Library
87,246 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
Corresync
MCP serversLocal-first mail, calendar, and task MCP with isolated accounts and guarded writes.
https://github.com/nkiyohara/corresync/releases/download/v0.9.4/corresync_0.9.4.mcpb -
aiglare
MCP serversAudit AI/LLM features for governance guardrails: confidence, fallback, validation, human-in-loop.
@nugehs/aiglare@0.2.3 -
x64dbg MCP
MCP serversWindows x64dbg/x32dbg debugging with guarded sessions, breakpoints, memory and runtime evidence.
https://github.com/rison1337/x64dbgMCP/releases/download/v0.1.9/x64dbg-mcp-v0.1.9.mcpb -
tracelane-mcp
MCP serversRead-only, tenant-scoped access to Tracelane agent traces and guardrail verdicts
@tracelanedev/mcp@0.4.0 -
agentrisk
MCP serversRisk guardrails for AI trading agents. Your agent proposes; your policy decides.
agentrisk@0.1.3 -
suprawall-mcp
MCP serversSupraWall security gateway for AI agents. Provides deterministic guardrails for MCP agents.
suprawall-mcp-plugin@0.1.0 -
Polis Protocol
MCP serversLocal-first control plane for coding agents: routing, reservations, and guardrails.
polis-protocol@2.0.1 -
Whiskers
MCP serversGoverned Docker and Kubernetes operations for AI agents: scoped keys, guardrails, human approvals.
ghcr.io/lupusmalusdeviant/whiskers:0.15.0 -
protect-context
MCP serversAgent guardrails: contract, evidence ledger, loop brake, diff-scope warnings, durable journal.
protect-context@3.3.1 -
rail-score
MCP serversResponsible-AI guardrails for agents: scoring with policy, injection & PII detection, DPDP.
-
ThinkNEO Control Plane
MCP serversEnterprise AI Control Plane: governance, guardrails, spend tracking, compliance & smart routing.
-
JevStation
MCP serversTyped-question decisions from Jev: classify, moderate, route models and guard tool calls.
-
Arc Control (macOS)
MCP serversArc browser MCP for macOS: agent window, snapshots, DevTools input, guardrails
arc-control-mcp@0.4.0 -
audrey
MCP serversLocal-first biological memory for coding agents: recall, consolidation, and pre-action Guard checks.
audrey@2.1.1 -
oraclemcp
MCP serversEngine-free, governed Oracle Database MCP server with a fail-closed SQL guard (unofficial).
ghcr.io/muhdur/oraclemcp:0.11.0 -
ovecc
MCP serversArchitecture guardrails for AI-written code: dependency graph, impact, dead code, CI gate
ovecc@0.3.1 -
Cloud DevOps MCP Server
MCP serversCloud DevOps analysis with guarded Git, infrastructure, cloud and observability operations.
cloud-devops-mcp-server@0.14.0 -
safeagent
MCP serversExactly-once execution guard for AI agents. Prevents duplicate payments and webhooks on retry.
safeagent-exec-guard@0.1.22 -
Regex Lab
MCP serversTest regular expressions in a timeout-guarded worker, explain them, find catastrophic backtracking.
ghcr.io/basitalisandhu/mcp-regex-lab:0.3.0 -
mcp-kubernetes
MCP serversKubernetes monitoring & ops for AI agents — safe-by-default access modes and guards.
@dockndevai/mcp-kubernetes@0.3.3 -
mcpm
MCP serversMCP security guard + package manager: trust-scored installs, blocks prompt injection and rug-pulls.
@getmcpm/cli@0.54.0 -
MySQL MCP
MCP serversMCP server for one MySQL database: schema, read-only queries and guarded writes.
mcp-mysql-client@1.1.1 -
GroundLens
MCP serversGuardrails for LLM answers: exact checks against sources, PASS/REVIEW/FAIL, signed records.
groundlens@6.0.5 -
sevdesk-mcp
MCP serversComplete sevDesk MCP server: all API endpoints, guarded writes, built-in bookkeeping audits.
sevdesk-mcp@0.6.0
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.