"Understanding Perplexity in Relation to Claude" matching MCP servers:

A zero-dependency Node.js playground for debugging how MCP clients authenticate to an MCP server over HTTP.

Encrypted token store for Claude Code sessions, providing MCP tools for secure secret management with macOS Keychain integration, per-project allowlists, and native dialog input.

Enables Claude to run safe, read-only diagnostics against servers and websites — certificate chains and expiry, HTTP status/redirects/security headers, DNS records, email authentication (SPF, DKIM, DMARC, MTA-STS, TLS-RPT) and sitemaps. Every check returns severity-tagged findings with concrete fixes, plus a 0-100 score and A-F grade, without any ability to modify the target.

An MCP server that sends plain-text Gmail messages only to a predefined allowlist, using generated recipient IDs instead of email addresses to enforce security.

Enables authorized web/API security analysis as a stateful, multi-stage workflow with persistent session state, human-controlled validation, candidate versus confirmed finding tracking, and stop conditions.

Provides an OAuth 2.1 authorization and login layer plus tool registration for MCP connectors, so a connector can be added to Claude clients with only a URL and password. It also shapes tool names, descriptions and input schemas for what Claude clients actually display, returning compact results and readable error messages.

A secure MCP server that allows Claude to read and write local files on your machine with explicit approval gating for each access.

Enables a sandboxed Claude Code session to see editor selections, review proposed edits as VS Code diffs, and read workspace diagnostics through an MCP-over-WebSocket IDE bridge.

Enables auditing public GitHub repositories over MCP Streamable HTTP, including classifying URLs, cloning repositories, scanning manifests, CI workflows, and credential signals, and producing findings, file trees, summaries, and PDF reports.

Enforces Awaken Church's governance policies by scanning content, correcting language, blocking unauthorized integrations, routing projects, and flagging content for review.

Blocks AI coding assistants from installing non-existent packages and accessing non-existent files.

Deterministic pre-execution safety certification for autonomous AI agents. Evaluates proposed actions across scope, reversibility, and sensitivity constraints — returns Certified, Warning, Escalate, or Blocked decisions with cryptographic audit trails. 3 tools: certify_action, check_budget, get_certification_history. Built on the QAE Safety Kernel (Rust + PyO3 bindings, pip install qae-safety).

Authentik MCP provides seamless integration with Authentik's API, supporting both full-featured and diagnostic modes. These enable secure, automated user, group, and system management through MCP-compatible tools.

Enables autonomous agents and MCP-compatible clients to enforce policy-approved actions using risk tiers, reversible checkpoints, and token approval bounds.

Automatically approves or blocks specified MCP tool calls in Claude Desktop by injecting JavaScript that restores granular per-chat approval control. Provides configurable permanent approvals while maintaining security through per-server tool whitelists and blacklists.

Enables an MCP server with OAuth authentication, protecting tools like user CRUD operations behind session tokens obtained through a browser-based authentication flow.

An MCP authorization server implementing OAuth2/OIDC flows, supporting dynamic client registration, PKCE, consent screens, and client ID metadata documents for MCP authorization.

Diagnoses a domain's email authentication — SPF, DMARC, DKIM, MX, blacklists and domain or SSL expiry - and returns copy-paste fix records generated by a validating engine, never a language model. The MCP server is hosted remotely; this repository carries the plugin manifest, connector config and bundled skill.

Enables Claude Code to work with personal data that stays on the local machine, running SQL, Python, and file/schema inspection in a sandboxed compute-to-data setup that returns only aggregates, schemas, synthetic fixtures, and pseudonymized results. Raw records, file names, and protected values never reach the Anthropic API, so Auto mode can stay hands-off.

Enables Claude to fetch live package versions across npm, PyPI, crates.io, and Go modules, flag deprecations and known vulnerabilities, and audit dependency manifests with minimum safe upgrade versions.

Enables Claude to answer business questions from a SQL database safely, using read-only queries and bounded summaries, while requiring confirmation and audit logging for order-status changes.

Enables Claude to query and manage Pennylane accounting data in French through 87 MCP tools, covering invoices, quotes, ledgers, customers, suppliers, journals, and FEC exports with read and write operations. It also supports local stdio use and OAuth-secured HTTP deployment for Claude web and mobile.

Single MCP server providing over 500 developer tools for Claude Code, covering security, testing, documentation, and more.

Connects Claude Code to MetaTrader 5 accounts over MCP, letting users read accounts, positions, orders, deals and quotes and place or manage trades, with OAuth sign-in and per-account trading permissions.

Free SSL/TLS scanning and Let's Encrypt certificate issuance (private key stays local), plus certificate-expiry monitoring via one MCP server. Public scan and cert tools need no account.

Provides Claude Desktop access to Defense.com threat intelligence data for risk assessment, threat analysis, and workload management. It also features interactive security training tools and supports over 200 source type aliases for simplified querying.

MCP server for ai-scanner that enables AI agents to scan codebases for LLM usage, AI frameworks, and exposed secrets.

Connects a Discord bot to Claude Code, forwarding incoming Discord messages to the assistant and exposing tools to reply, react, edit messages, fetch channel history, and download attachments. Adds multi-user access control with per-sender roles, an owner flag, request-bound tool permissions enforced by a PreToolUse hook, and per-role policies, limits, and audit logging.

Enables Claude Code sessions to be driven from WhatsApp, with bidirectional messaging, media and voice-note transcription, per-group personalities, and tool-permission approval via emoji reactions. Access is gated by pairing codes and allowlists, and it runs as a plain stdio MCP server using either a linked-device pairing or the official Cloud API.

Enables Claude to list Iceberg tables and run read-only DuckDB SQL queries, including time travel by snapshot, with per-caller token authentication and audit logging.