Library
85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
-
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.
-
clawock
SkillsStock investment and portfolio decision workflows for AI agents: Claude Code, Codex, OpenClaw, DeepSeek Harness (dsh plugin) or your own script. Agents argue bull vs bear on HK and US stocks; Python reconciles the book, gates risk and scores each trading call against market prices. Pluggable quant strategies, live real-money track record.
git clone https://github.com/KCNyu/clawock.git -
second-shift
SkillsScheduled agent tasks for your repositories, defined in Git. Approved access, sandboxed runs, a full audit trail.
git clone https://github.com/piotrekno1/second-shift.git -
DataNexa
MCP serversDataNexa is a local, read-only database MCP gateway for AI agents. It routes SQLite, MySQL, PostgreSQL, and any JDBC-compatible database through a single localhost endpoint, enforces read-only access via SQL AST validation with row, time, and connection limits, and keeps a local audit trail of every query.
git clone https://github.com/MingoZacwu/DataNexa.git -
agenticos
MCP serversOpen-source, self-hosted AI agent platform for your company's AI teammates. Build, run and govern agents on your own servers and models: shared chat, RAG, skills, a real browser, 4,700+ MCP servers, budgets, approvals and an audit trail. An alternative to ChatGPT Enterprise and Grok Bot. Apache-2.0, built on Pydantic AI.
git clone https://github.com/vstorm-co/agenticos.git
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.