Library
85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
HoldTheWheel
MCP serversPlan and approve automation in a shared workspace with spend limits and an audit trail.
-
caura
MCP serversCaura (formerly MemClaw) — governed shared memory for AI agent fleets. Multi-agent, multi-tenant, MCP-native. Trust tiers, keystone policies, audit trails, knowledge graph, self-improving retrieval. Apache 2.0.
git clone https://github.com/caura-ai/caura.git -
Gentkey
MCP serversOne MCP URL for all your connectors — scoped writes, enforced constraints, and a full audit trail.
-
BailingHub for Business Operations
MCP serversLet AI agents query and operate business systems with authorization, approval and audit trails.
bailinghub-mcp-server@0.8.0 -
rails-mcp
MCP serversDefault-deny action registry, append-only spend ledger, and human sign-off audit trail (MCP tools).
rails-mcp@0.1.0 -
mcp-gateway
MCP serversIdentity, authorization, audit trails, and revocable permissions for AI agents accessing MCP tools.
-
eContract
MCP serversSend contracts for e-signature, track signing, get signed PDFs and audit trails, verify any PDF.
-
vorim-mcp-server
MCP serversAI agent identity, permissions, trust scores, and tamper-evident audit trails via Vorim AI
@vorim/mcp-server@1.1.15 -
handinloop-mcp-server
MCP serversHuman-in-the-loop document extraction: submit a doc, get validated fields and an audit trail.
handinloop-mcp-server@0.5.0 -
mova-flat-runner
MCP serversGoverned AI workflows with human approval gates and audit trails for Claude and MCP clients.
mova-mcp@2.0.6 -
REMAP
MCP serversUp to 90% fewer tokens: deterministic, declared tool calls, each with a receipt and an audit trail.
-
SetLatch
MCP serversPrivacy requests (DSARs) for every site you run: triage, app look-ups, tasks and the audit trail.
-
k11 Playwright QA
MCP serversUser stories to verified Playwright tests, and self-healing locators with an audit trail.
k11-playwright-qa-mcp@0.3.0 -
agent-receipts-mcp
MCP serversEU AI Act-ready audit trail: signed, tamper-evident receipts proving what your AI agents did.
agent-receipts-mcp@0.1.2 -
AI Tasker
MCP serversTask and sprint coordination for humans and AI agents, with scoped API keys and full audit trail.
-
Eclipse Agent Wallet MCP
MCP serversPolicy-scoped agent wallet: caps, recipient allowlist, human approvals, kill switch, audit trail.
ghcr.io/cyan-eclipse-technologies-llc/agent-wallet-mcp:2842d69a363c4412a4c1347878fd27b7ca9d9aeb -
peta-core
MCP serversThe Control Plane for MCP — secure vault, managed runtime, audit trail, and policy-based approvals.
git clone https://github.com/dunialabs/peta-core.git -
Elicitly Pro
MCP serversHuman-in-the-loop for AI agents over MCP: durable approvals with a hosted review page & audit trail
-
handinloop-mcp-server
MCP serversHuman-in-the-loop document extraction: submit a doc, get validated fields and an audit trail.
handinloop-mcp-server@0.9.1 -
k11 Selenium QA
MCP serversSelenium tests from user stories (Python or Java) and self-healing locators with an audit trail.
k11-selenium-qa-mcp@0.2.2 -
obsigna
MCP serversAgent Receipts — cryptographically signed audit trails for AI agent actions. Protocol spec, SDKs (Go, TypeScript, Python), and MCP proxy.
git clone https://github.com/agent-receipts/obsigna.git -
Validated trading edges across futures, equities, crypto. Live signals, full audit trail.
-
Marrow AI: Control Layer for AI Agents
MCP serversApproval gate and audit trail for AI agent actions: policy check first, proof after. Any MCP client.
@getmarrow/mcp@3.9.114 -
Human-in-the-loop review and approval for AI agents. Audit trail, approval policies, native MCP.
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.