Library
85,766 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
Afriref: cited government reference data
MCP serversCited official data: tax, VAT, CPI, policy rates, wages, holidays, FX. 128 countries+EU, 7 regions.
-
Earning Paths Atlas
MCP serversSourced platform rules on where AI agents and their humans can earn money: AI/bot policy, KYC, fees.
-
Riptide — public risk and event research
MCP serversRead-only paper risk evidence and policy-gated committed event research. No real orders.
-
Agentic Diaries Audit
MCP serversChecks what a support agent knew but did not say against its policies. Free tier, no login.
-
sipi.bot — Spend Firewall for AI Agents
MCP serversPre-spend firewall for AI agents. Approves, blocks, flags transactions against policy rules.
-
Hatun MCP - Governed Agent Gateway
MCP serversGoverned MCP gateway: policy gate on every tool call, hash-chained DSSE receipt on every result.
ghcr.io/szl-holdings/hatun-mcp:1.0.4 -
Eclipse Constellation MCP
MCP serversThe governed, vendor-neutral VM fleet layer for agents: one policy, one receipt ledger, every cloud
eclipse-constellation@0.1.0 -
Wiser Human Agent Escalation Line
MCP serversHelp for AI agents when their task conflicts with ethical, legal, safety or policy constraints.
-
BarzelVault: AI Action Authorization Firewall
MCP serversAuthorize AI agent tool calls before they run: policy-as-code, human approval, signed receipts.
-
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 -
AKKO MCP server for Trino
MCP serversRead-only MCP server for Trino: queries run as the verified user, and Trino's own policies decide.
akko-mcp-trino@0.8.1 -
Boundra — Payment Approval Gateway for AI Agents
MCP serversAllow, ask, or veto — a policy decision point your agent consults before signing any payment
boundra-mcp@0.2.0 -
Eclipse Deep Field MCP
MCP serversThe governed database layer for agents — every store in one look, under policy: read-only by
-
Zero-cost in-memory legal terms, API policy & NDA scanner for autonomous coding agents
@ritualdev-lab/fineprint@0.1.1 -
Critical dates found in leases, loans, policies, HOA docs, contracts, clause if known. By Built AI.
-
Erik Bethke's Blog & Knowledge Graph
MCP serversSearch, read, and traverse 3,800+ posts on AI, energy, policy, games, and investing as a graph.
-
Critical dates and deadlines in leases, loans, policies, HOA docs and contracts, with the clause.
-
ClaimGate starter kit - set up a publish gate
MCP serversSet up a publish gate for AI-assisted marketing copy: policy, evidence folder and CI job.
https://github.com/caseone115/claimgate/releases/download/v0.1.0/claimgate-kit-0.1.0.mcpb -
AI Law Framework: firm knowledge
MCP serversA signed-in firm's own AI policies, know-how and adopted precedents. Needs a firm account (OAuth).
-
AIC — agent-native credits (read-only)
MCP serversFind AI-agent sellers, read AIC supply and join policy. Read-only; buying is done client-side.
-
Mandate Law: legal counsel for AI products
MCP serversFixed-fee legal review for AI apps and agents: privacy policies, terms, AI and agent compliance.
-
vibops-mcp
MCP servers117 MCP tools for GPU infrastructure + Agent FinOps — deploy LLMs, manage VMs (Proxmox/XO/vSphere), track cost per agent, enforce budgets and model policies. Works with Claude, Cursor, n8n, LangChain
git clone https://github.com/VibOpsai/vibops-mcp.git -
AI industry news (TechCrunch): launches, funding, policy. Be born in one call — free testnet funds.
-
ai·rete·rag
MCP serversAuthor rules from policy docs, then decide: a Rete engine gives the verdict, an LLM explains why.
ai-rete-rag-mcp@0.11.1
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.