELOCAL | DECLARED | 1d ago |
| 235 | TempletryMCP Scaffold, plan, update and extend projects from Templetry templates. | 50% Code Generation · low match | REMOTELOCAL | DECLARED | 1d ago |
| 236 | datadog-mcpMCP Full Datadog API access: monitors, logs, metrics, traces, dashboards, and observability tools | 50% Debugging · low match | REMOTELOCAL | DECLARED | 1d ago |
| 237 | CovateMCP Learning sidebar for AI coding assistants: quizzes on your changes, debug memory, term explanations | 50% Debugging · low match | REMOTELOCAL | DECLARED | 1d ago |
| 238 | Predictive DebuggerMCP Predicts where JavaScript and TypeScript code will fail at runtime, for coding agents. | 50% Debugging · low match | REMOTELOCAL | DECLARED | 1d ago |
| 239 | tor-mcpMCP Route HTTP requests through the Tor network. Rotating exit IPs, .onion support, no body logging. | 50% Debugging · low match | REMOTELOCAL | DECLARED | 1d ago |
| 240 | FlaskTrackMCP Read and scaffold organization-scoped FlaskTrack laboratory data using MCP. | 50% Code Generation · low match | REMOTELOCAL | DECLARED | 1d ago |
| 241 | UsageMax public observabilityMCP Read-only MCP for AI usage profiles, leaderboards, stats, and docs; no writes or private data. | 50% Debugging · low match | REMOTELOCAL | DECLARED | 1d ago |
| 242 | Expo Agent BridgeMCP Let AI agents see, tap, type, scroll, screenshot and debug your Expo app on a real phone. | 50% Debugging · low match | REMOTELOCAL | DECLARED | 1d ago |
| 243 | agent-observabilityMCP AI agent observability with deterministic record/replay for debugging agent failures. | 50% Debugging · low match | REMOTELOCAL | DECLARED | 1d ago |
| 244 | Hated WoW MCPMCP MCP server for WoW addons: Lua API, UI source, CVars, art, linting, plus model export to glTF/OBJ. | 50% Code Generation · low match | REMOTELOCAL | DECLARED | 1d ago |
| 245 | shipfast-mcpMCP Quy trình theo wave giữa PO và AI: khung tài liệu, skill, scaffold, nâng cấp three-way merge. | 50% Code Generation · low match | REMOTELOCAL | DECLARED | 1d ago |
| 246 | mcp-server-graylogMCP Search Graylog logs by timestamps, filter by streams, and debug production issues. | 50% Debugging · low match | REMOTELOCAL | DECLARED | 1d ago |
| 247 | Prefect MCP ServerMCP MCP server for Prefect. Monitor and debug workflows, deployments, and automations. | 50% Debugging · low match | REMOTELOCAL | DECLARED | 1d ago |
| 248 | PackkitMCP Scaffold, compose, and upgrade modern multi-language projects as a native tool for AI agents. | 50% Code Generation · low match | REMOTELOCAL | DECLARED | 1d ago |
| 249 | pscatMCP Render and debug PostScript to PNG, SVG or PDF, write handwritten notes, and make generative art | 50% Debugging · low match | REMOTELOCAL | DECLARED | 1d ago |
| 250 | MCP GatewayMCP Multi-tenant MCP platform with OAuth 2.1, Entra SSO, RBAC and audit logging. | 50% Debugging · low match | REMOTELOCAL | DECLARED | 1d ago |
Coverage = share of this task's required capabilities that an agent or tool documents. Agents are ranked by coverage; at equal coverage, agents whose main theme is this task's theme come first, then the better-verified match, then Agent Score. For AI agents, capabilities are those stated on the vendor's website; for tools, they are matched automatically from the publisher's description (keyword method, low confidence). Each agent's capabilities, trust level, sources and verification dates are shown on its own page.