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. Each candidate is checked by a language model from its name, description and topics, and only actual MCP servers are listed (not clients, SDKs, lists or skills). Package descriptions, licences and links are read from each package's own registry (npm, PyPI, crates.io, NuGet, RubyGems; Go and Maven packages are only checked to exist), and packages the registry no longer has are removed. 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.
-
Secure MCP server implementation with comprehensive security controls - input validation, injection prevention, path protection. Features all three MCP primitives (Resources, Tools, Prompts) with safe file operations and Claude Desktop integration ready.
-
Agent-safe, passive-first website security scanner. CLI, SARIF 2.1.0 and MCP — treats scanned pages as untrusted input.
MIT -
BIT Security Review — MCP server for devs + CLI for CI/CD pipelines. Activates 7 specialized agents (SECRETS, AUTH, DATA, INPUT, DEPS, INCIDENTS, AGENTIC) mapped to OWASP A1–A10, OWASP Agentic AI T1–T15, and CWE.
npm MIT -
🔍 Enterprise-grade secure MCP server with 33 specialized search tools for Claude Desktop. Features comprehensive security (9/10 score), input validation, Docker hardening, and automated CI/CD security workflows.
MIT ★ 3 -
Secure Model Context Protocol server for Rootly APIs with AI SRE capabilities, comprehensive error handling, and input validation
pypi Apache-2.0 -
MCP server for AI agent security -- input validation, prompt injection detection, PII redaction, policy enforcement, rate limiting, and audit logging
cargo MIT ★ 1 -
An MCP server and secure input broker: an AI agent can place a credential without ever receiving it, while a trusted human-controlled UI authorizes where it goes.
npm Apache-2.0 ★ 2 -
canva-mcp-servergithub.com/falcoschaefer99-eng/canva-mcp-serverupdated this year
Security-hardened Canva MCP server for Claude Code and AI assistants with auth middleware, XSS protection, CORS hardening, and input validation.
MIT ★ 2 -
Stage 3 — MCP server (FastMCP) exposing a secure record_reservation tool: token auth, input sanitisation, path confinement and file locking. 57 tests including a guarded stdio end-to-end test.
-
umbrielgithub.com/ObscuritySRL/umbrielupdated this year
Drive and inspect a whole Windows machine from Bun — apps, windows, input, screen, OCR, registry, and OS — exposed as a security-gated, profile-based MCP server. Pure TypeScript over bun:ffi, zero native deps.
npm MIT ★ 3 -
Secure, local-first document-to-Markdown conversion. Zero-trust input sanitization, multi-column PDF layout, LaTeX math, PII masking. No cloud dependencies.
MIT ★ 6 -
.NET SQL Agent MCP server featuring raw SQL input, strict AST validation, and an embedded Admin UI. Eliminates LLM hallucinations and security risks across 6 major databases.
nuget Apache-2.0 ★ 11 -
A Perplexity API MCP server that unlocks Perplexity's search-augmented AI capabilities for LLM agents. Features robust error handling, secure input validation, and transparent reasoning with the showThinking parameter.
go Apache-2.0 ★ 26 -
@iflow-mcp/shunsukehayashi-miyabi-mcp-bundlegithub.com/shunsukehayashi/miyabi-mcp-bundleupdated this year
🚀 The Ultimate All-in-One MCP Server - 172 tools for Claude Desktop & AI Agents. Git, GitHub, System Monitoring, Tmux, Logs, Network, Process, File, and more! Enterprise-grade security with input sanitization.
npm MIT -
miyabi-mcp-bundlegithub.com/shunsukehayashi/miyabiupdated this year
🚀 The Ultimate All-in-One MCP Server - 172 tools for Claude Desktop & AI Agents. Git, GitHub, System Monitoring, Tmux, Logs, Network, Process, File, and more! Enterprise-grade security with input sanitization.
npm MIT -
perplexity-mcp-serverstale
A Perplexity API Model Context Protocol (MCP) server that unlocks Perplexity's search-augmented AI capabilities for LLM agents. Features robust error handling, secure input validation, and transparent reasoning with the showThinking parameter. Built with
npm Apache-2.0 -
noodle-perplexity-mcpgithub.com/fahd-noodleseed/perplexity-mcp-serverupdated this year
A Perplexity API Model Context Protocol (MCP) server that unlocks Perplexity's search-augmented AI capabilities for LLM agents. Features robust error handling, secure input validation, transparent reasoning, and multimodal support with file attachments (P
npm Apache-2.0 -
@iflow-mcp/cyanheads_perplexity-mcp-serverupdated this year
A Perplexity API Model Context Protocol (MCP) server that unlocks Perplexity's search-augmented AI capabilities for LLM agents. Features robust error handling, secure input validation, and transparent reasoning with the showThinking parameter. Built with
npm Apache-2.0 -
autonomous-shell-eaze-editor-plugingithub.com/nurujjamanpollob/autonomous-shell-eaze-editor-pluginupdated this year
🐚 An unofficial shell plugin for Eaze Editor that gives AI agents secure, autonomous access to your system's shell — with persistent sessions, async execution, interactive input, token optimization, and configurable safety filters.
MIT -
Anonymous MCP/HTTP: static Python artifact/source/consumer import-layout evidence; PyPI wheel metadata; mathematical IPv4/IPv6 set differences; deterministic probe planning. Offline ledger tools also available. Hosted inputs public/non-secret; not a resolver, compatibility check or routing/security validation.
MIT -
IPGeolocation.io MCP Serverno update data
IPGeolocation.io MCP Server provides 17 tools for IP geolocation, security indicators, abuse contacts, ASN data, time zones, astronomy and user-agent parsing. It runs locally over stdio and requires Node.js 22 or later. Bulk tools accept up to 250 inputs by default. Use get_cached_result to read large responses in full without another API call or additional credits. Read cached pages in the same server process with the same API key before expiry or eviction. Configure your own IPGeolocation.io API key; endpoint and module access depend on your plan. get_my_ip works without a key.
smithery -
the-metis-fca-handbook-ai-harness-mcpno update data
# Metis FCA Handbook AI Harness — MCP Server An MCP (Model Context Protocol) server that integrates the Metis FCA Handbook AI Harness into Claude Desktop and other MCP-compatible agents. **Tool name:** `evaluate_fca_handbook_applicability` Use this tool to analyze FCA Handbook applicability for a product, service, or firm. Returns structured compliance reasoning with verbatim handbook citations. ## Why choose The Metis FCA Handbook AI Harness? - **Efficiency** Multiplies effectiveness of compliance advice. Saves £80+ in token fees per Harness run. - **Deals with "Hard Problem"**, in which LLMs' token incentives prioritise training data so results are unreliable. - **Verbatim citations** Quotes verbatim entries from the FCA Handbook. Other AI systems struggle to do this. - **Matches real-world need** You do not have to start off knowing which sections you are looking for. Carries out structured searches across all 10,000+ FCA Handbook entries. - **Secure Design** Harness compartmentalisation, one-shot structure, and statelessness fits natively with emerging AI agent security standards such as OWASP Top 10 for Agentic Applications 2026. - **AI Accessible** Integrates easily with AI workflows and agents. Your LLM can use it as a tool. ## Design Principles The Harness is built on proven principles: - **Stateless** — Each request is independent; no session coupling - **One-shot** — Complete analysis in a single call; no multi-turn state - **Clear contract** — Explicit input/output schemas for easy integration - **Hosted** — Single canonical source; no version drift or stale data ## Use Cases ### Compliance AI Platforms Embed FCA reasoning as a service within your compliance platform. Users ask natural-language questions; your platform calls the Harness and presents structured reasoning. ### AI Agent Workflows Agents building compliance workflows can include FCA Handbook reasoning as a composed tool—no external API calls, just MCP configuration. ### Compliance Review Automation Integrate into document review or due-diligence pipelines. Automatically screen new rules against FCA applicability. ## For Regulatory Screening FS firms screening MCP servers will find: - **Simple model:** Stateless, no hidden state, no background jobs - **Clear contract:** Explicit input schema, output schema, error modes - **Transparent updates:** Version pinning; no automatic upgrades - **Single point of failure:** If the Harness is down, it is obvious; no cascading config issues - **Audit-friendly:** All calls logged centrally, not distributed
smithery -
hermes-shieldgithub.com/amurlaniakea/hermes-shieldupdated this year
Input sanitizer for AI agents — anti-prompt-injection shield
AGPL-3.0 ★ 1 -
Educational reference AI agent and MCP server with an input guard, tool authorizer, output filter and audit logging, each control traced to OWASP, NIST or CSA guidance.
MIT -
MCP wrapper for Burp Suite that builds complete, well-formed HTTP requests from structured input + ingests dedup/JS exports for token-thrifty AI-assisted pentesting. Bundles a fixed Burp extension.
MIT ★ 7 -
Maps an Al agent's MCP tools as a graph, finds routes from untrusted input to public output, and computes the minimum set of permissions to revoke. Runs locally on FalkorDB.
Apache-2.0 -
Aran — the lightweight, open-source developer framework for local IDE telemetry and local input/output guardrails: blocks destructive tool calls and redacts prompt-injection payloads before they reach your agent or your machine.
pypi MIT -
Open source input firewall for AI agents, beta. A local scanner checks text, code, PDFs, images, QR codes, audio and video with 1,565 patterns across 117 categories and reports findings and incomplete scans. A Claude Code hook blocks secret material in tool calls and the paths and hosts your policy lists before tools run.
pypi MIT ★ 11 -
Analyze binaries with a sandboxed MCP tool that unifies reverse engineering utilities and adds filesystem isolation, timeouts, and input checks
★ 3 -
A read-only DuckDB MCP server that treats the rows it returns as untrusted input. Measuring the false positives on real database text is the next slice.
-
An agent-native database. Sessions are branches an agent can fork, merge, and rewind; every write records what it was derived from; and taint-and-recall tells you exactly what a poisoned input contaminated. Built on substrate.
Apache-2.0 ★ 1 -
Hardened Windows Sandbox automation for AI agents: 34 MCP tools — UIA-first input engine that beats consent walls, in-place guest reboot (state persists), CDP browser control, orphan janitor. Evolved fork of shanselman/sandbox-mcp (MIT).
MIT -
Windows computer-use MCP server (26 tools) with a human-in-the-loop approval gate: physical-input-only dialogs, signed guard switches, deny/launch lists, hash-chained audit log. 70+ unit tests, green CI.
MIT ★ 5