"A tool for browsing the web" matching MCP servers:

Enables centralized proxy and orchestration of MCP servers, providing unified tool discovery, authentication, and secure request routing. It adds a human-in-the-loop approval gate for high-risk actions and audit logging.

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.

Enables MCP clients to triage SOC alerts while enforcing a trust firewall across retrieval, memory, and privileged actions. It exposes tools for alerts, logs, memory, and alert actions, with defenses that refuse risky operations in the presence of attacker-controllable content.

A secure tool-execution plane for agentic AI that enforces JWT authentication, rate limiting, prompt-injection inspection, and audit logging, while ingesting downstream OpenAPI endpoints as MCP tools.

Enables AI agents to call tools through a security gateway that intercepts requests, enforces deterministic policy and risk checks, blocks or escalates high-risk actions for human approval, and keeps tool credentials and audit logs protected.

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

Input/output safety gate for AI agents: detect prompt-injection/jailbreak, leaked secrets/PII, and URL/IP reputation. Deterministic, no LLM.

Enables MCP tool handlers to be declared with a decorator, collected into a registry from a config map, and served over a bearer-token-authenticated Streamable HTTP ASGI app. Tools can also be invoked in-process without running any HTTP server.

Routes web requests from AI tools through Tor for anonymized fetching, with selective per-URL routing to bypass Tor-blocking sites.

Provides a local MCP server that exposes the check_prompt_injection tool to MCP clients, letting agents scan untrusted text (web pages, documents, tool outputs, emails) for prompt injection before passing it to another LLM.

Supply-chain gate for AI agent skills and MCP servers: poison-scan tool definitions, hash-pin the vetted set into a lock file and verify drift in CI. truecopy-mcp is a drop-in stdio proxy that filters a live server's tools/list down to its pinned, unmodified, unpoisoned tools.

Security scanner for third-party AI agent-skill files: SKILL.md manifests, hooks, and bundled scripts, exposed via an MCP tool.

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.

Enables agents and clients to fact-check factual claims against live web sources, returning citable verdicts with source details and cryptographically signed receipts for downstream verification.

An MCP front-end for AnB. The tool surface is "use-don't-reveal": no tool returns a plaintext secret. Reveal paths require a TTY the server doesn't have, so the no-reveal guarantee is structural, not prompt-based — it holds even against a prompt-injected agent. Runs as a dedicated, narrowly-scoped AnB identity; exec is default-deny (only allowlist rules tagged scope=mcp run); command output

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.

MCP security firewall (stdio): vet advertised tool definitions through static-scan → threat-feed → origin → pinning before they reach the model. Zero npm runtime deps. No secrets.

Lets an agent verify VSL settlement receipts entirely offline and produce signed triggers authorizing a settlement, with the signing key and endpoint fixed at start-up rather than passed in tool calls. When started with an endpoint and token, it can also request a receipt from an issuer, which is the only tool that touches the network.

Provides MCP-compatible AI agents with a verify_image tool to check a photo's capture time and provenance using C2PA, EXIF, XMP metadata, and pixel forensics, returning a verdict and confidence score.

This MCP server preserves a Bearer principal on every tool call and SSE frame, rotates vaulted credentials in place, and enforces per-tool allowlists for agents.

Enables MCP-speaking agents to execute tool calls through an authorization gate, producing signed decision records and reconciled effect rows for accountability.

Compare service-grant changes, tool alias origins, and saved MCP tool definitions with Gooo rules. Reports preserve incomplete-capture uncertainty and source bindings. No grants are applied and no compared tools are invoked.

Static security linter for MCP servers. Scans tool definitions for vulnerabilities (path traversal, SQL injection, SSRF), scores description quality, and auto-rewrites descriptions for safer agent tool selection.

Open-source permission control plane for AI agents — scan, enforce, and audit every tool call with code-level policies that prompt injection can't bypass.

An MCP server that lets an AI agent probe a live URL and confirm whether sensitive files (e.g., .git, .env, source maps) are genuinely served by fetching and validating the content, avoiding false positives.

MCP proxy that puts a deterministic gateway in front of any MCP server. Every critical tool argument (payee, amount, recipients) must resolve against a signed mandate or the user's own registries before a Cedar policy decides; step-ups are confirmed by the user through MCP elicitation, and every decision is a hash-chained receipt.

A local stdio proxy that pins every MCP tool definition when you approve a server and blocks the session with a diff if a description, schema or annotation changes later. A deterministic hash compare (RFC 8785 + SHA-256), with no model in the loop.

Enables AI agents to permanently remove personally identifiable information from PDF documents, returning redacted files with the sensitive text deleted rather than merely covered. Supports scanned documents, multiple languages, entity types, and optional human review.

One local gateway for all your MCP servers — shared by every AI coding tool (Claude, Cursor, VS Code, Codex). Set up each server once; keys stay in the OS keychain; lazy discovery keeps agent context small. Local-first, open source.

Enables production-grade answer verification for LLM agents by independently re-checking answers with a configurable verifier model, enforcing confidence policies, and producing Ed25519-signed, auditable verification results with optional web search and knowledge-base evidence.