- Conduid
- Marketplace
- #llm-agents
MCP servers tagged llm-agents
531 live MCP servers tagged "llm-agents", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with llm-agents.
Olga Automation
MCP server + Typer CLI for LLM-driven OLGA flow-assurance automation. Parse .opi models, modify keywords, run license-aware batches, parse .tpl/.ppl/.out outputs.
Harness Kit
Five executable Claude Code skills for building autonomous agent harnesses that don't silently fail — failure-mode auditing, constraint-first CLAUDE.md, sub-agent briefing, contex…
Sentinel Incident Response
Autonomous multi-agent incident response system using LangGraph, MCP, and LLMs — diagnoses production errors, classifies severity, and auto-files GitHub issues.
Agent Context Server
MCP server that turns an Obsidian vault into working memory for an LLM agent. Deterministic write guardrails in code, hybrid search (BM25 + vector + temporal + graph), automated r…
Harnesslab
Record, diff, and gate agent harness behavior as an executable Trace Contract. CI regression tests for lifecycle, tools, approvals, MCP, and adapters.
3d Router
Live file-backed AI gateway: 12 provider cards, mechanical fallback, real GLB artifacts with receipts, intent search and agent loop (Python stdlib, no keys)
Agent Canary
Tripwire detection for autonomous AI agents: file honeypots, MCP tool traps, API decoys, forensic alerts.
Modelhop
Intelligent LLM router that saves 60-90% on API costs by hopping to the cheapest capable model
Bmpp
A DeepSeek Harness plugin that enforces the mechanically verifiable part of an agent's Basic Memory policy — recall before mutation — while leaving semantic judgement to the model.
Sqlproctor
Deterministic semantic verification for agent-generated SQL.
Antigravity Graviton
Deterministic TDD Governance & State-Memory Harness for Google Antigravity Coding Agents.
Kushal9889
Open-source contributions to popular projects: vLLM (90k+ stars) PR #56846 and LlamaIndex (50k+ stars) PR #23053, under review; reported LangChain deepagents (29k+) issue #4846, f…
Storm
Fault-injection proxy at the MCP boundary: what tool failures cost your agent (completion, token multiplier, retry storms, dollars per task). Preregistered dose-response.
Proofdesk Showcase
Architecture and engineering decisions behind Proofdesk, a live showcase of citation-grounded RAG, confidence-based agent routing, and MCP integration.
Open Frame
Deterministic desktop automation engine for AI agents — capture, recognize, act, verify
Enterprise AI Scenario Map Skill
Generate AI scenario map reports for any company with research, use case discovery, priority ranking, and rollout plans
Chucky SDK Typescript
Universal TypeScript SDK for Chucky - build Claude-powered AI assistants for browser and Node.js. Sessions, streaming, tools, and MCP support.
Autonomous Trading
Morning stock trading routine driven by Claude Code reasoning
OKTS
OKT — open knowledge tools; OKTS — tool search and discovery for any agent.
Agentic Patterns
Reference implementations of 12 agentic AI patterns (ReAct, RAG, MCP, guardrails, multi-agent, and more) from canonical form to 2025-2026 research. Runs offline with no API key.
Multi Agent Market Research
Multi-agent LLM research platform: parallel data agents, synthesis agents, deterministic guardrails, MCP server
Topology Index
Multi-agent topology patterns for AI agents: orchestrator-worker, planner-executor, evaluator-optimizer, map-reduce, router, debate, swarm. Mirror of topologyindex.com + Agent Ski…
Beamxng
🛸 BeamXNG - Ultra-lightweight Rust gateway for SearXNG public instances
Autonomous AI Agents
Deep dive into enterprise-grade AI Agents & Advanced RAG. Implementing MCP architecture, hierarchical indexing, query transformation, ReAct loops from scratch, and multi-agent sta…
Matscout
MCP server with 25 tools and a two phase research agent over Materials Project. Personal course project.
Avito MCP
MCP-сервер: LLM работает на Авито через отдельный Chrome — поиск, объявления, кабинет и Pro, профили, правка форм; подтверждение необратимых действий
Bio Harness
I want to explore how NVIDIA-labs Object Oriented Agents written in python compare with a LangGraph approach for bioinformatic pipelines and the deterministic execution layer for…
Incidentgate
An AI-control evaluation harness: does a policy, monitor and human-approval chain stop an adversarial incident-response agent, and which layer does the work? Closed at a baseline…
Scoreia Forge Results
Open results of La Forge (ScoreIA): AI models forge and animate a 3D knight over MCP, scored by a programmatic referee (no LLM judge).
Jaeger MCP Bench
A/B benchmark of MCP tool output formats for Jaeger SPM metrics. 72 randomized trials, Claude + Gemini. Built for jaegertracing/jaeger#8409.
Deepbrief Lab
Build Your Own Deep Research — a 9-notebook student lab covering MCP, A2A, multi-agent, and HITL agent patterns
Retention Brain
Per-user retention agent for subscription apps. Reads cross-source signals (RevenueCat, Stripe, Sentry, PostHog) via MCP, scores per-user churn risk, drafts personalized retention…
Zed Harness Agents
Maximum-reasoning harness for Kiro CLI inside Zed (and any ACP-compatible editor). NDJSON wrapper, steering injection, think→verify enforcement, 7 MCP servers.
Agentiam Recipes
Short, opinionated integration recipes for AgentIAM — 18 x402 endpoints on Base Mainnet for agent identity, safety & execution proofs.
Witness Graph
Witness Graph: a falsifiable agent harness where every claim must cite an evidence node in an append-only ledger. Metric Truth Investigator benchmark + scorer.
Quality Guardian Langgraph
A stateful LangGraph agent that validates data quality, self-corrects with an evaluator-optimizer loop, and pauses for human approval on risky writes.
Researchops
Autonomous research & experiment engineering agent: stateful graph orchestration, hand-written MCP servers, sandboxed code execution with failure recovery, human-in-the-loop appro…
Recruiting Agent
Guarded multi-turn recruiting agent: MCP server, LangChain MCP adapters, LangGraph, conversational evals with guardrail ablation, FastAPI, Docker, CI.
Armguard MCP
Safety-first MCP server for ROS 2 manipulators: server-side joint/workspace/force envelopes, human approval via MCP elicitation, e-stop, audit log
Methanewatch Agent
Autonomous agent monitoring public satellite methane detections, matching them to operators and emitting sourced alerts. LangGraph + MCP + RAG, with measured evaluation.
Aoi Agent
AOI re-verification for PCB lines: a vision model in front of the operator queue, an agent behind it, and a benchmark for every claim. Portfolio project.
Tinystruct Smart Dba
An AI database agent for the terminal, built on the tinystruct Java framework. You ask questions in plain English, such as "show me the ten newest orders" or "how many users signe…
Linklint
Read-only mirror of gitlab.com/bart-turczynski/linklint (issues and development there). An explainable, offline-first, agent-native URL inspector — detects deceptive URLs and tell…
Fleet MCP Platform
Claude agent that detects and fixes faults in a simulated 100-vehicle fleet through a Go MCP server. Seeded fault simulator, ground-truth eval harness, two-layer write validation.
Bboard
A public bulletin board for AI agents: shared memory, task queue and agent-to-agent coordination over plain HTTP. No sign-up, Ed25519 keys, MCP server included.
Bountyops Claim Guardian Demo
Public-safe reasoning-agent demo for GitHub bounty monitoring, CI checks, payout-risk triage, and no-spam claim protection
Antigravity SDK Go
A Go library for building AI agents that leverage the full power of Google Antigravity.
Agentic Compliance Checker
Self-verifying LLM agent for repo/IaC assessment against code-detectable NIST 800-53-inspired controls, with evidence-backed verdicts and evals.
Tdae
Test-Driven Agent Evolution - ground-truth evaluation harness for LLM agents: accuracy scoring, per-agent metrics, regression detection. Runs offline via a mock provider.
Minishop Agent MCP
Asistente de atencion al cliente montado como orquestador de tres capas + 2 sub-agentes RAG + servidores MCP (FastMCP). Evaluacion ciega de 40 casos: 98 % de enrutado y 100 % de s…