- Attest proxy @dev-prathap/attest-proxyZero-code proxy: policy, human gate, read-back and a hash-chained ledger for any MCP server.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- Sealgate @edison-watch/sealgate-mcpSealgate gateway proxy: list governed MCP servers and review agent session and audit status.12% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- MarketNow @marketnow/marketnow68k+ security-audited MCP skills + free agent trust layer: signed ATC cards, tool gating, audits.11% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- ForgeBridge @t1ktakdev/forgebridgeA local, permissioned MCP agent for authorized developer workstations.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- isitdone @raimondasl/isitdoneMake a coding agent prove it: run the repo's real tests, typecheck and lint before it says done.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- CRA AGENT @giupy997/cra-agentLets an agent pay for x402 APIs in USDC on Arc, under a spending policy it cannot change.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Attest @dev-prathap/attestDecide by policy, gate behind a human, verify by read-back, record a hash-chained ledger.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- Pursers @swisspra/pursersCoordinate AI-agent work on a local-first, owner-controlled MCP board5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.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.
- Data Prism @aindriub/data-prismFail-closed privacy layer that pseudonymises enterprise API data for LLM agents and MCP clients.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.1 GitHub stars.
- Cost Guard MCP @mcpsmiths/cost-guard-mcpPre-flight query cost and result-size guardrails for AI agents on BigQuery, Snowflake, Databricks3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- Tkach Security @ecd5a/tkach-securityFail-closed MCP adapter for untrusted model output over a local Tkach runtime.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from cargo.1 GitHub stars.
- CCS Runtime Evidence @dshcorrectover/ccs-mcp-serverAgent tool-call guardrail: fail-closed runtime security verification with Ed25519 evidence receipts.9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Clay Seal @clayseal/claysealAuthorizes MCP tool calls against a session policy, not one call at a time.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- Aggrete @aggrete/aggreteMCP policy proxy: enforces a code of conduct across connectors before the upstream is called.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- YunoHost MCP @imattau/yunohost-mcpNostr-authenticated MCP server for secure YunoHost administration.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- HEIDES @abduljabbarbxr/heidesDeterministic code analysis harness giving AI agents senses, memory and judgment for code.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.1 GitHub stars.
- PolicyVault @zapsoblige-hash/policyvaultNon-custodial Kaspa policy enforcement for AI agents; signers retain custody.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Phases Agents @cherridsaid/phases-agentsDeterministic skill selection: local discovery, strict validation, every skill classified.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- Enterprise Gateway @benjaminj/enterprise-mcp-gatewayProduction-grade MCP Gateway in Go with RBAC, in-flight PII redaction, and audit logging.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.1 GitHub stars.
- Trazum @davmunrey/trazumTrazum as an MCP server: let an agent price and budget its own prompts before it sends them.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Cedulon @dogrucanemek-alt/cedulonPolicy-gated agent spend with signed receipts and rail-extract audit5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Azure DevOps @dockndevai/mcp-azure-devopsAzure DevOps boards, repos, pipelines & projects for AI agents — governed.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- OrchestrUI @ecd5a/orchestruiDeterministic UI policy, discovery and audits for coding agents across seven ecosystems.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
