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
-
mcpwall
MCP serversiptables for MCP — blocks dangerous tool calls, scans for secrets, logs everything.
mcpwall@0.1.2 -
mcp
MCP serversMCP auth middleware: gate tool calls so only authorized agents can act.
@bolyra/mcp@0.6.4 -
signet-eval
MCP serversDeterministic policy enforcement and MCP management for AI agent tool calls.
-
agenticpay
MCP serversx402 USDC paywall bridge for MCP — pay per tool call on Solana.
@agenticpay/mcp-bridge@0.0.2 -
Codex MCP Go
MCP serversMCP server wrapping Codex CLI for stdio-based tool calls.
@zenfun510/codex-mcp-go@0.2.1 -
policyrecall
MCP serversPolicy-verified recall and calibration for tool calls via signed operational memory.
@reneturcios/policyrecall@0.1.0 -
Forecall Failure KB
MCP serversKnown MCP tool-call failures and workarounds verified by reproduction.
-
agentsnap
MCP serversSnapshot tests for AI tool-call traces: diff, validate, and catch silent regressions.
@mukundakatta/agentsnap-mcp@0.1.0 -
gatekeeper
MCP serversRun MCP tool calls through Runestone Gatekeeper — policy enforcement, human approval, audit.
@runestone-labs/gatekeeper-mcp@0.1.2 -
aimcpgate
MCP serversMCP gateway/proxy: multiplexes tool calls across upstream MCP servers into one catalog.
ghcr.io/akomyagin/aimcpgate:0.5.0 -
PromptSpeak Governance
MCP serversPre-execution governance for AI agents. Validates tool calls before they execute.
@chrbailey/promptspeak-mcp-server@0.4.1 -
evalsmith-mcp
MCP serversEvaluate RAG retrieval, agent tool calls and prompt regressions with deterministic metrics.
evalsmith-mcp@0.1.0 -
guardian-mcp
MCP serversRoutes agent tool calls through Guardian for ALLOW/ASK/DENY before execution.
@odingard/guardian-mcp@0.5.0 -
clawmetry
Agents & frameworksSee 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.
git clone https://github.com/vivekchand/clawmetry.git -
agentic-ai-engineering
PromptsHands-on tutorials for building AI agents from scratch. Learn LLM APIs, prompt engineering, tool calling, and the agent loop through practical examples.
git clone https://github.com/agenticloops-ai/agentic-ai-engineering.git -
norviq
MCP serversRuntime security platform for LLM agent tool calls on Kubernetes
git clone https://github.com/norviq-dev/norviq.git -
tokentelemetry
Agents & frameworksToken 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.
git clone https://github.com/VasiHemanth/tokentelemetry.git -
ghostget
SkillsGhostGet 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.
git clone https://github.com/hraness/ghostget.git -
JevStation
MCP serversTyped-question decisions from Jev: classify, moderate, route models and guard tool calls.
-
superagenticmcp
MCP serversMCP-native router and multi-agent control plane: plan, route tool calls, stream execution.
-
Composio
MCP serversConnect AI agents to 1000+ apps with managed authentication and tool-calling.
-
ccs
MCP serversRuntime verification MCP server: fail-closed checks for agent tool calls, signed evidence receipts.
ccs-mcp-server@1.2.7 -
Tripwire
MCP serversSecurity gateway for MCP agents: blocks prompt-injection-driven tool calls before they execute.
tripwire-mcp@0.3.1 -
ReasonGate
MCP serversProvenance gateway for stdio MCP servers: blocks tool calls fed by untrusted tool results.
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.