Library
86,219 resources from 11 public sources. 46 checked by hand; the rest are unreviewed.
Results
-
Brevet
MCP serversChange control for what AI agents learn: humans promote, releases are signed, rules can be recalled
brevet@0.4.0 -
delego
MCP serversIntent-bound action authorization for AI agents: policy, human approval, and a signed audit trail.
delego@0.3.4 -
mutual
MCP serversIntroductions network: your AI agent flags people privately, theirs flags back, two humans decide.
-
MCP Doctor
MCP serversCheck and improve the contract quality of any MCP server — for humans, agents, and platforms.
mcp-doctor@0.1.0 -
INCOME 2
MCP serversAutonomous earning and outcome routing: Agent Earn, Human Earn, Purchase Guard, and HYDRA.
-
StackMap
MCP serversSearch 344 human-reviewed AI/agent repos and the 817 typed connections between them.
@ship-with-ai/stackmap-mcp@0.2.2 -
Tendem MCP server
MCP serversDelegate tasks to vetted human experts - research, writing, analysis, and data work.
-
rednote-gate
MCP serversMCP server for one throwaway RedNote account. Every write waits for a human Approve click.
rednote-gate@1.1.1 -
Almega
MCP serversThe immutable delegation frame for AI agents: gate any sensitive action, human-in-the-loop.
almega-mcp@0.2.0 -
hubd
MCP serversThe project tracker for teams of humans and AI agents — in plain files. MCP server + CLI.
@bzdos/hubd@0.4.2 -
Covalt Execution Gateway
MCP serversTrusted execution infrastructure for AI agents. Proposal-only protocol with human consent.
-
reliefweb-mcp-server
MCP serversSearch ReliefWeb humanitarian reports, disasters, jobs, training, and country profiles via MCP.
@cyanheads/reliefweb-mcp-server@0.3.0 -
mcp-gera-witness
MCP serversGeraWitness MCP (placeholder) — human-in-the-loop safety layer for AI agents. Launching 2026.
@gera-services/mcp-gera-witness@0.1.1 -
mail
MCP serversApple Mail over MCP: fenced reads, draft-only writing, human-gated actions, audited with undo.
@honeycrisp/mail@0.1.2 -
consentgate-mcp
MCP serversGate AI agent actions behind a consent policy with human approval via Telegram. Fail-closed.
consentgate-mcp@0.1.1 -
Flottix
MCP serversDeterministic IT asset registry operated by AI agents over MCP. Agents propose, humans approve.
-
Molt2Meet
MCP serversDispatch real-world physical tasks to verified human operators. Escrow or direct-settlement.
-
Terrarium
MCP serversHuman visual review for agent-built HTML: publish artifacts, pull anchored comments, push fixes.
-
SMTP
MCP serversMCP server that sends mail over SMTP, gated behind an allowlist and a human confirmation
@ni-c/smtp-mcp@0.2.0 -
Rove
MCP serversRove — supervised browser for AI agents. Your agent drives; a human watches, takes over.
@roveapi/mcp@1.18.1 -
Global Agent Memory
MCP serversShared, project-aware memory for Claude Code, Codex, and other agents with human review.
global-memory-mcp@0.1.6 -
posecode-mcp
MCP serversAuthor, ROM-validate, and render 3D human movement (.posecode) with a shareable playground link.
posecode-mcp@0.5.0 -
Graphiti Local
MCP serversLocal-first temporal knowledge graph with six read-only MCP tools and human-reviewed writes.
graphiti-local@0.11.0 -
SpeedContent Social
MCP serversGenerate platform-native social posts that are humanized, AI-detection scored and illustrated.
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.