MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
leak-secure-mcpgithub.com/cbuntingde/leak-secure-mcpupdated this year
MCP server for Leak Secure - Enterprise GitHub security scanner detecting 35+ types of secrets
npm MIT -
Zero-dependency credential leak scanner: 86 rules, entropy detection, placeholder triage, baseline diffs for PR gates, SARIF, MCP and a GitHub Action
MIT -
dotnet-dumplinggithub.com/coreykaylor/dotnet-dumplingupdated this year
A delightful CLI tool and stdio MCP server for analyzing .NET memory dumps (.gcdump and process dumps). Provides heap analysis, type statistics, retained size calculations, string duplicate detection, object inspection, memory leak detection, interactive mode, and AI-agent MCP tools.
nuget Apache-2.0 -
Lightweight Go tool and MCP server tool for running network diagnostics through proxies — compare direct vs proxied connections, detect DNS/TLS/IP leaks and expose your proxy as a local proxy in order to use it
go NOASSERTION ★ 1 -
correctover-runtime-guardgithub.com/correctover/runtime-guardupdated this year
Real-time RCE/SSRF/credential leak interception for AI agents — 22µs P50, 99.7% detection rate. MCP Server mode with diagnose_error, fault patterns, repair suggestions.
pypi Apache-2.0 -
Trestlegithub.com/toro-guapo/trestleno update data
Detects leaked secrets (API keys, tokens, private keys) in source code.
npm -
agent-security-mcpgithub.com/mdfifty50-boop/agent-security-mcpupdated this year
MCP server providing security scanning, prompt injection detection, secret leak detection, and agent permission auditing for AI agent workflows
npm -
MCP server detecting leaked secrets/credentials (32+ provider rules). In the official MCP Registry: io.github.eltociear/secrets-audit-mcp. Pure stdlib, zero deps.
oci MIT ★ 1 -
MCP server for remediating hardcoded secrets using GitGuardian’s API. It detects over 600 secret types and prevents credential leaks before code is made public.
pypi MIT ★ 44 -
MCP server for bug bounty recon. Subdomain enum, JS leak hunting, WAF fingerprint, takeover detection, nuclei scan. Free, no API keys, runs locally.
MIT ★ 4 -
A firewall for LLM traffic: detect prompt injection, jailbreaks, and secret/PII leaks. Zero-dependency Python library + CLI + MCP server.
MIT ★ 1 -
Evidence-grade landing page audit via MCP. Detects conversion leaks across 9 signals. Free, no API key.
-
TapQR AgentOS — an autonomous QR growth intelligence platform powered by MCP and Alexa+ that detects customer journey leaks, explains insights, proposes fixes, executes approved actions, and verifies results.
MIT ★ 2 -
ThumbGate Pre-Action Checks self-improve from ranked lessons and repeated failures, hard-block detected secret leaks, and block matches in strict mode.
npm MIT ★ 31 -
Security scanner for MCP (Model Context Protocol) servers. Detect prompt injection, secrets leaks, supply chain attacks, and vulnerabilities in MCP servers. CLI + MCP server mode.
npm MIT ★ 2 -
crosscheck-mcpactive
Multi-LLM MCP server: confer / debate / coordinate / audit / orchestrate across Anthropic + OpenAI + xAI + Gemini + Mistral + Groq + DeepSeek + Kimi + Qwen, with scoreboard-driven router, canary-leak detection, sandboxed shell verifiers, and a tier-aware
npm SEE LICENSE IN LICENSE -
Open-source privacy testing for AI agents. Python SDK, CLI and MCP tools to detect data leaks across tool calls, memory, inter-agent messages and logs, with redacted reports and CI gates.
pypi MIT ★ 11 -
silentwatch-mcpgithub.com/temurkhan13/silentwatch-mcpupdated this year
MCP server for catching cron silent failures in production AI deployments — exit-0-with-empty-output detection, overdue jobs, retry storms, action-budget leaks. Works with system cron, systemd timers, OpenClaw cron logs, and any JSONL run-log.
pypi MIT License -
AI-powered secret scanner for code and git history. Finds leaked API keys, tokens and credentials with near-zero false positives by pairing Rényi entropy detection with LLM adjudication. Runs as a CLI, pre-commit hook, GitHub Action, MCP server or Claude Code hook. Single Go binary, MIT licensed.
go MIT ★ 11 -
MCP server for MemPro enabling AI-assisted bug fixing and memory profiling analysis.
MIT -
MCP server for repeated console errors, slow and failed requests, page performance regressions, broken assets, and approximate heap growth.
npm MIT -
Local MCP security reviewer for AI coding agents — catches NEXT_PUBLIC_ secret leaks, missing RLS, unauth server actions, and verbose error leaks
npm MIT -
MCP server for TextWatermarking.com: embed, extract and verify invisible Unicode watermarks in text. Runs over stdio (npx) or as a remote Streamable HTTP server.
npm MIT -
Zero-dependency environment security auditor, secret leak detector, and .env.example generator. CLI, MCP server, and GitHub Action.
Apache-2.0 -
MCP server: scan text for leaked credentials before an agent commits it. Local-only, dependency-free.
mcpb MIT -
opzyai-mcpgithub.com/thfothijn/opzyai-mcpupdated this year
Local-first security check MCP server for AI coding agents — hardcoded secrets, .env exposure, git-history leaks, dependency CVEs. Runs entirely on your machine.
MIT -
Find what your AI coding agent left behind: hallucinated packages, leaked keys, truncated code, mocked stubs. Zero dependencies. npx aftertaste
MIT -
panhoundgithub.com/cognis-digital/panhoundupdated this year
Scans code, logs, fixtures, and S3 buckets for leaked PANs (Luhn-validated card numbers) and CVVs before they hit prod.
NOASSERTION -
halugardgithub.com/ppp727276/halugardupdated this year
Anti-hallucination MCP server for AI agents. 4-gate dual-stage pipeline. Go binary. Blocks fabricated claims, identity drift, credential leaks, dangerous commands.
MIT -
Find what your AI-built app leaks — before you ship. Secrets, copyleft licenses, unlocked routes, missing privacy policies, card handling. MCP server + Claude Code plugin.
MIT -
MCP server that scans a diff/file/snippet for leaked secrets (AWS, GitHub, Slack, Stripe, private keys, JWTs, entropy-gated generic) before an agent commits or shares it. Local-only, redacted output.
MIT -
Precision-first C/C++ static analyzer on Clang LibTooling — catches the null-derefs, leaks and overflows your compiler waves through, each with a dataflow trace. MCP-ready for the AI coding loop.
Apache-2.0 ★ 2 -
Mask secrets in a project with stable placeholders, encrypt the originals, and restore them byte-for-byte. Guards Claude Code, Codex, Gemini CLI, Cursor and Copilot, and blocks git commits that leak secrets. Powered by gitleaks.
MIT ★ 3 -
MCP server that redacts secrets and PII from files before an AI coding agent (Claude Code, Cursor, Codex) ever reads them into its context — closing the agent-reads-file leak surface that chat-box privacy tools don't cover.
npm SEE LICENSE IN LICENSE -
Plumber as an MCP server — let your AI coding agent scan repos and GitHub Actions workflows for leaked secrets, dead code, and AI slop, with fixes in plain English. Add your own checks with custom rule packs.
npm MIT -
Find the security holes your AI left behind. Zero-config scanner for apps built with Cursor, Claude Code, Lovable & Copilot: leaked keys, open Supabase/Firebase data, missing auth, SQL injection and more. Every finding comes with a fix prompt for your AI editor. CLI + MCP server
MIT ★ 2