"Sublime Text" matching MCP servers:

Enables LLM agents to fetch web pages safely, blocking SSRF, downloads, hidden text, and prompt-injection attacks before returning cleaned content.

Enables structured robustness and security testing by scanning text for policy/safety issues and generating test suite outlines.

MCP server that provides tools to scan text and URLs for prompt injection attacks, protecting AI agents from adversarial inputs.

Local-first CLI and MCP server for redacting sensitive text before sharing logs, configs, and errors with AI tools.

Deterministic untrusted-text inspection with paid x402 HTTP and MCP tools on Base

Detect PII in text: emails, phones, SSNs, credit cards, IPs, addresses. Pay-per-call via x402 micropayments without API keys or signup.

Enables AI assistants to scan text and compare strings for hidden prompt-injection content such as ASCII smuggling, zero-width or emoji steganography, bidirectional text tricks, and homoglyphs. It provides one detection layer, not a full defense against plainly written prompt injection.

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.

Detects leaked credentials in source code with tools to scan text, files, and directories for API keys, tokens, and private keys across 30+ providers.

Enables sanitizing PII from text, classifying data into sovereignty zones, and monitoring compliance scores to keep sensitive information out of AI outputs.

Blocks indirect prompt injection by tracking data provenance, not text patterns. Enables safe agent interaction with untrusted content.

A spec-compliant remote MCP server with built-in OAuth 2.1 and Dynamic Client Registration, enabling Notion Custom Agents to connect via 'Sign in with OAuth' without bearer tokens. It supports SSO federation to Google and Microsoft Entra, and includes basic tools like whoami, echo, and slow_task.

A tiny local MCP server and CLI that lets AI agents read only allowlisted environment variables, redacts known secrets from text, and logs every access.

Provides cryptographic hash and HMAC computation for text, supporting algorithms like md5, sha1, sha256, sha384, and sha512. All operations are performed locally without transmitting or storing input data.

A minimal MCP server that tests Authgear's Dynamic Client Registration and resource-indicator flow, verifying JWTs bound to a specific resource.

Enables agents to request private text or image input from users, run a command once with the submitted values through a one-use grant, and retrieve only user-approved text output.

A remote MCP server demonstrating OAuth 2.1 authentication with Firebase, providing a 'whoami' tool that returns the authenticated user's identity and plan.

Enables deterministic, no-LLM scrubbing of secrets from text or logs before they enter agent context, supporting redaction, masking, and hashing without ever leaking the original value.

Enables authenticated, read-only access to mailbox folders, tags, message metadata, and message text via MCP, while preventing send, draft, delete, move, tag-change, contact/calendar changes, and attachment downloads.

Enables auditing of npm, Yarn, and pnpm lockfiles in local project directories or remote Git repositories, returning vulnerability findings filtered by severity threshold in text or JSON.