- Conduid
- Marketplace
- #swe-bench
MCP servers tagged swe-bench
20 live MCP servers tagged "swe-bench", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with swe-bench.
DM Code Agent
Lightweight, auditable Python code agent (~1500 LOC) — ReAct + Planner + Reflexion + Hybrid RAG, with SWE-bench Lite eval and trace replay.
Coder Eval
Test that your Claude Code skills, MCP servers, and CLIs actually work when an agent uses them — sandboxed YAML suites, activation checks, A/B experiments, CI gates.
Xenon
🚀 Xenon — Agent Harness for AI coding agents. 证据导向架构 + 7种推理范式 + 执行隔离边界 + SWE-bench 40% 通过率（+6.7pp）。可信、可验证、可评测的 AI Agent 运行时。
Mini Ork
Prove an AI-written fix actually fixes the bug. mini-ork certify reproduces the bug against your repo's own code, attacks the patch with generated invariants in a Docker sandbox,…
Awesome AI Coding Tools
Awesome AI Coding Tools (2026): Curated 3-tier taxonomy of coding assistants, CLI agents, local LLMs, MCP servers, and benchmarks
ContextGraph
🔮 The Oracle — a deterministic reality predictor that judges any AI-generated Python code change Pass/Fail against a real test oracle. An open climb toward domain super-intelligen…
Provenant
Microsoft Build AI 2026 National 1st Place. Local codebase memory for AI coding agents: 63.8% Coverage@5, 75.2% Coverage@10, 60-65x lower context.
Vexp Swe Bench
Open benchmark for AI coding agents on SWE-bench Verified. Compare resolution rates, cost, and unique wins.
Mcpbr CLI
Model Context Protocol Benchmark Runner - CLI tool for evaluating MCP servers
Xanther Context Engine
Context engine for coding agents. Indexes a repo into a multi-layer knowledge graph and serves precise architectural context over MCP. 78.2% on SWE-bench Verified at $0.22/instanc…
Siftr
Fast, cheap judgment for AI coding agents: semantic search, focused reads and list picking in ~2s. CLI + MCP server on TypeSafe Jev. Benchmarked on SWE-bench.
Sieve
Transparent feedback compression middleware for LLM coding agents
Agent Smith 42
LLM code-agent framework — Thought→Code→Observation loop, process-isolated sandbox, MBPP + SWE-bench tracks, MCP tools, multi-model OpenRouter benchmarks. 42 School project.
Atomic Forge
The reliable, test-driven repair engine you can drop under any coding agent. Issue -> failing test -> repair -> PR. Library, CLI, GitHub Action.
Sieve
Transparent feedback compression middleware for LLM coding agents
Saleha
Local-first autonomous multi-agent AI platform: ReAct agent loop, sandboxed self-healing codegen, real test-driven healing, SAST security scanning, vision-to-code, MCP engine. Run…
Reify
Your coding agent is smart. Your legacy codebase is the problem. Reify gives it the context to understand and safely change large, unfamiliar codebases — 100% locally.
Refact AI
Refact.ai — independent third-party profile of a public API surface, by API Evangelist. Refact.ai is an open-source, local-first AI coding assistant and autonomous software-engine…
AI Engineering Control Plane
AI Engineering Control Plane - portable, agent-agnostic control plane. v2.1.0: 52 ADRs, 42 skills, 15 workflows, 5 adapters, 1756 assertions. SWE-bench Verified Pass@1 adapter, fi…
Contextgraph
🔮 The Oracle — a deterministic reality predictor that judges any AI-generated Python code change Pass/Fail against a real test oracle. An open climb toward domain super-intelligen…