MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. Each candidate is checked by a language model from its name, description and topics, and only actual MCP servers are listed (not clients, SDKs, lists or skills). Package metadata comes from ecosyste.ms (CC BY-SA 4.0). A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
ay-elastic-incident-triage-agentgithub.com/aminyuddin/ay-elastic-incident-triage-agentupdated this year
Incident portal + MCP server for Elastic Agent Builder. AY Elastic Incident Triage Agent: ES|QL log analysis, create/list/close/reopen tickets.
MIT -
Local MCP triage tool for automating first-response payment alerts using SQL error logs and markdown runbooks.
-
Typescript AI incident-triage agent powereed by GRoq with custom MCP tools for service-health and log analysis#
MIT -
incident-triage-studiogithub.com/ParasJagdale/incident-triage-studioupdated this year
AI-powered DevOps assistant for CI/CD incident triage using Archestra MCP orchestration - Fast 2 MCP Hackathon 2026
MIT -
Enterprise-AI-Incident-Triage-Automation-Agentgithub.com/KarthikRamesh9149/Enterprise-AI-Incident-Triage-Automation-Agentupdated this year
Enterprise AI Incident Triage and Automation Agent - local-first FastAPI, Next.js, MCP-style tools, OpenAI, RBAC, approvals, evals and observability
-
incident-triage-mcpgithub.com/felixkwasisarpong/incident-triage-mcpupdated this year
Incident Triage MCP is a Model Context Protocol–native incident‑response tool server. It exposes structured triage tools, alerts, service health, runbook search, ticket creation, and more, to enable AI agents or LLM hosts to diagnose and respond to outages safely.
Apache-2.0 ★ 1 -
AI-native MCP server for natural-language cyber incident investigation and triage across Windows, Linux, and macOS artifacts, plus Volatility3 memory forensics and Hashcat. Mount evidence, parse artifacts, trace lateral movement, correlate IOCs, and generate reports through conversation.
NOASSERTION ★ 2 -
MCP server for incident triage across Docker, Prometheus and Loki
MIT -
A read-only security triage agent — it reads a detection incident or scan finding, adds MITRE guidance, and asks a model for a structured verdict. It only reads and suggests, never acts.
MIT ★ 1 -
Lineage-based impact analysis and remediation for workflow runs. What a bad input or an incident report reached, what to re-run, delete or disclose, sealed as evidence an auditor verifies offline. Incident triage, MCP tools for agents, agent-written providers. Reads Nextflow, Snakemake, Cromwell, Horus, DNAnexus and Latch.
pypi AGPL-3.0 ★ 5 -
incident-mcp-pocgithub.com/baliramkadam094-AI/incident-mcp-pocupdated this year
Agentic AI Incident Response Platform — MCP Server (4 tools, 3 resources) + LangGraph Multi-Agent System (4 agents) for automated IT incident triage, RAG knowledge search, and ServiceNow enrichment. Built with Azure OpenAI, Pinecone, FastAPI, Docker.
-
🛡️ Autonomous SRE Incident Response & Canary Deployment Safety Room on Switch (WeMakeDevs Hackathon Track 01). Multi-agent outage triage, FastMCP telemetry, and human-in-the-loop rollback dispatch.
MIT ★ 1 -
Autonomous Level-1 SRE Incident Triage Agent built with LangGraph, FastMCP, and FastAPI. Evaluated on 30 golden incidents with 100% verified RCA and 0.0823 ECE.
★ 1 -
AI-powered zero-touch L1 incident triage for ServiceNow — Azure OpenAI + company knowledge embeddings auto-classify and route incidents to enterprise teams. FastAPI + MCP server, RAG with ChromaDB, confidence-gated routing.
-
Multi-agent payment failure triage built with Spring AI — diagnoses failures via an agentic feedback loop, explains card-network rules with RAG (pgvector), and opens GitHub incidents through bidirectional MCP, with human-in-the-loop execution.
-
Production-oriented MCP server for vulnerability intelligence and agentic incident triage
MIT ★ 1 -
ibm-concert-mcpgithub.com/ibm-ai-platform/ibm-concert-mcpupdated this year
MCP server for IBM Concert — workflow health monitoring, incident diagnosis, auto-remediation, CVE triage, and Slack alerting
pypi Apache-2.0 -
Incident triage copilot: evidence in, ranked hypotheses, checks, and escalation notes out. REST and MCP interfaces, mock and live Bedrock modes.
MIT ★ 8 -
MCP server that lets Claude Code triage Kubernetes incidents. Read-only by default, Helm chart with least-privilege RBAC.
MIT -
mcp-incident-copilotgithub.com/ShreyAC962/mcp-incident-copilotupdated this year
MCP server giving AI agents guarded, audited, read-only access to ops tooling, plus a triage agent that diagnoses an injected Kafka-lag incident in 7 tool calls with the full transcript committed. CI fails if the diagnosis names the wrong service. War story: the agent once blamed a deploy 35 minutes late until CUSUM replaced max-slope onset detect.
MIT -
Incident-triage agent that cites real evidence or abstains — model-agnostic, read-only MCP servers, frontier-competitive on a local 4B at $0.
pypi MIT ★ 1 -
AI support copilot for a mini data platform: Airflow+PySpark+Trino, Prometheus/Grafana, PagerDuty-style incidents, custom MCP server and a Slack agent that triages failures.
MIT -
Ephemeral, safe-by-default Kubernetes & Linux triage container featuring automated incident bundling, multi-pane tmux diagnostics, Flux-based GitOps RBAC, and a read-only MCP server for AI-assisted debugging.
MIT -
SREcopilotgithub.com/TushGH/SREcopilotupdated this year
AI on-call incident responder with a custom MCP server. LangGraph agent triages, investigates, proposes a runbook, waits for human approval. Same tools exposed to Claude Desktop / Cursor.
-
CppMcpAigithub.com/cschladetsch/CppMcpAiupdated this year
Native C++23 demo for MCP using an autonomous mission incident-triage console.
MIT -
MCP plugin for Tallwatch. List monitors and triage incidents from the editor.
MIT -
Blackhat 2025 presentation and codebase: AI SOC agent & MCP server for automated security investigation, alert triage, and incident response. Integrates with ELK, IRIS, and other platforms.
pypi MIT ★ 55 -
phoebegithub.com/msradam/phoebeupdated this year
SRE incident-investigation finite state machine for LLM agents, served over MCP by Theodosia. The agent keeps the full Grafana toolset; the FSM gates the procedure (triage, diagnose, verify, conclude) and the audit trail, not the tools.
Apache-2.0 ★ 3 -
claudat-itsm-mcp-agentgithub.com/dharmik136/claudat-itsm-mcp-agentupdated this year
A runnable demo: a Claude agent that triages incidents, drafts RCAs and suggests runbooks against a mock ServiceNow over the Model Context Protocol (MCP). The same MCP server plugs into Azure AI Foundry Agent Service.
MIT -
Crisis Desk AI - AI-powered emergency incident reporting and triage system with MCP-based tool orchestration.
MIT ★ 1 -
MCP server and CLI for offline VMware incident triage: event timelines, evidence correlation, hypotheses and next-check recommendations.
pypi MIT ★ 1 -
AI-powered incident triage agent for root-cause analysis, infrastructure diagnostics, and human-approved remediation.
-
dobbe-mcpgithub.com/nareshnavinash/dobbe-mcpupdated this year
AI-powered MCP server + Claude Code skills - scan vulnerabilities, fix dependencies, review PRs, generate tests, triage incidents, track DORA metrics
-
An open-source, local-first Model Context Protocol (MCP) server for **Enterprise Operations, Sentry Error Triage, Linear Issue Sync, and Slack Incident Response**.
pypi MIT -
data-center-healthcheckgithub.com/GagauzSergii/data-center-healthcheckupdated this year
AI-powered data center health check dashboard with FastAPI, React, Docker, and MCP-based incident triage for log analysis, Jira bug creation, and Slack notifications
MIT -
sre-agentgithub.com/benmoggee/sre-agentupdated this year
SRE Agent — An AI-powered MCP server for production incident triage. Takes natural-language symptom reports, plans structured investigations using Gemini, executes parallel workers (logs, metrics, deploys, runbooks), synthesizes root-cause reports, and proposes remediation patches with human approval gates.
MIT ★ 39 -
Model Context Protocol (MCP) server in Go for ThreatBook TDP (微步在线威胁检测平台): 105 OpenAPI endpoints + 4 diagnostics as typed MCP tools - alert triage, incident forensics, log hunting, threat intel & SOC automation.
MIT ★ 2 -
shieldpi-mcpgithub.com/shieldpi1/shieldpi-watchtowerupdated this year
MCP server for ShieldPi Watchtower — run LLM security scans, generate drop-in guardrails from scan findings, operate the AI SOC analyst (incident triage + kill-chain reconstruction), and query the live agent monitor from Claude Desktop / Cursor / Continue.
pypi MIT -
Real-time streaming data contract gatekeeper & zero-trust Delta Lake quarantine engine. Features PySpark Structured Streaming, Kafka (KRaft), Model Context Protocol (MCP) shift-left validation, dbt/DuckDB analytics marts, and automated LLM incident triage handling 40K+ events/sec with sub-millisecond latency.
MIT -
triagekit-mcp-k8s-triagegithub.com/karthick-dev-cart/k8s-triageupdated this year
MCP server that diagnoses unhealthy Kubernetes workloads and finds resource right-sizing candidates using real cluster state - not another kubectl wrapper.
pypi MIT -
secops-agent-triagegithub.com/drummer475-94/secops-agent-triageupdated this year
Tool-calling SOC triage agent with multi-format alert ingestion, threat-intelligence enrichment, and structured NIST/MITRE assessments.
MIT -
LLM-integrated observability pipeline: ingest kernel/driver hardware diagnostic logs into Elasticsearch, triage failures with a Claude agent over MCP, route deduplicated alerts for scale-out clusters
-
MCP adapter for GreenerPlatform Kubernetes evidence collection and rule-based incident correlation.
pypi Apache-2.0 -
Autonomous DFIR triage agent built with Google ADK & FastMCP. 4-phase NLP pipeline: frequency stacking → Isolation Forest anomaly detection → SIGMA rule enrichment → multi-agent LLM analysis. Zero-hallucination via hash-chained provenance. Kaggle AI Agents Capstone — Agents for Business.
Apache-2.0 -
Yomi is engineered to operate on a fundamentally faster timeline. By orchestrating SANS SIFT Workstation forensic tools through a strict, type-safe Model Context Protocol (MCP) server and evaluating evidence via a cascading Epistemic Doubt Engine, Yomi achieves a Time-to-Containment (TTC) of < 5 seconds.
MIT ★ 2 -
Open-source AI Security Operations Center: alert fusion, LLM-agent triage, MITRE ATT&CK investigation, and a replayable decision ledger for every agent step. Self-hostable, runs with no API keys, MIT licensed. Ships an MCP server for Claude, Cursor and Continue.
pypi MIT ★ 7,953 -
SRE Hub for Kubernetes: alert triage and right-sizing for several clients, with human approval for every change
NOASSERTION ★ 1 -
Local CLI for OSINT, email triage, image metadata/ELA, binary checks, and MCP tools; includes destructive file removal, so review commands before use.
MIT ★ 2 -
Open-core SOAR platform for the autonomous SOC. Tier-1 triage agents, immutable audit, MCP portal for examiners. Built on SynapCores.
Apache-2.0 ★ 2 -
MCP server bridging Kali and FlareVM for automated Windows malware analysis. 48 tools, 5 prompts, 5 resources, composite playbooks (triage, behavioral, unpack, persistence audit).
MIT ★ 13 -
MacVM-MCPgithub.com/zixuantemp/MacVM-MCPupdated this year
MCP server for automated macOS malware analysis via SSH. 43 tools, 5 prompts, 5 resources, composite playbooks (triage, behavioral, app-bundle audit, IR scan).
MIT -
Safety observation triage, corrective-action tracking and shift handovers. FastAPI/Postgres workspace, explainable DistilBERT severity, YOLO PPE pipeline, and read-only MCP tools.
MIT ★ 1 -
AllBluegithub.com/amareshhebbar/AllBlueupdated this year
Autonomous multi-agent DFIR orchestrator — Splunk alerts trigger AI triage, findings pushed back to Splunk. 100% precision, 0 hallucinations. Claude + SIFT + Go MCP Server.
MIT -
secai - agentic cybersecurity engine: 272 capability scripts (93 detection skills + 176 tools, 121 ported from 995 concepts), Rust core + one contract, MCP, offline-first triage. No proof, no report.
NOASSERTION ★ 1 -
Open, AI-assisted SecOps platform on the Basic-licensed Elastic Stack: SIEM, detection rules, alert correlation, PII masking, LLM triage with human review, and a read-only MCP server.
Apache-2.0 -
Free MCP server for security operations: CVSS 3.1 scoring, IOC extraction and defanging, email header triage, hash and JWT decoding, timestamps, layered decoding, CISA KEV lookup. No account, no telemetry.
oci MIT -
notes-recovergithub.com/xiaojiou176-open/notes-recoverupdated this year
Copy-first Apple Notes recovery and review toolkit for macOS, with AI-assisted triage, evidence-backed case Q&A, and a read-mostly MCP server for Codex / Claude Code style local agent workflows.
MIT ★ 2 -
Production-grade MCP server for Wazuh SIEM — 55 security tools for alert triage, threat hunting, vulnerability management, compliance (PCI DSS, GDPR, HIPAA, NIST CSF, ISO 27001) and active response. Connect Claude or any LLM to your SOC. OAuth 2.1, RBAC, multi-cluster, air-gap ready.
go MIT ★ 272 -
Static + dynamic malware analysis for Windows. Deep static triage (entropy map, multi-stage strings, code patterns, imports, capabilities), then optional dynamic unpacking under x64dbg in a disposable VM: captures the payload, recovers keys, classifies the family, exports YARA/Sigma/STIX IOCs. One PDF per run, driveable from any LLM via MCP.
MIT ★ 2 -
Harness de operaciones de ciberseguridad sobre Trend Micro Vision One: agentes de IA que hacen triage, investigan IOCs, ejecutan la contención y documentan la alerta. Incluye el servidor MCP (FastMCP) que expone su API, VirusTotal y Slack como herramientas. Ninguna acción de respuesta corre sin autorización humana, garantizada en código.
Apache-2.0 ★ 1