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
-
attest-mcp
MCP serversCredential enforcement middleware for MCP servers — verifies scoped tokens on every tool call
@attest-dev/mcp@0.1.0 -
ipybox
MCP serversUnified execution environment for Python code, shell commands, and programmatic MCP tool calls
ipybox@0.9.2 -
JevSim
MCP serversRun verified iOS and Android UI workflows in one agent tool call with Jev.
@huaaudio/jevsim@0.1.0 -
conductor
MCP serversVerified tool calls for Claude Code: verify, retry and fallback over hermetic claude calls.
@fainir/conductor@0.4.1 -
YUSA
MCP serversPrompt-injection firewall for AI agents: scan untrusted text, fence it, gate tool calls.
https://github.com/yusasecurity/yusa/releases/download/v0.3.5/yusa.mcpb -
better-github-skill
SkillsOptimized GitHub skill for coding agents: fewer tool calls, less context burned, lower cost, faster answers. One bounded call each for PR state, review threads, and CI failures.
git clone https://github.com/AVGVSTVS96/better-github-skill.git -
3dstreet
MCP serversDrive an open 3DStreet scene tab from Claude Desktop or Claude Code via MCP tool calls.
3dstreet-mcp@0.2.2 -
Aperion Shield
MCP serversLocal guardrail proxy that blocks destructive MCP tool calls, rug pulls, and tool poisoning
ghcr.io/aperionai/shield:shield-v1.0.1 -
PurRAssist
MCP serversRecovers intent from imperfect AI output: JSON, tool calls, names, paths and Markdown edits.
purrassist-cli@0.1.0 -
OnchainAI
MCP serversCrypto tool MCP: search/trust/install-risk. Remote tools/call is x402 paid.
-
CCS Runtime Evidence
MCP serversAgent tool-call guardrail: fail-closed runtime security verification with Ed25519 evidence receipts.
ccs-mcp-server@1.2.17 -
mcp-seatbelt
MCP serversMCP runtime security proxy. Blocks dangerous AI agent tool calls with a policy engine.
@kryptosai/mcp-seatbelt@0.7.0 -
AgentGuard
MCP serversLocal spend caps, kill-switch blocking and Ed25519-signed receipts for AI agent tool calls.
@agentguard-run/mcp@0.3.1 -
Agent Security Scanner
MCP serversScan AI agents for tool-calling vulnerabilities: prompt leaks, hijacking, injections, and more.
agentvuln@0.4.2 -
guardian-mcp
MCP serversRuntime AI-threat screening for coding agents: analyze, scan tool calls/outputs & docs (paid).
ethicore-guardian-mcp@0.1.2 -
mcpwatch
MCP serversRecords MCP tool calls and itemises the token cost each server adds to your context.
@sreelal727/mcpwatch@0.4.1 -
Aileron Journal
MCP serversRead-only queries over Aileron audit journals: verify integrity, search recorded tool calls
aileron@0.1.6 -
klanex
MCP serversReliable async execution for agent tool calls: schema gating, retries, idempotency, audit trail.
klanex-mcp@0.1.0 -
Clay Seal
MCP serversAuthorizes MCP tool calls against a session policy, not one call at a time.
clayseal@0.6.2 -
cssgraph
MCP serversCSS intelligence for AI coding agents — surgical style context, fewer tool calls. 100% local.
cssgraph@0.6.3 -
prompt-protection
MCP serversScan prompts, tool definitions and model output for injection, and guard agent tool calls.
prompt-protection@4.4.0 -
Palveron MCP Server
MCP serversEarly access - AI governance gateway for MCP tool calls (policies, PII masking, audit).
@palveron/mcp-server@1.0.1 -
verimcp
MCP serversTransparent MCP proxy that independently re-verifies tool-call claims before the Host trusts them.
verimcp@0.2.2 -
agenttrace
MCP serversSummarize a supplied agent tool-call trace: per-tool stats, the error list, and totals.
@reneturcios/agenttrace@0.1.0
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.