"How to use a search engine" matching MCP servers:

Safety middleware for AI computer use agents that monitors, enforces policies, and provides guardrails to enable safe desktop interaction.

Demonstrates Agent Passport System pre-dispatch authorization by issuing one-use grants and verifying signed authorization envelopes before proxied tool calls reach the upstream server.

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

Read-only ProofRelay MCP verifier for non-confidential evidence bundles. Exposes 22 public-safe tools, 11 resources, and 11 prompts for bundle integrity checks, receipt-chain review, checkpoint recommendations, MCP risk metadata review, and real-estate closing proof-pack readiness.

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 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

Enables AI agents to securely use real secrets (API keys, database passwords) by requiring human approval for each release, ensuring secrets never enter the model's context.

Scans suspicious messages, URLs, and text for scams inside any MCP-compatible AI assistant. No signup or API key needed for anonymous use.

Enables AI assistants to read identification verdicts, search history, summarize entities, explain risk scores, and verify webhook signatures through read-only tools over stdio or streamable HTTP.

A consequence engine for shell commands. Blast Scope scores what a command would actually do before an AI agent runs it.

A local-first MCP server that scores your codebase's Build Readiness by reading code and running tests on your machine, outputting a diligence-grade score and risk register without uploading your source.

Enables passive security scanning of HAR files from QA test automation to detect missing security headers, insecure cookies, CORS misconfigurations, and leaked secrets, without making any live requests.

Investigate fraud directly from Claude, Cursor, or any MCP-compatible client. Analyze suspicious activity with clear, evidence-backed verdicts. Pivot from a single signup to every account sharing the same device, IP address, or email inbox. Check entities against a cross-operator abuse network, review linked accounts, and efficiently process your fraud review queue. Read-only by default, with no r

Lets an LLM explore a cryptic legacy ERP schema in plain language through a semantic layer (table listing, column descriptions, published dictionary) and run single read-only SELECT queries that return capped results. Enforces safety at the database engine level: only reads are authorized, sensitive columns are masked to NULL, queries are aborted after a few seconds, and every call is written to an append-only audit log.

A read-only MCP server that provides tools to read, list, and inspect secrets from HashiCorp Vault's KV secrets engine (versions 1 and 2) using a Vault token.

MCP server to easily use compliance-trestle for OSCAL compliance workflows from any MCP-compliant client.

Enables agents to discover, compare, and install other MCP servers using natural language tasks, backed by a searchable index of thousands of servers.

Read-only attack-path tools for cloud and Kubernetes: list the reachable routes from internet exposure to sensitive assets, explain each hop and the evidence behind it, and simulate a fix before recommending it. Connects to a running PerspectiveGraph engine.

Runs a regular expression on real engines — JavaScript (V8), Python (CPython re), PCRE2 and RE2 — reporting each engine's own compile errors with positions, every match with its groups and named groups, replacement results, and where the engines disagree. It also detects catastrophic backtracking (ReDoS), naming the at-risk part of the pattern, generating an attack string, and timing how long each engine actually takes on it.

An MCP server that enables AI assistants to interact with Tenzir, a data pipeline engine for security operations, including executing pipeline queries, managing OCSF schemas, and generating parsers.