Related Servers

No user-submitted related servers found.

Related Servers

• MCP Airlock

  lara-muhanna

  A

  license

  C

  quality

  D

  maintenance

  Enables secure, zero-trust access to MCP tools through short-lived, signed capability leases that bind tool execution to specific sessions, intents, and constraints. Prevents prompt injection attacks and privilege escalation with dynamic risk scoring, policy enforcement, and tamper-evident audit logging.

  Updated 6 months ago (2026-04-04 16:03 UTC)

  4

  1

  MIT

• latchkey

  SanjoyDat1

  A

  license

  -Not graded

  quality

  C

  maintenance

  Capability-token gate for AI agents. Mint time-boxed, scope-limited grants that authorize specific tool calls.

  Updated 2 months ago (2026-07-22 11:11 UTC)

  3,793 npm

  MIT

• pod

  suhui-organization

  A

  license

  A

  quality

  A

  maintenance

  Least-privilege compiler and MCP gateway for AI agents: run your agent in record-only mode, compile the smallest policy it actually needs from its real tool calls, enforce it at the gateway (deny > approve > allow), and keep a SHA-256 hash-chained audit of every call that verifies offline.

  Updated 8 days ago (2026-09-18 08:54 UTC)

  14

  179 npm

  1

  Apache 2.0
• 

  Outfitofficial

  MyceliumInc

  A

  license

  -Not graded

  quality

  C

  maintenance

  An MCP server that enforces agent persona permissions by acting as a gateway, scoping tool access and denying unauthorized capabilities.

  Updated 7 days ago (2026-09-20 08:02 UTC)

  9 npm

  7

  MIT

• Secure Agent MCP Gateway

  aki83reo

  F

  license

  -Not graded

  quality

  C

  maintenance

  Enables AI agents to safely call MCP tools through a security gateway that enforces per-role authorization and least-privilege tool scoping.

  Updated a month ago (2026-08-22 08:54 UTC)

  1

  -
• 

  agentguardofficial

  MerchantGuard

  A

  license

  A

  quality

  C

  maintenance

  Enables local spend caps and Ed25519-signed provenance receipts for AI agent tool calls, allowing any MCP host to gate model usage and independently verify signed decisions without sending prompts or content.

  Updated 5 days ago (2026-09-21 18:11 UTC)

  6

  66 npm

  -