Library
88,764 resources from 11 public sources. 54 checked by hand. The rest are indexed automatically and not reviewed.
Results
-
peon-mem
MCP serversLocal-first memory brain for AI coding agents: hooks capture sessions, beliefs injected per prompt.
Source for peon-mem (opens github.com) peon-mem@1.0.9 -
agentforge
MCP serversSafety checks for AI agents: preflight before signing, prompt-injection scan, sanctions, rug checks.
-
CanaryGuard 402
MCP serversDeterministic prompt-injection detection & sanitization for AI agents via x402 on Base.
-
cartography
MCP serversMCP-first read-only discovery of your infra & SaaS landscape as MCP resources, tools and prompts.
Source for cartography (opens github.com) @datasynx/agentic-ai-cartography@2.12.1 -
EdgarTools
MCP serversOpen-source SEC EDGAR toolkit — 13 tools, 7 prompts, every filing type. No API key required.
Source for EdgarTools (opens github.com) edgartools@6.3.0 -
Slimlytics
MCP serversPrivacy-first cookieless web analytics with agent one-prompt setup via remote MCP OAuth.
-
OpenClaw Agent Instruction Registry
MCP serversSearch and retrieve agent instruction files: system prompts, skills, workflows, and safety filters.
Source for OpenClaw Agent Instruction Registry (opens github.com) agentbase-mcp@1.0.1 -
Oh My Posh Configurator
MCP serversMCP server for creating, validating, and exporting Oh My Posh terminal prompt configurations.
Source for Oh My Posh Configurator (opens github.com) ohmyposh-configurator@1.1.1 -
Tiny Go MCP Server
MCP serversDemo stdio MCP server (tools, resource, prompt) for tinymcp tests—not production use.
Source for Tiny Go MCP Server (opens github.com) ghcr.io/kioie/tiny-go-mcp:1.1.2 -
ShareGrokBots
MCP serversSearch shared Grok Bots by what they do. Credit the creator. No prompt text.
-
LetDraw
MCP serversCreate, edit, share and export hand-drawn LetDraw diagrams, from code or a prompt.
Source for LetDraw (opens github.com) @letdraw/mcp@0.1.2 -
heu-mcp
MCP serversHEU Legal e-signature MCP: manage HEU documents and PDFs, prompt signers, download PDFs.
Source for heu-mcp (opens github.com) heu-mcp@0.1.2 -
Advanced Zebrunner MCP Server
MCP serversZebrunner analytics, reporting and safe mutations: 79 adv_* tools, 15 resources, 22 prompts.
Source for Advanced Zebrunner MCP Server (opens github.com) mcp-zebrunner@9.4.5 -
MCP Fortress
MCP serversSecurity scanner for MCP servers. Detect vulnerabilities, prompt injection, and tool poisoning.
-
Varyntiq
MCP serversPre-payment checks for AI agents: x402 quotes, untrusted prompts and audit receipts.
-
Hive Vault
MCP serversOn-demand Obsidian vault access for AI coding assistants — 17 tools, 5 resources, 4 prompts.
Source for Hive Vault (opens github.com) hive-vault@1.12.2 -
aria-mcp-server
MCP serversSearch 35M+ PubMed, 400K+ ClinicalTrials.gov & ISRCTN trials. Prompts included. No API key.
Source for aria-mcp-server (opens github.com) aria-mcp-server@0.2.2 -
tech-risk
MCP serversMCP security scanner: tool-poisoning & prompt-injection audit (OWASP LLM01/LLM08), x402-payable
Source for tech-risk (opens github.com) greyridge-x402-tools@0.8.3 -
agent-security-scanner-mcp
MCP serversSecurity layer for AI agents: blocks prompt injection, detects fake packages, scans vulnerabilities.
Source for agent-security-scanner-mcp (opens github.com) agent-security-scanner-mcp@2.0.1 -
mcp-server-security-scanner
MCP serversScan MCP configs for 30+ CVEs, prompt injection, tool poisoning; validate OAuth configs
Source for mcp-server-security-scanner (opens aivp-mcp.vercel.app) mcp-server-security-scanner@1.1.4 -
Agent Safe
MCP serversEmail safety MCP server. Detects phishing, prompt injection, CEO fraud for AI agents.
-
Patronus Security
MCP serversScan text, documents, websites, and MCP metadata for prompt injection and sensitive-data risks.
-
veida-mcp
MCP serversGenerate AI images from a prompt with no API key, using Veida's anonymous free tier.
Source for veida-mcp (opens github.com) veida-mcp@0.1.0 -
GrowthVector
MCP serversFree SEO, GEO, ads, and email marketing knowledge base: search guides, pages, glossary, and prompts.
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.