Library
85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
-
mcp-jdwp-java
MCP serversMCP server giving AI agents full debugger control over running Java applications — inspect state, set breakpoints, evaluate expressions, and mutate values at runtime via JDWP/JDI
git clone https://github.com/FgForrest/mcp-jdwp-java.git -
AgentCAD
MCP serversThe CAD runtime built for AI agents: 2D drawings (DXF/DWG) and parametric 3D parts (FreeCAD, STEP) through MCP, CLI and Python, with undo, independent validation and a live viewer.
git clone https://github.com/lizaixi01/AgentCAD.git -
boundaryai
MCP serversDeterministic runtime safety for AI agents: scan PII, gate tool actions, verify LLM output.
-
keymaster-mcp
MCP serversRead-only runtime secret retrieval from HashiCorp Vault via Keymaster for autonomous AI agents.
@akari-os/keymaster-mcp@1.0.2 -
AitherOS ADK
MCP serversAgent runtime with typed memory, knowledge and code graphs, plus file and web tools
aither-adk@3.5.0 -
Chrome Debugger MCP
MCP serversChrome breakpoint debugging MCP server for inspecting runtime values and stepping through code
chrome-debugger-mcp@1.0.4 -
mcp-bastion
MCP serversReliability + security proxy for MCP: runtime tool-security and a compliance-mapped audit trail.
mcp-bastion@1.5.0 -
threat-rules
MCP serversGuardBee MCP bridge to Agent Threat Rules (ATR) for runtime agent/MCP threat detection
@guardbee/mcp-threat-rules@0.5.1 -
mcp-seatbelt
MCP serversMCP runtime security proxy. Blocks dangerous AI agent tool calls with a policy engine.
@kryptosai/mcp-seatbelt@0.7.0 -
guardian-mcp
MCP serversRuntime AI-threat screening for coding agents: analyze, scan tool calls/outputs & docs (paid).
ethicore-guardian-mcp@0.1.2 -
wyd
MCP serversLocal runtime provenance for coding agents. Inspect sessions and explain which one owns a process.
wyd@0.10.0 -
PEAC Protocol: Signed interaction receipts
MCP serversPortable signed records for agent, API, MCP, and cross-runtime interactions.
@peac/mcp-server@0.15.0 -
CodeSampleX
MCP serversCompatibility evidence from real builds: does this library API work on your versions and runtime?
https://github.com/r2cuerdame/CodeSampleX/releases/download/v0.2.26/codesamplex-mcp.mcpb@0.2.26 -
CompatLab
MCP serversRead recorded npm loading evidence across pinned Node.js, Bun and Deno runtimes.
-
Magg
MCP serversAggregates and proxies other MCP servers, letting LLMs discover, add, and manage tools at runtime.
magg@1.2.1 -
godot
MCP serversThe most complete Godot 4 MCP: secure sandbox, 40+ tools (projects–runtime), major MCP clients.
godot-mcp-server@1.0.2 -
Metro MCP
MCP serversMCP server for React Native/Expo runtime debugging, inspection, and automation via Metro/CDP
metro-mcp@0.15.0 -
Agent Tavern
MCP serversPublic board where AI agents ask, answer and post findings across runtimes.
-
Vessel Browser
MCP serversAI-native browser runtime for autonomous agents with human-in-the-loop supervision
@quanta-intellect/vessel-browser@0.1.10 -
dominion-observatory
MCP serversRuntime behavioral trust scoring for MCP servers. Check reliability before calling unknown tools.
-
Pi Worker MCP
MCP serversA host-agnostic MCP worker runtime for supervising local Pi coding-agent processes.
@zguiyang/pi-worker-mcp@0.1.1 -
code-factory
MCP serversRead-only audit evidence for security, tests, native coverage, runtime failures and repair status.
factoryline-code-factory@0.49.6 -
Colab-MCP (unofficial)
MCP serversUnofficial MCP server for Google Colab: runtimes, code, long jobs, files and notebooks.
colab-cli-mcp@0.1.0 -
sadasend
MCP serversTransactional email API & AI agent safety runtime with 12 scoped tools and SpendGuard.
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.