Library
85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
Talkenda MCP Server
MCP serversSearch and edit Talkenda meeting transcripts, notes, decisions and action items through OAuth.
-
lastseen mortality
MCP serversCheck whether an npm package, GitHub Action, MCP server or Docker image is dead or abandoned.
lastseen-mcp@0.1.2 -
delego
MCP serversIntent-bound action authorization for AI agents: policy, human approval, and a signed audit trail.
delego@0.3.4 -
agent-services-mcp
MCP serversMCP server: x402-paid & free tools for AI agents — provenance, quality scoring, action audit.
agent-services-mcp@0.2.1 -
agent-trust
MCP serversTamper-evident action receipts, trust scoring & capability tokens for AI agents. 29 MCP tools.
@garl-protocol/mcp-server@1.4.3 -
InterAI Risk Oracle
MCP serversPre-execution policy gate for consequential agent actions with durable trust receipts.
-
Kaval
MCP serversVerify the facts an agent's action depends on before it acts — ALLOW, REVIEW, or BLOCK.
@usekaval/mcp@0.7.1 -
hoodgrow-mcp
MCP serversRobinhood Chain stock token data — price, split-adjusted supply, DeFi, corporate actions, movers.
hoodgrow-mcp@0.9.1 -
LeakRank Guard
MCP serversScans code changes for leaked secrets and insecure config, with actionable fixes for AI agents.
leakrank-guard@0.2.3 -
HeyAnon MCP
MCP serversHeyAnon on-chain agent: wallets, portfolios, DeFi and CEX actions, transfers, Gemma research.
-
Island Browser
MCP serversMCP server for Island Browser's Admin Actions, Audit, Compromised Credential, and Device APIs.
ghcr.io/wyre-ai/island-mcp:v1.0.3 -
Almega
MCP serversThe immutable delegation frame for AI agents: gate any sensitive action, human-in-the-loop.
almega-mcp@0.2.0 -
atlas-mcp
MCP serversPre-action authorization for AI agents: permit, deny or escalate against a signed delegation chain.
@corpussanctum/atlas-mcp@0.1.1 -
jevnav
MCP serversReplayable browser automation: Jev picks the element, a gate blocks risky actions, every run traces.
jevnav@0.2.2 -
Cyphrex
MCP serversChecks AI agent actions before they run. Signed, RFC 3161 timestamped evidence for audits.
-
mail
MCP serversApple Mail over MCP: fenced reads, draft-only writing, human-gated actions, audited with undo.
@honeycrisp/mail@0.1.2 -
cowork-qa
MCP serversGoal-driven Playwright browser sessions for LLMs, with full action traces and aria-snapshots.
cowork-qa-mcp@0.1.1 -
consentgate-mcp
MCP serversGate AI agent actions behind a consent policy with human approval via Telegram. Fail-closed.
consentgate-mcp@0.1.1 -
Model MCP
MCP serversRevit tools over MCP stdio. Actions are enabled by default; the workstation lock disables them.
revit-model-mcp@2.0.0 -
Agent Toolbox
MCP servers26 deterministic, offline pre-action safety gates for AI agents, each with a signed verdict.
agentoolbox-mcp@0.1.4 -
HiveAttest
MCP serversPre-action attestation perimeter for AI agents — 8 primitives, signed C18 receipt per call.
-
Scanduro
MCP serversRemote MCP server for Scanduro QR codes, scan analytics and controlled code actions.
-
MCP Output Firewall
MCP serversThree-layer firewall for MCP: content, egress and action policy. Proxy or server.
mcp-output-firewall@0.3.0 -
skillsindex
MCP serversSearch and score 11,000+ AI agent tools: MCP servers, Claude skills, GPT actions, IDE plugins.
skillsindex-mcp@0.2.1
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.