"Writing about MCP" matching MCP servers:

Scans code strings for hardcoded secrets (AWS keys, tokens, private keys, etc.) and returns redacted findings, helping AI coding agents catch secrets before writing or committing code.

A robust Model Control Protocol server that enables AI agents to access real-time cyber threat intelligence and detailed information about vulnerabilities, threat actors, malware, and other cyber-security entities.

A read-only MCP server for the Qualys PCI Merchant API that lets LLM assistants answer questions about PCI compliance posture, such as which hosts are failing PCI or listing high findings.

Ghost Hands gives agents governed, recorded, replayable hands on the web through a zero-dependency Python CDP stack, classifying every action before it runs and writing it to a provenance trail.

An MCP server that exposes macOS-native device trust signals — the facts about a Mac that cannot be gathered from a Linux container or a cloud runner. All tools are strictly read-only.

MCP server that enables Claude Code to drive the Konsulto cybersecurity audit platform from the CLI, including reading and writing findings, managing evidence, and handling scope and assets.

Enables AI agents to verify email addresses, clean lists, run bulk verification jobs, and manage a Verifly account through natural language, without writing HTTP calls.

Exposes Microsoft 365 privacy/compliance audit checks as MCP tools, enabling natural language queries about tenant configuration, orphaned documents, Conditional Access policies, DLP policies, and Copilot usage.

Enables natural-language queries about Azure resource compliance, including VM compliance, patch status, orphaned RBAC, and infrastructure health, through read-only MCP tools.

Provides access to Shodan API functionality, enabling AI assistants to query information about internet-connected devices for cybersecurity research and threat intelligence.

Provides access to a malicious URL database API, enabling users to search, list, and retrieve information about potentially dangerous URLs for security analysis and threat detection.

Enables AI clients to ask questions about a codebase and receive ranked, citation-backed findings from a scanned project graph, with tools for search, explanation, verification, route listing, drift checks, and security findings.

Enables transparent security for any MCP server by intercepting tool calls, blocking prompt injection attempts, masking PII in responses, and writing immutable audit logs.

The official MCP Server for Cylera. Brings context about device inventory, threats, risks and utilization powered by the Cylera Partner API into an LLM.

Enables AI assistants to search and retrieve information from the REMnux malware analysis toolkit documentation, allowing users to ask questions about reverse-engineering tools and get accurate, up-to-date answers from the live documentation.

Provides a local MCP inspection workspace for testing permission-gated note reading and writing, showing rules, request payloads, execution status, and before/after SHA-256 hashes so developers can verify whether denied writes actually left files unchanged.

Enables clients to select administrator-registered machines and projects, work in isolated Git-versioned sandboxes, inspect diffs, and generate policy-gated publish plans without writing changes back to source.

Enables AI agents to browse email-security incidents and their details, look up what the platform knows about a sender, read mitigation statistics and allow-list entries, and, on explicit request, classify incidents and add or remove allow-list entries through the Management API.

A local policy wrapper for Supabase MCP that secures access tokens and enforces strict execution models, including project allowlists and write-access restrictions. It provides a safety layer to prevent AI agents from accidentally executing migrations or writing SQL against production environments.

Enables read-only verification of SR Linux and FRR network-device command output without device credentials, turning raw text into structured verdicts about interfaces, routes, BGP peers, and overall health. It also sanitizes that untrusted output by masking secrets and neutralizing prompt injection before a model reads it.

Enables secure filesystem access with privacy controls using .mcpignore files to block MCP clients from reading or writing sensitive files and directories while allowing directory browsing and search.

Connects your Bradescard account to AI assistants via Open Finance Brasil, enabling natural language queries about balances, statements, credit card bills, and investments in read-only mode.

Enables fully offline, token-free screening of text through a local Laya typed-decision model, exposing prompt-injection/jailbreak detection plus structured choice, score, and yes/no judgments in about 55ms per call. It also reports service status with measured metrics and known limitations.

MCP server for reading C2PA content provenance manifests from media files, enabling natural language queries about AI-generated content, signatures, and provenance.

Gives AI agents governed context about a data warehouse — table meaning, ownership, lineage, freshness, and PII flags — plus read-only, row-limited, PII-protected querying across DuckDB, Snowflake, and Databricks. Guardrails enforced at parsing, connection, and result layers keep agents from writing, running away, or leaking personal data.

Enables Active Directory administration over LDAPS, including reading and writing users, computers, and groups with a dry-run-first safety guard.

Provides Claude with access to Shodan for IP address lookups, service discovery, and vulnerability scanning, allowing users to query information about hosts, count results, and check API usage.

Enables AI agents to enroll and verify voice samples against known identities, providing honest confidence signals about voice authenticity.

Provides read-only access to a DEGIRO brokerage account, letting an MCP client answer questions about holdings with live or delayed prices, cash balances, executed trades, cash movements, orders and dividends. All requests are restricted to safe GET calls, so credentials stay local and no trading actions can be performed.

A Model Context Protocol server that enables AI assistants to search and retrieve information about security exploits and vulnerabilities from the Exploit Database, enhancing cybersecurity research capabilities.

Enables a machine to expose its registered folders and locally added tools to remote callers over MCP, deciding each request against local policy with default-deny access, per-person tool grants, pre-approval for anything not marked read-only, and an on-machine audit log. Also runs a folder file server offering directory listing, text reading, and text writing where permitted.

Enables Claude to connect to a household's ICA account through BankID and access shopping lists, offers, bonus, stores, product lookup, catalogue search, purchase history, and Handla online prices. It also provides OAuth-based MCP connection, admin controls, audit logging, and optional list-writing tools.

Enables an agent to evaluate a target MCP server and verify attestations about it from inside the editor, using read-only, allowlisted tools that never send credentials.

Enables interaction with HashiCorp Vault for secret management operations including reading, writing, listing, and deleting secrets through the Model Context Protocol.

Enables read-only static posture audits of Tor Browser and Firefox configurations and residue, including layer-mismatch assessment, without launching or modifying the applications or writing files.

Enables asking management questions about a Citrix NetScaler — what expires, what breaks when it does, what to do about it, and what could not be established — with evidence attached and answers computed by code for reproducibility. Also supports a human-in-the-loop, two-step confirmation flow for seven guarded write actions such as staging or replacing certificates and disabling service-group members.

Enables querying threat intelligence data about files, URLs, IPs, and domains from multiple abuse.ch platforms (MalwareBazaar, URLhaus, and ThreatFox) through a unified API. Provides comprehensive security reports and threat analysis data for cybersecurity investigations.

Enables AI agents to resolve stored API tokens and credentials from a locally encrypted vault through an inject_secret tool, writing them to env-file handles the agent consumes outside the conversation so secret values never appear in chat transcripts. Provides listing and metadata access while requiring a human unlock gate before any decryption.

Provides AI agents with context for integrating Arcjet security features like bot detection and rate limiting into applications. It enables users to retrieve information about processed requests, teams, and sites through the Model Context Protocol.

Enables controlled local Windows file inspection, reading, writing, reversible deletion, restoration, and auditing across user-selected folder roots. Commits occur only after separate owner approval in a native desktop dialog, while the tool cannot bypass OS security controls.