Popular MCP Servers

Aziel Runtime is a node-meshed MCP software orchestration suite for digital forensics, auditing, provenance, research, intelligence-support, and secure agent workflows, with a single gated execution path, compartmentalized engines, verifiable receipts, temporal integrity, and explicit capability refusal. It is not merely an API aggregator or generic tool router.

Self-hosted MCP gateway that registers upstream MCP servers and fronts them behind one governed Streamable HTTP endpoint: per-tool access control by caller API key, guardrails over tool arguments and results, rate limits, and usage logs. The same Rust gateway also proxies LLM and A2A agent traffic.

Answer CTRLRun approvals from your assistant: list the agent actions waiting on a human, inspect one action's full history, and approve, deny or resolve it, plus read receipts, effects and stats. Reads answer without a credential; the three write tools refuse without one that names a person.

Policy proxy that governs what AI assistants can reach and do: it refuses forbidden tool calls before the upstream is contacted, with per-user memory and a tamper-evident audit. Stops prompt-injection exfiltration and forbidden data combinations across connectors.

Enforces authorize-before-execute for any MCP-compatible AI agent. Exposes atlasent_evaluate and atlasent_verify_permit tools so a protected tool call only runs after AtlaSent issues and verifies a signed, single-use permit — fail-closed on any error, timeout, or malformed response.

Self-hostable MCP server for WhisperGraph — a graph of 7.39B nodes / 39B edges mapping DNS, BGP, GeoIP, WHOIS, and threat intelligence. Six read-only tools (Cypher query + schema introspection + threat assessment), six resources, eight investigation prompts. stdio and Streamable HTTP transports.

Detect and redact PII, PHI, PCI and secrets — SSNs, credit cards, passports, API keys and cloud credentials — in text and in local files, using the Strac DLP API. Five tools: redact_text, detect_sensitive_data, detect_file, redact_file and detokenize.

Allows developers to query security findings (SAST issues, secrets, patches) using natural language within AI-assisted tools like Claude Desktop, Cursor, and other MCP-compatible environments.

MCP server for Verigent's AI agent verification, enabling agents to verify themselves, check other agents' status, and browse the leaderboard.

Enables AI agents to verify trust scores, search certified capabilities, compare side-by-side, and submit experience reports through Fidensa's certification authority.

Trust Graduation gate for AI agents: visible approval ceremonies and receipt-backed boundaries for consequential actions.

Enables AI assistants to securely manage Bitwarden vault items, folders, attachments, and organization administration through the Model Context Protocol.

Connects MCP-compatible AI agents to the AGLedger API for change control, recording every change with signed, hash-chained records. Provides API pass-through tools and an offline audit verifier.

Enables AI assistants to create and manage Hellō applications with full developer context, supporting app creation, updates, secret generation, and logo management through a single unified tool.

Official reference MCP server for A202, the Verifiable Agreement Protocol for Agent-Led Commerce. Gives an agent the seven capabilities two organisations need to buy and sell directly: issue a mandate, check what an agent may do under it, approve an act needing a person, form an agreement, exchange obligations, verify a record by replay, and read the transaction record back.

Exposes PatrowlIntel vulnerability intelligence (CVEs, EPSS, CISA KEV, public exploits, trending attacks) via MCP tools like search_cves, get_cve, and list_trending_attacks.

Enables AI assistants to manage DNS filtering accounts by blocking or allowing domains, checking policies, reviewing blocked queries, and managing filter categories, schedules, and devices through natural language.

Scan any project or website for privacy compliance issues directly in your AI coding tool. Detects tracking tech, cookies, and third-party data collection. Works in Claude Code, Cursor, and Windsurf.

Verify sealed voice recordings (WAV) from any AI assistant: verdict (verified, unsealed, warning, alert) and the seconds that changed after sealing. Verify-only, no secrets.

Enables AI assistants to read and search a bilingual CORF register, follow ISO 27001, PCI DSS and SWIFT CSCF crosswalks in any direction, and score exported assessments.