InnerVault

Library

85,340 resources from 11 public sources. 54 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. mcpwall

    MCP servers

    iptables for MCP — blocks dangerous tool calls, scans for secrets, logs everything.

    Stale Official MCP Registry, io.github.behrensd Updated 9 months ago 1 note

    mcpwall@0.1.2
  2. mcp

    MCP servers

    MCP auth middleware: gate tool calls so only authorized agents can act.

    Stale Official MCP Registry, io.github.bolyra Updated 4 months ago 1 note

    @bolyra/mcp@0.6.4
  3. signet-eval

    MCP servers

    Deterministic policy enforcement and MCP management for AI agent tool calls.

    Stale Official MCP Registry, io.github.jmcentire Updated 2 months ago

  4. agenticpay

    MCP servers

    x402 USDC paywall bridge for MCP — pay per tool call on Solana.

    Stale Official MCP Registry, io.github.krystiangw Updated 6 months ago 2 notes

    @agenticpay/mcp-bridge@0.0.2
  5. Codex MCP Go

    MCP servers

    MCP server wrapping Codex CLI for stdio-based tool calls.

    Stale Official MCP Registry, io.github.w31r4 Updated 9 months ago 1 note

    @zenfun510/codex-mcp-go@0.2.1
  6. policyrecall

    MCP servers

    Policy-verified recall and calibration for tool calls via signed operational memory.

    Stale Official MCP Registry, io.github.CloudCorpRecords Updated 14 days ago 1 note

    @reneturcios/policyrecall@0.1.0
  7. Forecall Failure KB

    MCP servers

    Known MCP tool-call failures and workarounds verified by reproduction.

    Stale Official MCP Registry, dev.forecall Updated 32 days ago 1 note

  8. agentsnap

    MCP servers

    Snapshot tests for AI tool-call traces: diff, validate, and catch silent regressions.

    Stale Official MCP Registry, io.github.MukundaKatta Updated 6 months ago 1 note

    @mukundakatta/agentsnap-mcp@0.1.0
  9. gatekeeper

    MCP servers

    Run MCP tool calls through Runestone Gatekeeper — policy enforcement, human approval, audit.

    Stale Official MCP Registry, io.github.Runestone-Labs Updated 2 months ago 1 note

    @runestone-labs/gatekeeper-mcp@0.1.2
  10. aimcpgate

    MCP servers

    MCP gateway/proxy: multiplexes tool calls across upstream MCP servers into one catalog.

    Stale Official MCP Registry, io.github.akomyagin Updated 2 months ago 1 note

    ghcr.io/akomyagin/aimcpgate:0.5.0
  11. Pre-execution governance for AI agents. Validates tool calls before they execute.

    Stale Official MCP Registry, io.github.chrbailey Updated 8 months ago 1 note

    @chrbailey/promptspeak-mcp-server@0.4.1
  12. evalsmith-mcp

    MCP servers

    Evaluate RAG retrieval, agent tool calls and prompt regressions with deterministic metrics.

    Stale Official MCP Registry, io.github.diegoperezg7 Updated 19 days ago 2 notes

    evalsmith-mcp@0.1.0
  13. guardian-mcp

    MCP servers

    Routes agent tool calls through Guardian for ALLOW/ASK/DENY before execution.

    Indexed Official MCP Registry, io.github.Odingard Updated 2 days ago 2 notes

    @odingard/guardian-mcp@0.5.0
  14. clawmetry

    Agents & frameworks

    See your agent think. Zero-config observability & governance for 30 AI agent runtimes: Claude Code, OpenAI Codex, Hermes, OpenClaw & 26 more. Live token costs, sessions, tool calls, crons.

    Indexed GitHub, vivekchand 438 ★MITUpdated yesterday

    git clone https://github.com/vivekchand/clawmetry.git
  15. Hands-on tutorials for building AI agents from scratch. Learn LLM APIs, prompt engineering, tool calling, and the agent loop through practical examples.

    Stale GitHub, agenticloops-ai 385 ★MITUpdated 11 days ago

    git clone https://github.com/agenticloops-ai/agentic-ai-engineering.git
  16. norviq

    MCP servers

    Runtime security platform for LLM agent tool calls on Kubernetes

    Indexed GitHub, norviq-dev 27 ★Apache-2.0Updated 2 days ago

    git clone https://github.com/norviq-dev/norviq.git
  17. tokentelemetry

    Agents & frameworks

    Token telemetry dashboard for AI autonomous and coding agents — tracks tokens, sessions, tool calls & reasoning across Hermes agent, Claude Code, Antigravity CLI, Codex & more. 100% local.

    Stale GitHub, VasiHemanth 384 ★MITUpdated 10 days ago

    git clone https://github.com/VasiHemanth/tokentelemetry.git
  18. ghostget

    Skills

    GhostGet gives your AI agent named web actions: read a page, archive one media item, or use a connected account, without credentials or a browser to steer.

    Stale GitHub, hraness 8 ★MITUpdated 28 days ago

    git clone https://github.com/hraness/ghostget.git
  19. JevStation

    MCP servers

    Typed-question decisions from Jev: classify, moderate, route models and guard tool calls.

    Stale Official MCP Registry, com.jevstation Updated 38 days ago 1 note

  20. superagenticmcp

    MCP servers

    MCP-native router and multi-agent control plane: plan, route tool calls, stream execution.

    Stale Official MCP Registry, io.github.ANAMIZED Updated 2 months ago

  21. Composio

    MCP servers

    Connect AI agents to 1000+ apps with managed authentication and tool-calling.

    Stale Official MCP Registry, io.github.ComposioHQ Updated 4 months ago 1 note

  22. ccs

    MCP servers

    Runtime verification MCP server: fail-closed checks for agent tool calls, signed evidence receipts.

    Stale Official MCP Registry, io.github.Correctover Updated 2 months ago 1 note

    ccs-mcp-server@1.2.7
  23. Tripwire

    MCP servers

    Security gateway for MCP agents: blocks prompt-injection-driven tool calls before they execute.

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

    tripwire-mcp@0.3.1
  24. ReasonGate

    MCP servers

    Provenance gateway for stdio MCP servers: blocks tool calls fed by untrusted tool results.

    Stale Official MCP Registry, io.github.cgrtml Updated 54 days ago 1 note

    reasongate@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.