1. Conduid
  2. Marketplace
  3. #capability-security
Tag

MCP servers tagged capability-security

16 live MCP servers tagged "capability-security", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with capability-security.

16
live servers
38
avg trust
10K
most stars
1

Astrid

Astrid is a portable, capability-secure operating system for composable software.

★ 10K
64
2

Astrid

astrid-runtime

Astrid is a portable, capability-secure operating system for composable software.

★ 10Kupdated 6 days agoApache-2.0
64
3

Decision Os Min

Aliipou

Execution governance for AI agents: signed action-bound decisions, Hosted effect mediation, replay resistance, and evidence-scoped isolation.

★ 6updated a month ago
34
4

PAL

A daily-driver AI agent runtime built solo: multi-process isolation pods (MCP/LSP/workflow), event-sourced task ledger, proactive scheduling, and multi-channel delivery.

★ 2
34
5

Prx

bounded-systems

The agent-run work-unit CLI: capability-scoped agents whose every privileged effect is verified against its signed owner, driving a work unit through one signed pipeline to a merg…

★ 1updated a month ago
34
6

Openclaw Nie Guard

xsoc-corp

Cryptographic trust mediation layer for AI agent frameworks. Apache 2.0 reference architecture composing device-attested admission, short-TTL scoped capabilities, runtime continui…

★ 1
34
7

Boj Server Cartridges

Canonical registry of BoJ capability cartridges — each one a machine-checked ABI, a five-symbol C-ABI implementation and a loopback adapter, minted from a single template. Hosts (…

34
8

Command Scope Contract

Bounded shell and CLI execution for AI agents: structured contracts, policy-gated execution, hardened Linux runtime enforcement, and signed receipts.

34
9

Autopentest MCP

Capability-gated MCP-style tool server for pentest agents: four gates (capability, scope, policy, run) the agent cannot exceed, plus a tamper-evident hash-chained audit of every c…

34
10

Solarplex

Governed workspaces for humans and AI agents

34
11

Vcp

hassard0

VCP — Verifiable Capability Protocol: zero-trust capability execution for AI agents. A stricter sibling of MCP where models plan and a signed gateway enforces. Signed content-addr…

34
12

Claude Box

bounded-systems

A capability-secured box for agent sessions — its authority is the door references it holds (keeper/scout/concierge/net), parent-agnostic.

updated 4 months ago
34
13

Oowatch

openOODA-tools

Continuous command scheduler and delta watcher with ANSI diff highlighting and MCP surface

34
14

Preflight

2654-zed

Capability-aware risk scoring for AI coding agent tool calls. Five-dimensional decomposition, session-graph composition, repo awareness, the Agent Control Plane and Confused Deput…

updated 5 months ago
34
15

Oocurl

openOODA-tools

Capability-bounded HTTP and API client with syntax-highlighted responses and MCP surface

updated 10 days ago
34
16

MCP

openOODA

MCP server for openOODA. 26 capability-aware tools for agents: check, emit, build, run, query, and blackbox flight inspection.

updated 10 days ago
34
← Previous Page 1 of 1 Next →