- Thingctx @thingctx/thingctxDrive devices and APIs from their W3C Thing Description. You gate every operation.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.16 GitHub stars.
- IdentArk Gateway @identark/gatewayZero-secret MCP gateway for AI agents: risk-scored, audited calls with human-in-the-loop approval.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.16 GitHub stars.
- Lians Agent Memory @ebeirne/liansBitemporal memory for AI agents with point-in-time recall and tamper-evident audit history.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.16 GitHub stars.
- LLM CLI Gateway @verivus-oss/llm-cli-gatewayOne MCP endpoint for Claude Code, Codex, Gemini, Grok and Mistral CLIs, with durable async jobs.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.16 GitHub stars.
- Phantom Secrets @ashlrai/phantom-secrets-mcpValue-blind secret metadata and gated workflows for AI coding agents through Phantom's local proxy.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.16 GitHub stars.
- Vaara MCP Server @vaaraio/vaara-serverAccountable autonomy MCP server: gating, tamper-evident audit for every action5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.15 GitHub stars.
- ReasonGate @cgrtml/reasongateProvenance gateway for stdio MCP servers: blocks tool calls fed by untrusted tool results.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.15 GitHub stars.
- SysKnife @lacs-project/sysknifeAdministers Linux via typed, approval-gated actions with an Ed25519-signed audit trail.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from cargo.15 GitHub stars.
- s-gw @sgateway/s-gwKeep credentials out of AI coding agents with local approvals, scoped injection, and audit trails.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.15 GitHub stars.
- Midas @vornicx/midasLocal-first, source-traceable agent memory — no LLM at ingest, fully offline6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.15 GitHub stars.
- Vaara @vaaraio/vaaraAccountable autonomy proxy: gating, tamper-evident audit, time anchor for every action6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.15 GitHub stars.
- Crabeye Bridge @crabeye-ai/crabeye-mcp-bridgeOne MCP connection for all your tools — with discovery, namespacing, and execution policies.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.15 GitHub stars.
- Sidclaw Governance @vladuzh/sidclaw-governance-mcpGovernance proxy for MCP servers — policy evaluation, human approval, audit trails.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.15 GitHub stars.
- Orbit @constellation-works/orbitOrbit's local-first task and workflow registry for coding agents.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.14 GitHub stars.
- Aegis @getaegis/aegisCredential isolation for AI agents. Inject secrets at the network boundary.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.14 GitHub stars.
- Infrabroker @luisgf/infrabrokerSSH & Kubernetes access broker for AI agents; the model never touches a credential.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.13 GitHub stars.
- Assay @rul1an/assayThe firewall for MCP tool calls. Block, audit, replay with evidence bundles.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.12 GitHub stars.
- Stepgate @chaarangan/stepgateAgents can't skip steps: runs gated stepfiles on the client's own model.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.12 GitHub stars.
- MobiLoop @enessubass/mobiloop-mcpGuarded AI mobile Appium testing, security scanning, verification, and fix-retest MCP tools.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.12 GitHub stars.
- Behavior Runtime MCP @putervision/behavior-mcpIn-browser ~60Hz behavior tree execution engine with reactive triggers and blackboard projection.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.12 GitHub stars.
- Aletheia Runtime Safety & Scope Creep Filter @vikasny30/aletheia-mcpDeterministic pre-execution filter that blocks known scope-creep and prompt-injection tool calls5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.12 GitHub stars.
- SkillTotal @skilltotal/skilltotalDeterministic security scan of MCP servers, agent skills and npm/PyPI packages. Runs locally.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.12 GitHub stars.
- TAP @human/tapCredential isolation for AI agents: placeholder secrets, policy checks, optional human approval.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.12 GitHub stars.
- Cortex Gateway @wellknownmcp/cortex-gatewaySelf-hosted federated MCP gateway: one OAuth 2.1 MCP server in front of N apps, user-level scopes.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.12 GitHub stars.
