InnerVault

Library

85,762 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. conductor

    MCP servers

    Verified tool calls for Claude Code: verify, retry and fallback over hermetic claude calls.

    Stale Official MCP Registry, io.github.fainir Updated 18 days ago 1 note

    @fainir/conductor@0.4.1
  2. YUSA

    MCP servers

    Prompt-injection firewall for AI agents: scan untrusted text, fence it, gate tool calls.

    Stale Official MCP Registry, io.github.yusasecurity Updated 2 days ago 1 note

    https://github.com/yusasecurity/yusa/releases/download/v0.3.5/yusa.mcpb
  3. 3dstreet

    MCP servers

    Drive an open 3DStreet scene tab from Claude Desktop or Claude Code via MCP tool calls.

    Stale Official MCP Registry, app.3dstreet Updated 6 months ago 1 note

    3dstreet-mcp@0.2.2
  4. Aperion Shield

    MCP servers

    Local guardrail proxy that blocks destructive MCP tool calls, rug pulls, and tool poisoning

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

    ghcr.io/aperionai/shield:shield-v1.0.1
  5. PurRAssist

    MCP servers

    Recovers intent from imperfect AI output: JSON, tool calls, names, paths and Markdown edits.

    Stale Official MCP Registry, io.github.Blackcat-Informatics Updated 34 days ago 1 note

    purrassist-cli@0.1.0
  6. OnchainAI

    MCP servers

    Crypto tool MCP: search/trust/install-risk. Remote tools/call is x402 paid.

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

  7. CCS Runtime Evidence

    MCP servers

    Agent tool-call guardrail: fail-closed runtime security verification with Ed25519 evidence receipts.

    Stale Official MCP Registry, io.github.DSHCorrectover Updated 42 days ago 2 notes

    ccs-mcp-server@1.2.17
  8. mcp-seatbelt

    MCP servers

    MCP runtime security proxy. Blocks dangerous AI agent tool calls with a policy engine.

    Stale Official MCP Registry, io.github.KryptosAI Updated 3 months ago 1 note

    @kryptosai/mcp-seatbelt@0.7.0
  9. AgentGuard

    MCP servers

    Local spend caps, kill-switch blocking and Ed25519-signed receipts for AI agent tool calls.

    Stale Official MCP Registry, io.github.MerchantGuard Updated 56 days ago 2 notes

    @agentguard-run/mcp@0.3.1
  10. Scan AI agents for tool-calling vulnerabilities: prompt leaks, hijacking, injections, and more.

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

    agentvuln@0.4.2
  11. guardian-mcp

    MCP servers

    Runtime AI-threat screening for coding agents: analyze, scan tool calls/outputs & docs (paid).

    Stale Official MCP Registry, io.github.OraclesTech Updated 48 days ago 2 notes

    ethicore-guardian-mcp@0.1.2
  12. mcpwatch

    MCP servers

    Records MCP tool calls and itemises the token cost each server adds to your context.

    Stale Official MCP Registry, io.github.Sreelal727 Updated 2 months ago 1 note

    @sreelal727/mcpwatch@0.4.1
  13. Aileron Journal

    MCP servers

    Read-only queries over Aileron audit journals: verify integrity, search recorded tool calls

    Stale Official MCP Registry, io.github.aileron-sh Updated 28 days ago 1 note

    aileron@0.1.6
  14. klanex

    MCP servers

    Reliable async execution for agent tool calls: schema gating, retries, idempotency, audit trail.

    Stale Official MCP Registry, io.github.chrassy Updated 3 months ago 3 notes

    klanex-mcp@0.1.0
  15. Clay Seal

    MCP servers

    Authorizes MCP tool calls against a session policy, not one call at a time.

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

    clayseal@0.6.2
  16. cssgraph

    MCP servers

    CSS intelligence for AI coding agents — surgical style context, fewer tool calls. 100% local.

    Stale Official MCP Registry, io.github.mack-peng Updated 2 months ago 1 note

    cssgraph@0.6.3
  17. prompt-protection

    MCP servers

    Scan prompts, tool definitions and model output for injection, and guard agent tool calls.

    Stale Official MCP Registry, io.github.mughalhere Updated 11 days ago 1 note

    prompt-protection@4.4.0
  18. Palveron MCP Server

    MCP servers

    Early access - AI governance gateway for MCP tool calls (policies, PII masking, audit).

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

    @palveron/mcp-server@1.0.1
  19. verimcp

    MCP servers

    Transparent MCP proxy that independently re-verifies tool-call claims before the Host trusts them.

    Stale Official MCP Registry, io.github.rudranaresh0201 Updated 3 months ago 1 note

    verimcp@0.2.2
  20. agenttrace

    MCP servers

    Summarize a supplied agent tool-call trace: per-tool stats, the error list, and totals.

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

    @reneturcios/agenttrace@0.1.0
  21. cordum

    MCP servers

    The action firewall for AI agents. Enforce policy and human approval before risky tool calls, shell commands, workflows, and production changes, with auditable evidence.

    Indexed GitHub, cordum-io 510 ★Custom licence (see repository)Updated today

    git clone https://github.com/cordum-io/cordum.git
  22. gateway

    MCP servers

    MCP gateway with runtime security policy, tool-call-level control, and audit of agent actions.

    Stale Official MCP Registry, ai.sealgate Updated 2 months ago 1 note

  23. mcpulse

    MCP servers

    Analytics for MCP servers. Query your tool calls, first-call success, retries and schema cost.

    Stale Official MCP Registry, com.getmcpulse Updated 2 months ago 1 note

  24. protect-mcp

    MCP servers

    Fail-closed Cedar policy gate + Ed25519 signed receipts for agent tool calls. Denies on any error.

    Stale Official MCP Registry, com.scopeblind Updated 22 days ago 1 note

    protect-mcp@0.32.4

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.