Related Servers

• dingdawg-governance

  dingdawg

  A

  license

  A

  quality

  D

  maintenance

  Universal governance layer for AI agents — MCP-native, fail-closed, LNN interpretability. Governed receipts, IPFS audit proofs, and rollback for any agent in any framework.

  Updated 3 months ago (2026-08-06 18:50 UTC)

  3

  38 npm

  Apache 2.0

• dingdawg-loop

  dingdawg

  A

  license

  -Not graded

  quality

  D

  maintenance

  DingDawg Loop Protocol (DDLP) — safe scheduled AI agents with governance gates. Every loop execution is verified, receipted, and fail-closed. MCP-native, works with CrewAI, LangGraph, Claude Code, Cursor.

  Updated 3 months ago (2026-08-06 18:52 UTC)

  29 npm

  MIT

Related Servers

• kevros-mcp

  taskhawk-systems

  A

  license

  -Not graded

  quality

  -Not graded

  maintenance

  Governance primitives for autonomous agents. Verify actions against policy, record signed provenance, and bind intents cryptographically. Free tier available.

  Updated 7 months ago (2026-04-04 04:31 UTC)

  -
• 

  agentguardofficial

  agentwares

  A

  license

  -Not graded

  quality

  A

  maintenance

  Enforces policy controls for AI agents, including spend limits, action approvals, kill switch, scoped credentials, dry-run diffs, loop prevention, and auditable hash-chained logs.

  Updated 13 days ago (2026-10-09 04:57 UTC)

  MIT
• 

  AgentValetofficial

  AgentValet

  A

  license

  A

  quality

  B

  maintenance

  Identity and credential governance for AI agents. Every agent gets its own cryptographic identity, scoped short-lived credentials per platform, human approval on sensitive actions, and an immutable audit log.

  Updated a month ago (2026-09-26 08:25 UTC)

  7

  2

  MIT

• Vector Decisions MCP Server

  NikitaDatar

  A

  license

  B

  quality

  B

  maintenance

  Provides AI governance and action-assurance primitives, enabling trust scoring, policy-based allow/deny decisions, risk assessment, EU AI Act compliance checks, and an emergency kill-switch for autonomous agents.

  Updated 2 months ago (2026-08-14 14:49 UTC)

  6

  25 npm

  MIT

• mcpcut

  RostislavMatov

  A

  license

  -Not graded

  quality

  A

  maintenance

  A local proxy in front of any MCP server for developers on Claude Code or Cursor: see every tool call your agent makes, hold the risky ones for your approval, and keep a secret-redacted journal that is tamper-evident with an external anchor.

  Updated 12 days ago (2026-10-10 15:09 UTC)

  76 npm

  1

  Apache 2.0
• 

  mcp-vaaraofficial

  vaaraio

  A

  license

  A

  quality

  A

  maintenance

  Gates every AI agent tool call against your policy before it runs, then writes a hash-chained, tamper-evident record of what was decided and what happened. Anyone can verify that record offline, without your software, your systems or any key you hold.

  Updated 3 days ago (2026-10-19 11:24 UTC)

  4

  1,769 PyPI

  15

  AGPL 3.0