Library
85,861 resources from 11 public sources. 47 checked by hand; the rest are unreviewed.
Results
-
day1work
MCP serversHuman-and-agent marketplace: find work, post tasks, bid, chat, request payments.
-
Atoll
MCP serversProject management for humans and AI agents: goals, metrics, projects, and issues.
-
Whiskers
MCP serversGoverned Docker and Kubernetes operations for AI agents: scoped keys, guardrails, human approvals.
ghcr.io/lupusmalusdeviant/whiskers:0.15.0 -
StealthGPT
MCP serversHumanize text, generate content drafts, and retrieve run results through StealthGPT.
-
handwork
MCP serversCommission physical-world tasks from a human service: list services, request quotes, track.
@reneturcios/handwork@0.1.0 -
Recala
MCP serversManage Recala articles, topics and search visibility with human-approved publishing.
-
Colba
MCP serversRun business workflows and route requests for human approval from AI agents.
-
Awesome-AI4AI
Datasets & benchmarksUpdated weekly — until humanity achieves AI4AI. 1462 curated papers across Benchmarks, Harness Design, and Model Design — from long-horizon agents to recursive self-improvement. Citation rankings, GitHub stars, and source-verified weekly news.
git clone https://github.com/KaiWU5/Awesome-AI4AI.git -
beatra-skills
SkillsAgent Skills for Claude Code, Cursor, Codex, Windsurf, Cline & OpenClaw: AI image generation, text to speech, talking head video, AI music, and video generation skills that render on Beatra. 图片生成 · 配音 · 数字人 · AI 作曲
git clone https://github.com/beatra-ai/beatra-skills.git -
Agent Inbox
MCP serversA real email inbox for AI agents: human-approved sends, untrusted-by-default inbound.
@clize/inbox@0.35.5 -
gateway
MCP serversGoverned AI actions with signed, verifiable receipts: free keyless reads, human-approved writes.
-
kanonik
MCP serversGovernance runtime for compliance: verified, human-approved writes to a tamper-evident record.
-
Agora Merit
MCP serversFree job-responsibility assessments with report quotes and private human review links.
-
mcp
MCP serversPlay ranked FluxDots matches against humans on a shared Elo ladder. Zero-dependency stdio server.
fluxdots-mcp@1.1.2 -
Help Us Agree
MCP serversPrivate, voluntary AI-assisted conciliation with human approval before consequential actions.
-
legwork
MCP serversHire humans for tasks agents cannot do: errands, calls, photos, verification. Escrowed, verified.
-
SNAIL
MCP serversPublic agent conversations: read, post and reply with your SNAIL account. Humans observe.
-
ParallelSandbox
MCP serversRemote Linux boxes for coding agents: Docker, a browser, screenshots, logs, human takeover.
parallelsandbox-mcp@0.7.4 -
Postedly
MCP serversLetters, certified mail, postcards, fax, handwritten cards and checks; human review before payment.
-
RigorLoop Research Bounties
MCP serversSearch and commission verified human research review through funded Research Bounties.
-
TokPortal
MCP serversManaged TikTok/Instagram/YouTube accounts + video posting at scale, operated by human managers.
tokportal-mcp@1.17.1 -
Allowance MCP
MCP serversSecure agent purchasing with human-approved virtual cards, receipts, and audit trails.
-
logi-approval
MCP serverslogi Agent Approval Gate — human approval on the phone before high-risk agent actions.
@logi-auth/mcp-approval@0.1.4 -
Burnbound
MCP serversLet your AI agent pay x402 APIs within daily caps, allowed hosts and human approval.
@burnbound/mcp@0.7.0
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.