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.
-
Pre-execution governance for AI agents. Sub-millisecond tool call validation, drift detection, circuit breakers, human-in-the-loop holds. 829 tests. 56 MCP tools.
go MIT ★ 1 -
velarion-mcpgithub.com/velarion-ai/velarion-mcpupdated this year
MCP server for executive-compensation, say-on-pay, and governance data on US public companies. Self-serve token, 8 tools, live at ai.velarion/company-intelligence.
NOASSERTION -
Agent gateway for external tools — Rhumb Index scores services; Rhumb Resolve routes supported capability calls through governed execution rails.
npm MIT ★ 6 -
Deterministic MCP server for governed and auditable AI execution
Apache-2.0 -
gov-mcpgithub.com/liuhaotian2024-prog/gov-mcpupdated this year
Governed execution layer for AI agents — MCP server with Y*gov runtime enforcement
MIT -
sift-mcpgithub.com/walkojas-boop/sift-mcpupdated this year
Sift MCP Server — Agent Execution Governance for Claude Desktop and other MCP clients
pypi MIT -
Governed state engine for AI agents: typed, executable knowledge artifacts with a code-like lifecycle
pypi Apache-2.0 ★ 17 -
gax-cligithub.com/0sparsh2/gaxupdated this year
Governed execution layer for agent shell commands — capability-gated, audited, MCP-compatible
pypi MIT -
DRAFT Protocol — Intake governance for AI tool calls. Ensures AI understands human intent before execution begins.
pypi Apache-2.0 -
@vorionsys/mcp-servergithub.com/vorionsys/vorionupdated this year
MCP server for Vorion AI governance — trust-gated tool execution, proof logging, and tier lookup
npm Apache-2.0 -
Official Model Context Protocol (MCP) server for SPHIOR AI Governance — let your AI agent (Claude, Cursor, Cline, Windsurf, Zed, VS Code) record its own executions as tamper-evident, independently verifiable evidence (hash-only) for ISO 42001 / EU AI Act
npm Apache-2.0 -
guardian-safety-mcpgithub.com/guardian-safety-gate/guardian-mcp-serverupdated this year
MCP server for Guardian Safety Gate — allow AI agents to evaluate and execute governed actions through a safety policy layer.
npm MIT -
Official Model Context Protocol (MCP) server for Blocklog. Give AI agents access to auditable execution traces, governance policies, and cryptographically verifiable evidence.
NOASSERTION ★ 1 -
Governed expense-operations platform with deterministic policy execution, durable workflows, provenance, evaluations, observability, and MCP interfaces.
MIT -
Self-hosted governance platform for AI agents: identity, SSO/RBAC, approvals, signed execution grants, tamper-evident audit and Solution Packs.
AGPL-3.0 -
Governance & observability for your AI capabilities in Spring Boot — capability registry, versioning, per-capability cost & budgets, a durable execution recorder, and MCP export, from one annotation.
maven Apache-2.0 ★ 11 -
schema-driven-policy-workflow-agentgithub.com/PouyaPour/schema-driven-policy-workflow-agentupdated this year
Deterministic pre-execution governance layer for agentic workflow actions using schema contracts, MCP, HITL, ADK-style orchestration, and evaluation cases.
NOASSERTION -
dlx7-mcp-interceptorgithub.com/everybitcounts/dlx7shieldnetupdated this year
DLX7 Agent Zero Trust (AZT) MCP server — governance runtime for AI coding agents. Validates every file edit and shell command before execution. Works in VS Code, Cursor, Windsurf, and Claude Desktop.
npm MIT -
Spec-driven development governance for AI coding agents: Gherkin specs as executable contracts, deterministic drift gates, an agent firewall and a least-privilege MCP server, on any repository.
npm MIT -
io.github.Runewardd/runewardgithub.com/runewardd/runewardno update data
Governed execution cells for AI agents: Docker/K8s sandboxes with policy, audit, and approvals.
oci -
io.github.Jarroslav/agentic-osno update data
Read-only, never-executing MCP server for the agentic-os governance, SDLC, and QE methodology.
npm -
Executable architecture governance. A CLI, MCP server and REST API that check a repository against Rego/OPA rules — and report a rule they could not evaluate as a failure, never a silent pass.
npm MIT ★ 2 -
AI-native unified cloud governance platform — multi-cloud discovery, 6R migration planning, IaC security, FinOps, compliance audit, and executive AI chat. Built on Claude Opus 4.7. EU AI Act Annex IV ready. Zero paid SaaS dependencies.
MIT ★ 1 -
Attestify OS MCP package — connect Claude, Cursor, VS Code Copilot and any MCP host to governed, receipted AI lane execution.
npm -
ledgermendergithub.com/neerazz/ledgermenderupdated this year
Deterministic AI-agent payment-integrity investigator with bounded replanning, MCP governance, evidence provenance, and executable patch verification.
MIT -
OrgX Work Ledger, MCP tools, skills, proof, and governed execution for DeepSeek Harness
MIT -
loop-protocolgithub.com/dingdawg/loop-protocolupdated this year
DingDawg Loop Protocol (DDLP) — safe scheduled AI agents with governance gates. Every loop execution is verified, receipted, and fail-closed. MCP-native.
npm MIT -
Authorization-first, MCP-governed security execution for explicitly approved environments.
MIT ★ 1 -
MCP governance server — permission enforcement, blast-radius controls, execution timeout, and audit trail for large-scale AI agent deployments
-
Agentic AI system for enterprise incident resolution using LLM agents, RAG, tool calling, MCP, and governed execution.
-
Coding-agent orchestration and MCP context runtime with governed repository execution, bounded tool results, and multi-agent session management.
npm MIT -
OpenXnet by SynapXnet: enterprise AI employee collaboration, governed MCP tools, evidence chains, approvals, verification, and auditable execution.
AGPL-3.0 -
aegis-mcpgithub.com/cleburn/aegis-mcpupdated this year
Runtime enforcement. Loads policy into server memory, validates every agent action before execution. Blocked actions get a specific reason and an override protocol. Zero token overhead — agents never load governance files.
npm MIT ★ 3 -
Type-safe SDK, CLI, and MCP server for the Flowgate Governed execution layer for private capital.
Apache-2.0 -
Reference runtime and operator console for sovereign AI agents — REPL, daemon, delegation, MCP server. Persistent Ed25519 identity, signed execution receipts, governance at the boundary.
npm BUSL-1.1 -
gateway-ops-mcpgithub.com/Pratik-Kanani/gateway-ops-mcpupdated this year
AI-native operations platform for payment gateways with governed execution, semantic routing, and resilient orchestration.
-
Enterprise knowledge copilot — grounded RAG chat with citations, source connectors, custom assistants & tools with governance, MCP, per-tenant secrets vault, sandboxed code execution.
MIT -
Use Todoist with AI agents through one PipMCP API key, actual hosted schemas and governed execution.
MIT -
Use UptimeRobot with AI agents through one PipMCP API key, actual hosted schemas and governed execution.
MIT -
Use Datadog with AI agents through one PipMCP API key, actual hosted schemas and governed execution.
MIT -
Use Grafana with AI agents through one PipMCP API key, actual hosted schemas and governed execution.
MIT -
Use Render with AI agents through one PipMCP API key, actual hosted schemas and governed execution.
MIT -
Use Netlify with AI agents through one PipMCP API key, actual hosted schemas and governed execution.
MIT -
Use Vercel with AI agents through one PipMCP API key, actual hosted schemas and governed execution.
MIT -
Use DigitalOcean with AI agents through one PipMCP API key, actual hosted schemas and governed execution.
MIT -
Use Buildkite with AI agents through one PipMCP API key, actual hosted schemas and governed execution.
MIT -
Use CircleCI with AI agents through one PipMCP API key, actual hosted schemas and governed execution.
MIT -
Use Bitbucket with AI agents through one PipMCP API key, actual hosted schemas and governed execution.
MIT -
Use Browserbase with AI agents through one PipMCP API key, actual hosted schemas and governed execution.
MIT -
Use Exa with AI agents through one PipMCP API key, actual hosted schemas and governed execution.
MIT -
Use Firecrawl with AI agents through one PipMCP API key, actual hosted schemas and governed execution.
MIT -
Use Tavily with AI agents through one PipMCP API key, actual hosted schemas and governed execution.
MIT -
Use Pinecone with AI agents through one PipMCP API key, actual hosted schemas and governed execution.
MIT -
Use Replicate with AI agents through one PipMCP API key, actual hosted schemas and governed execution.
MIT -
Use ElevenLabs with AI agents through one PipMCP API key, actual hosted schemas and governed execution.
MIT -
Use Deepgram with AI agents through one PipMCP API key, actual hosted schemas and governed execution.
MIT -
Use Gorgias with AI agents through one PipMCP API key, actual hosted schemas and governed execution.
MIT -
Use Front with AI agents through one PipMCP API key, actual hosted schemas and governed execution.
MIT -
Use Jotform with AI agents through one PipMCP API key, actual hosted schemas and governed execution.
MIT -
Use Typeform with AI agents through one PipMCP API key, actual hosted schemas and governed execution.
MIT