- Trusty Squire @trustysquire/trusty-squireProvision, ship, and pay from your coding agent — keys and cards never leave the vault.12% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.3 GitHub stars.
- Insumer @insumermodel/insumerWallet auth: send a wallet and conditions, get a signed boolean across 37 chains.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.2 GitHub stars.
- Microsoft Entra SCIM @darrenjrobinson/entra-scim-mcpMicrosoft Entra SCIM 2.0 Provisioning API: user and group lifecycle, with a local mock.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- Raziel @tide-foundation/razielMCP server teaching AI agents to implement TideCloak: auth, E2EE, IGA, security analysis6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.2 GitHub stars.
- Keycloak Admin @mrz1880/mcp-keycloak-adminAdminister Keycloak via its Admin REST API: users, roles, clients, groups, IdP, events.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- Waxseal @degenlegion-com/waxsealEd25519 identity for AI agents. Verify seals, sign documents, gate actions with approvals.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- PrivacyFence @privacyfence/privacyfenceNeeds the PrivacyFence app from privacyfence.eu: human approval and audit for AI access to your dataNot assessed yet.Runs on your machine, installed from MCPB.1 GitHub stars.
- Nacre @nacre/nacreSelf-hosted permission-aware context layer. Search returns only what the caller may read.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- CorroborateMe @cnrcode/corroboratemeProve end users to agents and apps: login-links, OIDC clients, and API keys over remote MCP8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.1 GitHub stars.
- Mnki @mnkiagentos/mnki-mcpMCP proxy that checks every tools/call against Agent Trust policy, with evidence, before it runs.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Boat House @boathousecloud/boathouseDeploy and share small apps with team login, persistent data, versioned updates and domains.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.1 GitHub stars.
- Keycloak @dockndevai/mcp-keycloakKeycloak admin for AI agents — realms, users, clients, roles; safe-by-default governance.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- SealGate MCP Gateway @sealgate/gatewayMCP gateway with runtime security policy, tool-call-level control, and audit of agent actions.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.1 GitHub stars.
- AgentEnvelope @blackboxengineering/agent-envelope-mcpNeutral MCP server for AgentEnvelope authority: sovereign verify + vault verify/lookup/mint.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Grantd @rafavecchi/grantdGrantd MCP server: let your AI agent act on a user's behalf across third-party APIs via OAuth.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- LiveAuth @dulzuradev/liveauth-mcpMCP server for LiveAuth: PoW + Lightning auth, L402 bundles, and paid MCP tool receipts.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Attest @chudah1/attest-mcpCredential enforcement middleware for MCP servers — verifies scoped tokens on every tool call4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- FusionAuth MCP @fusionauth/mcp-apiPreview release of FusionAuth API MCP server4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Auth Token Service @mikerawsonnz/auth-token-serviceHash passwords with bcrypt and issue/verify JWT session tokens over A2A + MCP.22% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.1 GitHub stars.
- Oakallow @oakallow/oakallowRuntime permission, approval, and audit layer for AI agent tool execution.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.1 GitHub stars.
- AgentSIM MCP @agentsim/mcpControl plane for agent auth walls. Connector 0 handles SMS OTP with US test numbers.23% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.1 GitHub stars.
- Qdrant RBAC @fidonis/qdrant-mcp-rbacRole-based access to your Qdrant vector store, via MCP. OIDC in, scoped JWTs out.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.
- 4chems Platform — IUCLID, CHESAR & QSAR Toolbox hosting @4chems/platform-apiRemote MCP server for 4chems hosted IUCLID, CHESAR and QSAR Toolbox: onboarding, inquiries, admin.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- The Bridge @thebridge/bridgeHosted login, teams, billing and feature flags for your SaaS app, set up by your AI assistant.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
