InnerVault

Library

85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.

Results

Looks like a goal we have a starting path for: I want to connect AI to my tools

  1. Zero-trust gateway for AI agents: score tool calls, verify agent cards, enforce policy, audit.

    Stale Official MCP Registry, com.axiorank Updated 3 months ago 1 note

  2. {"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"whoami","arguments":{}}} free no key

    Stale Official MCP Registry, dev.workers.pathwren.www Updated 2 months ago 1 note

  3. AI music, video, image, and voice tools callable by agents with USDC payments via x402 on Base.

    Stale Official MCP Registry, io.github.JasonColapietro Updated 5 months ago 1 note

  4. Budget, payment and audit controls for AI agent API calls and MCP tool calls.

    Stale Official MCP Registry, io.github.SatGate-io Updated 49 days ago 3 notes

    satgate-mcp-bridge@1.0.5
  5. conductor-graph-mcp

    MCP servers

    Exposes a CognOS agent system as a machine-readable graph. Full system snapshot with one tool call.

    Stale Official MCP Registry, io.github.base76-research-lab Updated 8 months ago 2 notes

    conductor-graph-mcp@0.1.1
  6. Governed MCP gateway: policy gate on every tool call, hash-chained DSSE receipt on every result.

    Indexed Official MCP Registry, io.github.szl-holdings Updated yesterday 2 notes

    ghcr.io/szl-holdings/hatun-mcp:1.0.4
  7. Deputy

    MCP servers

    Any web page as a typed tool call, run in your own logged-in Chrome. Free to start; Pro adds more.

    Stale Official MCP Registry, io.github.zraisan Updated 13 days ago 1 note

    deputy-mcp@0.1.6
  8. MintPage

    MCP servers

    Publish Markdown or HTML as a live, shareable web page in one tool call. Guest mode needs no key.

    Stale Official MCP Registry, io.github.hlsitechio Updated 27 days ago 1 note

  9. chartremotely-mcp

    MCP servers

    ChartRemotely — put a security on a desktop chart anywhere in the world, by voice or by tool call

    Stale Official MCP Registry, io.github.lonniev Updated 26 days ago 1 note

  10. Stops runaway AI agent loops and token burn. Checks each tool call before it runs. No signup.

    Stale Official MCP Registry, com.audiscape.agentguard Updated 15 days ago 1 note

  11. Authorize AI agent tool calls before they run: policy-as-code, human approval, signed receipts.

    Stale Official MCP Registry, io.github.Realbizdigital Updated 7 days ago 1 note

  12. cc-safety-net

    Agents & frameworks

    A pre-execution guard for AI coding agents. It blocks destructive Git and file system commands, plus common attempts to access sensitive files, before a tool call runs. Supports Amp Code, Antigravity CLI, Claude Code, Codex, Cursor, DeepSeek Harness, Devin CLI, GitHub Copilot CLI, Grok Build, Hermes Agent, Kimi Code, OpenClaw, OpenCode, and Pi.

    Indexed GitHub, kenryu42 2,027 ★MITUpdated 2 days ago

    git clone https://github.com/kenryu42/cc-safety-net.git
  13. sagent

    Agents & frameworks

    A coding-agent CLI and strongly-typed Python library -- self-mutating, hot-swapping, multi-provider, with async tool calls and bidirectional recursive spawn.

    Indexed GitHub, rekursiv-ai 84 ★Apache-2.0Updated yesterday

    git clone https://github.com/rekursiv-ai/sagent.git
  14. Audit AI agents' tool calls, planning and memory; Base on-chain data; pay per call via x402.

    Stale Official MCP Registry, com.a-upgradenet Updated 34 days ago 1 note

  15. SEO Tools

    MCP servers

    5 pay-per-call SEO tools over MCP. Free discovery, tool calls settle in USDC on Base via x402.

    Stale Official MCP Registry, com.timzinin.api Updated 3 months ago 1 note

  16. Agent Trace Check

    MCP servers

    Read a tool-call log from an AI agent run and see which calls failed, looped or were slow.

    Stale Official MCP Registry, app.openkrill Updated 31 days ago 1 note

  17. Puts an MCP tool server behind Archytan Lite: each tool call is authorized and spent before it runs.

    Stale Official MCP Registry, io.github.High-ArchyTech-Solutions Updated 3 days ago 1 note

    https://github.com/High-ArchyTech-Solutions/archytan-mcp-gate/releases/download/v2.8.1/archytan-mcp-gate.mcpb
  18. UETR tracking and SWIFT payment tracking. Tool calls require OAuth or a uetr.ai API key.

    Indexed Official MCP Registry, ai.uetr Updated today 1 note

  19. toolnexus

    Skills

    One agent SDK, hand-ported to 8 languages — JavaScript, Python, Go, Java, C#, Elixir, Clojure, Rust — every port held to the same spec by a CI-enforced cross-port conformance suite, all eight at full tier. MCP · skills · native · HTTP · built-in · A2A tools behind one interface. Docs: https://muthuishere.github.io/toolnexus/

    Stale GitHub, muthuishere 6 ★MITUpdated 4 days ago

    git clone https://github.com/muthuishere/toolnexus.git
  20. {"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"whoami","arguments":{}}} free no key

    Stale Official MCP Registry, dev.workers.pathwren.www Updated 2 months ago 1 note

  21. Hash-chained HMAC-signed audit log MCP for A2A (agent-to-agent) calls. Every tool-call, agent-ha...

    Stale Official MCP Registry, io.github.CSOAI-ORG Updated 48 days ago 3 notes

    agent-audit-logger-mcp@1.1.10
  22. Pay-per-call GLM 5.3 MCP tool via x402 on Base. Reasoning, tool-calls, OpenAI-compatible.

    Stale Official MCP Registry, net.ts.tail45da3a.cursor Updated 2 months ago 1 note

  23. Hands-on, framework-free Colab notebooks for the AI Engineer / Forward Deployed Engineer (FDE) skill set — model APIs, structured output, tool calling, RAG, evals-as-the-spine, agents (loop from scratch, tool design, guardrails, MCP, Skills), fine-tuning vs LoRA, prompt-injection/security, LLMOps, and customer craft. Runs on the free Groq API.

    Stale GitHub, calmrocks 743 ★MITUpdated 9 days ago

    git clone https://github.com/calmrocks/ai-engineer-notebooks.git
  24. {"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"whoami","arguments":{}}} free no key

    Stale Official MCP Registry, dev.workers.pathwren.www Updated 2 months ago 1 note

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.