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.
-
Akeyless Agentic Runtime Authoritygithub.com/akeyless-community/devin-akeyless-connectorno update data
Secretless database and cloud access via Akeyless RTA. Credentials never enter the model.
npm -
Cross-platform (Windows + macOS) lane coordinator for AI coding agents (Claude, Codex, etc.) — keeps multiple local agents from colliding on dev-server ports, Chrome debug ports, and Chrome user profiles. Includes a CLI, an MCP server, and a native Tauri
npm MIT -
MCP server for verifiable AI agent authority, powered by the open VAGP protocol.
npm NOASSERTION -
Shows how organizations can expose secure API data to AI agents using Model Content Protocol Authorization
Apache-2.0 ★ 7 -
Agent_Sudogithub.com/Kisyntra/Agent_Sudoupdated this year
Authorization, delegation, provenance, and verifiable-audit engine for AI agents. MCP adapter published.
pypi Apache-2.0 ★ 5 -
Akeyless Agentic Runtime Authority (ARA) MCP server for OpenAI Codex — secretless database and cloud access, no CLI required
npm Apache-2.0 -
Open standard for verifiable AI agent identity and authority. One signed JSON file at /.well-known/agent-passport.json, keyed in DNS. Verifier, spend caps, signed receipts, CLI and MCP server. MIT.
MIT ★ 1 -
yebo-mcp-serverupdated this year
Yebo MCP Authorization Server — add hardware-bound human authorization to any AI agent in one line
npm MIT -
@yebo-auth/mcp-serverupdated this year
Yebo MCP Authorization Server — add hardware-bound human authorization to any AI agent in one line
npm MIT -
Prior authorization for lumbar MRI: Google ADK A2A agent + FastMCP FHIR tools on Prompt Opinion.
-
Citation-driven prior authorization appeals MCP server for healthcare AI agents
-
@codespar/mcp-ap2updated this year
MCP server for AP2 — Google's Agent-to-Agent Payment Protocol (authorization, audit, trust)
npm MIT -
@attesso/mcpgithub.com/attesso/attessoupdated this year
Attesso MCP server. Authorization and safety tools for AI agents.
npm MIT -
@getripple/mcpgithub.com/raushankcode/rippleupdated this year
MCP stdio server for Ripple's local authorization gate for AI coding agents.
npm MIT -
Rig agent with Tenuo warrants: call-level authorization, narrowing delegation to a worker agent, and an MCP server that verifies each call
Apache-2.0 ★ 1 -
plugingithub.com/Delego-Dev/pluginupdated this year
delego — Claude Code plugin: intent-bound action-authorization skills, review agents, and the MCP server in one install
Apache-2.0 -
An all-in-one authorization fabric for the agentic era.
npm MIT -
mcp-authz-spicedb-demogithub.com/databased/mcp-authz-spicedb-demoupdated this year
AI agent tool-call authorization using SpiceDB (Google Zanzibar) via Model Context Protocol (MCP)
Apache-2.0 -
Open-source authority layer for AI agents: who may approve what, how decisions escalate, and the evidence.
Apache-2.0 -
webmcp-sentinelgithub.com/guyle/webmcp-sentinelupdated this year
Server-enforced authorization, human approval, and audit for AI-agent actions — a WebMCP security reference implementation
MIT -
Policy-aware MCP server for Keel: expose on-chain agent actions to a model, gated by the authorization policy before anything executes.
npm Apache-2.0 -
Policy & authorization layer for AI agent payments: ALLOW / APPROVAL / DENY with budgets, merchant lists, signed one-time grants and tamper-evident audit. Python + MCP.
pypi MIT ★ 2 -
prior-auth-copilotgithub.com/pcmedsinge/prior-auth-copilotupdated this year
Open-source agentic FHIR-native Prior Authorization co-pilot — Da Vinci PAS/CRD/DTR · LangGraph · MCP. Reference implementation for CMS-0057.
NOASSERTION -
Demo: stop prompt injection on AI agent tool calls with an MCP server that authorizes every action via renker-core-authz. Runnable, no LLM or API key needed.
Apache-2.0 -
Model Context Protocol server for Open Policy Agent (OPA). Author, validate, debug, and explain Rego policies through any MCP-compatible client.
npm MIT ★ 8 -
The authorization boundary between an AI agent and a consequential action. Self-hosted MCP server (2025-11-25) + simulated Alexa+ experience. 232 tests, hash-chained ledger, single-use mandates.
MIT -
A deterministic authorization boundary that stops an AI agent issuing refunds nobody approved. Sits in front of Razorpay's MCP server; measured recall and false-positive cost published.
MIT -
Deterministic governance layer for AI agents: action-bound authority, deny-by-default with no LLM in the decision, and offline-verifiable Ed25519 receipts.
NOASSERTION ★ 9 -
Authorization, delegation and audit for AI agent actions over MCP: a policy on every tool call, short-lived agent tokens, human approvals and a tamper-evident audit log.
npm Apache-2.0 ★ 2 -
mcp-servergithub.com/vengtoo/mcp-serverupdated this year
MCP server for Vengtoo — gives AI agents tools to check authorization, list namespaces, and manage access policies directly from any MCP-compatible client.
MIT -
IronTrellis evidence MCP server: one bounded local tool that copies operator-selected files into an evidence packet when the configured agent still holds the authority, exactly once per operation id. Agents change. The structure holds.
npm Apache-2.0 -
Audiokinetic Wwise MCP adapter for AI agents to import game audio, author Events and dynamic music, generate SoundBanks, and inspect profiling data through WAAPI in DCC-MCP.
pypi MIT -
baton-publicgithub.com/euuuuuuan/baton-publicupdated this year
A local-first platform for giving an agent a bounded amount of authority over one macOS workstation: a Swift daemon exposes 63 documented MCP tools behind a policy engine, an approval broker and an append-only audit log, while the TypeScript orchestrator plans work and can never grant itself new authority. A platform, not a packaged product.
Apache-2.0 -
Adobe Substance 3D Painter MCP adapter for AI agents to inspect texture sets, author PBR layers, apply smart materials, and export textures through the DCC-MCP gateway.
pypi MIT ★ 2 -
Asimov's Three Laws compiled to real Cedar authorization policy that acts as the runtime safety layer for AI agents which touch the physical world. Governs the real SO-101 (LeRobot) arm over MCP.
★ 1 -
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 -
Capability-contract enforcement for AI agent tool calls — signed authority, a mediator that decides allow/deny/approve, and a tamper-evident ledger. Includes 3 reproducible incident labs and a conformance suite that declares its own uncovered paths.
Apache-2.0 -
MCP server giving LLM agents real authorization answers: evaluate Rego in-process via OPA, or ask an OpenID AuthZEN 1.0 PDP
go MIT ★ 1 -
mapae-mcpgithub.com/grapeinthetree/mapaeupdated this year
MCP server for Mapae - scoped, identity-bound spending authority on GIWA. The agent gets use of an authority, never the wallet.
npm MIT -
flow-ottergithub.com/jp5lab/flow-otterupdated this year
MCP server that lets AI agents author Node-RED flows a plant operator can read — computed layout, typed authoring, safety-spine staging and rollback.
MPL-2.0 ★ 1 -
evals-mcp-servergithub.com/cyanheads/evals-mcp-serverno update data
Agent-driven eval authoring via a new authoring-loop archetype — draft → subagent-review → surgical-revise → submit, with server-enforced self-consistent graders; compiles to standard harnesses.
smithery -
Hachiman Agent — autonomous security layer for AI agents and MCP. Scan before deployment, authorize before access, monitor during execution, contain when compromised, report everything. Includes an authorized offensive security skill with verified fix-on-fail loops. MIT License. Developer: Nidhish Guhan.
MIT ★ 1 -
pentest-mcp-toolkitgithub.com/KoaBrown/pentest-mcp-toolkitupdated this year
Pentest MCP Toolkit: 50 Kali Linux security tools exposed as one MCP server over Docker stdio, built to be driven 100% by AI agents (Claude Code, Codex). For authorized pentests of systems you own. You are responsible for authorization.
MIT ★ 1 -
DevDocs-MCPgithub.com/madhan-g-p/DevDocs-MCPupdated this year
Documentation Authority for AI Agents based upon Devdocs
npm NOASSERTION ★ 14 -
A small credential and authorization MCP sidecar for agent environments
MIT -
conto-mcp-serverupdated this year
Conto MCP Server - Payment authorization for AI agents
npm MIT -
OAuth for AI agents — identity authorization and trust scoring
pypi MIT -
Conto MCP Server - Payment authorization for AI agents
npm MIT -
wbotgithub.com/celados/wbotactive
Agent-first read-only CLI and MCP for authorized WeChat conversations
MIT ★ 1 -
Official OmniMod MCP server v1.7.0: 68 tools that turn any AI agent into a professional map builder and mod author. Includes CC0 3D model and game-sound libraries, a validator for hand-authored OBJ, a full connection card for every MCP client, and a watchable serve mode.
NOASSERTION -
Thoth CLI (thothctl) and MCP proxy: runtime authorization for AI agents
★ 2 -
agentgate-mcp-serverupdated this year
MCP server for AgentGate — AI agent payment authorization and governance
npm Apache-2.0 -
MCP server: author renamite rigs from an agent
cargo MPL-2.0 -
Owner-authorized, locally encrypted credentials for agents, with a local MCP server
npm Apache-2.0 -
Official stdio MCP server for server-authorized Agnostic local agent development.
npm ISC -
Reclaim Protocol MCP and agent skills for integrating user-authorized verification from online accounts.
npm MIT ★ 1 -
The MCP server developers install when they don't trust their agent with unrestricted authority.
npm Apache-2.0 -
@payclaw/badgegithub.com/payclaw/badge-serverupdated this year
Prove your agent is an authorized actor, not a bot. MCP-native identity declaration for agent commerce.
npm MIT -
@kyalabs/badgegithub.com/kyalabs-io/badge-serverupdated this year
Prove your agent is an authorized actor, not a bot. MCP-native identity declaration for agent commerce.
npm MIT -
custodian-mcpgithub.com/Zacplischka/custodian-mcpupdated this year
Governed agent-memory MCP server — fail-closed auth, strict multi-tenant isolation, audited authorization. Synthetic-data demonstration.
MIT ★ 1