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. 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.
-
Self-hosted on-call alerting and incident escalation. Open-source PagerDuty and Opsgenie alternative with on-call schedules, escalation policies, SMS, voice and push notifications, a mobile app and an MCP server for AI agents. Built on GoAlert.
-
wardenpoint-mcpgithub.com/WardenPoint/wardenpoint-mcpupdated this year
WardenPoint MCP server — configure recipients, groups, escalation policies and on-call schedules from an AI agent. Built entirely from the installation's own OpenAPI description.
npm MIT -
MCP server for analyzing AWS IAM policies for security risks, wildcards, privilege escalation, and best practice violations
npm MIT -
Spending-policy wallet for AI agents on Solana: agents propose payments over MCP, an owner-set policy signs, escalates or denies; multi-step tasks use an on-chain Anchor capability vault (Devnet).
MIT ★ 1 -
goalert-mcpgithub.com/amitray007/goalert-mcpupdated this year
goalert-mcp — MCP server for GoAlert: manage on-call alerts, schedules & escalation policies from Claude & other LLMs
MIT ★ 2 -
Evaluation-driven LLM agent for customer operations with LangGraph, RAG, structured tool execution, policy-aware escalation, and MCP interoperability.
-
mcp_customer_supportgithub.com/gagan0116/mcp_customer_supportupdated this year
MCP-compatible customer service agent that automates refund/return requests from emails with Database verification, Policy clause evaluation and human review escalation.
★ 1 -
mcp-ticketinggithub.com/zavora-ai/mcp-ticketingupdated this year
Ticketing MCP Server — a service-desk / case-ticketing platform (queues with SLA policies, tickets with priority and SLA due dates + breach detection, intake & triage, assignment, status workflow, public/internal comments, escalation, tags, and SLA/workload analytics) with a full audit trail
cargo Apache-2.0 -
Open-source AI agent security gate: deterministic ALLOW/BLOCK/ESCALATE authorization before every tool call, plain-English policy compilation, tamper-evident audit ledger. MCP security gateway + Claude Code/Cursor guardrails. Rust, Apache-2.0.
Apache-2.0 -
Typed judgment tools for MCP agents. TypeSafe's Jev model as verify, screen, find, classify, rerank, decide, compare, extract, review, gate, and score: the model judges, policy decides auto, review, or escalate.
MIT ★ 49 -
Multi-agent AI customer-support system that takes real actions safely: router, support, actions and escalation agents with separated privileges and typed handoffs, an MCP tool server with per-agent scopes, LangGraph orchestration, human-in-the-loop approvals, a deterministic policy engine, τ-bench-style simulated-user evals and red-teaming
MIT -
AWS IAM MCP Server – user/role inspection, policy analysis, access key audit, and privilege simulation for security investigations
npm Apache-2.0 -
Open-source authority layer for AI agents: who may approve what, how decisions escalate, and the evidence.
Apache-2.0 -
Guardrails service for AI agents. Default-deny tool call evaluation with LLM safety analysis, priority-ordered decision matrix, and human-in-the-loop escalations. Session recording, behavioral analysis, MCP proxy, secret redaction, and real-time audit.
pypi NOASSERTION ★ 22