"Exploring Computer Usage" matching MCP servers:

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

Enables querying and analyzing Tenable Vulnerability Management audit logs, including activity summaries, API key usage, and anomaly detection through MCP tools.

Demonstrates agent-native platform onboarding with human-in-the-loop API key provisioning, plus live usage and rate-limit queries via Anthropic Admin APIs.

Enables AI agents to read Microsoft 365 tenant data, such as users, license usage, and stale accounts, while enforcing least-privilege by refusing to run with excessive Azure permissions.

Enables local spend caps and Ed25519-signed provenance receipts for AI agent tool calls, allowing any MCP host to gate model usage and independently verify signed decisions without sending prompts or content.

Enables MCP clients to check URLs for scam/phishing risks, get verdicts with confidence and severity, report false positives, and monitor plan usage.

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.

Enables LLM agents to extract, validate, and mask personally identifiable information using deterministic regular expressions, reducing token usage and hallucination risks.

Enables read-only access to Teramind's employee-monitoring metadata, including computer and agent inventory, departments, alerts, anomaly rules, behavior policies, and monitoring profiles.

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.

Automates Android app analysis using Frida via AI commands, connecting a rooted Android phone to a computer and running dynamic analysis scripts without manual command execution.

Full coverage of Anthropic Admin API to manage organization, workspaces, members, API keys, usage, and costs via natural language from any MCP client.

Provides threat intelligence lookups against the AbuseIPDB database, enabling IP reputation checks, CIDR block analysis, and log enrichment. It features intelligent caching and rate limiting to efficiently manage API usage for security analysis and automated workflows.

Exposes the OpenAI Admin API as MCP tools, enabling management of organization members, projects, service accounts, API keys, rate limits, usage, costs, and audit logs through natural language.

Exposes verification and safety tools to MCP clients, enabling text and agent-output hallucination checks, computer-use action risk grading, and prompt-injection, jailbreak, harmful-content, sensitive-data, and fraud screening through an authenticated proxy.

Enables read-only access to Circle parental-control data, including family profiles and per-profile internet usage.

Enables observability and governance for local LLMs via Ollama, including auditing model usage, scanning prompts for secrets/PII, and enforcing allow/deny policies.

Provides 45 developer utilities (UUID generation, hashing, JWT decoding, etc.) for AI assistants like Claude Desktop, Cursor, and Windsurf. Includes 16 free tools and 29 pro tools with trial usage.

Enables read-only interaction with HackerOne, providing tools for searching and analyzing reports, exploring programs and scope, accessing earnings, and retrieving public disclosures.

Enables AI assistants to manage API keys, check usage, and debug authentication issues for the Holdify API.