"How to create an MCP tool" matching MCP servers:

Governed MCP server for bank-grade agent tool access with RBAC, PII redaction, rate limiting, and audit logging.

An MCP server that reads a file's embedded C2PA Content Credential to report whether it declares AI generation or a real-world capture, and checks whether that declaration's signature still verifies against the file's current bytes.

An MCP server that lets LLM agents operate the IDnow Trust Platform sandbox to list verification flows, create sessions, check sessions, and get session details.

An MCP server that exposes 43 domain tools behind 4 meta-tools, applying guardrails such as budgets, rate limits, schema validation, human-in-the-loop confirmation for mutations, PII redaction, and an append-only audit log while reducing context window usage.

Provides a human-approval tool for MCP-compatible agents, pausing execution until a human approves or edits the action, with every decision logged.

Enables an AI assistant to list, search, and read email over IMAP without marking messages as read, and to create and revise reply drafts that you review before sending. It runs with least privilege, keeping the app password in an OS keychain or password store and never sending, deleting, or moving anything.

Scans prompts for PII and masks or redacts sensitive data locally before sending to an LLM, supporting multiple anonymization modes.

An MCP server that enforces plain-English rules on AI agent tool calls, deterministically blocking forbidden actions before execution via a Claude Code hook and a check_action tool.

A pre-action risk gate for AI agents. Your agent calls the forecast tool before any irreversible action — send email, run SQL, make a payment, delete a file — and gets a risk score (0–100) and a GO / CONFIRM / STOP verdict in a few seconds.

Enables email address verification through a single MCP tool, returning whether an address is valid, invalid, or risky.

Enables binary comparison capabilities by leveraging IDA Pro and BinDiff to analyze similarities and differences between files. Users can perform automated function analysis to identify changed functions and compare original binaries against patched versions.

An MCP proxy that enforces policy on every tool call, blocking or flagging actions before they reach downstream MCP servers.

A demonstration server that reveals security risks by accessing sensitive environment variables, illustrating how MCP tools can potentially leak user data without explicit consent.

Enables AI coding agents (Claude Code, Copilot, Cursor, Windsurf) to log tool actions automatically through hooks or via the et_log_action tool, buffering them for flush to an ingestion API as SHA-256 hash-chained audit evidence linked to pull requests.

A read-only MCP server that lets an agent browse the HackerOne Hacker API using an authenticated hacker account, exposing programs, policies, scope, reports, and payments. It cannot create, update, or submit reports.

Give any MCP-compatible AI the ability to create and verify agent departure records.

An MCP server that provides safeguard capabilities to protect against prompt injection and unsafe tool calls.

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 security inspection of MCP tool metadata by analyzing tool names, descriptions, and input schemas, and returning SAFE, REVIEW, or HIGH RISK verdicts through the analyze_tools tool.

An MCP server for 7-Zip archive operations (list, extract, create) with dual-engine architecture and sandbox security features. Note: currently a learning project and not yet functional.