Audience
Developers and teams whose AI agents install or connect to MCP servers
About The MCP Census
The MCP Census is a web-based evidence-checking service for developers and teams that use Model Context Protocol (MCP) servers. It compares server listings with public signals such as repository identity and status, package availability, hosted endpoint health, registry records, and vulnerability advisories. Users can look up a server or submit an MCP configuration and receive PASS, REVIEW, BLOCK, or UNKNOWN results under a versioned policy, with reasons and supporting evidence. The service is accessible through a website, REST API, and remote MCP server, and can be used in agent workflows and CI checks for configuration changes. Setup guides connect it to coding agents and developer tools. MCP Census is an initial public-evidence gate, not a malware scanner, penetration test, or guarantee that a server is safe to run.
Other Popular Alternatives & Related Software
General Analysis
General Analysis is an AI security platform that helps security teams adversarially test, monitor, and protect AI agents and systems in production. It is built to help organizations understand AI risk, prevent incidents, and secure real AI deployments across employee copilots, coding agents, customer support agents, healthcare assistants, legal assistants, financial copilots, creative pipelines, and other agentic workflows. It maps AI applications and agents across prompts, retrieval, tools, MCP servers, browser actions, permissions, repositories, cloud accounts, SaaS workflows, and business processes, then generates context-aware attacks that expose system-level risks. Its automated red teaming uses attacker models that adapt to target responses and produce multi-step exploit chains, helping teams uncover vulnerabilities that static prompt sets or endpoint-only tests may miss.
Learn more
Pillar Security
Pillar Security is a unified AI security platform for securing the agentic workforce across the entire AI lifecycle, from development to deployment and runtime protection. It connects business context across discovery, testing, and protection so security intelligence compounds across AI applications, agents, models, prompts, frameworks, tools, MCP servers, skills, coding agents, SaaS, cloud, code, and endpoints. Pillar helps organizations discover and manage AI assets everywhere, including shadow AI and unapproved systems, assess supply chain and posture risks, map agentic attack surfaces, and validate the vulnerabilities that actually matter. Its AI Security Posture Management capabilities analyze connected agents, tools, permissions, data sources, prompts, models, and supply chain components to expose risky paths, policy violations, misconfigurations, coding agent risks, and blast radius when a single component is compromised.
Learn more
Cortex Agentic Endpoint Security
Palo Alto Networks Cortex Agentic Endpoint Security (AES) is an AI-native endpoint security platform designed to protect enterprise devices from risks associated with autonomous AI agents and modern software applications. The platform continuously discovers AI agents, local models, browser extensions, IDE plugins, Model Context Protocol (MCP) servers, and other software components operating on endpoints. Its context-aware risk analysis evaluates software dependencies, permissions, behaviors, and potential security exposures to help organizations prioritize threats. Cortex AES provides automated governance policies and security guardrails that control agent interactions and restrict potentially unsafe software. Its real-time prevention capabilities block malicious agent actions, prompt injection attacks, unauthorized data access, and risky software execution before they cause damage.
Learn more
Flint AI
Flint AI is a local-first, framework-agnostic AgentOps CLI that helps developers determine whether an AI agent is reliable before it reaches production. One command, flintai scan, analyzes Python source code for security vulnerabilities, misconfigurations, risky tool access, missing guardrails, and quality issues, then uses AI reasoning to triage likely false positives. A second command, flintai eval, sends functional and adversarial prompts to a running agent and scores its responses across more than 35 built-in evaluations, including factual accuracy, instruction adherence, prompt injection resistance, jailbreak resilience, and other runtime behaviors. Each agent receives a reliability score, with findings mapped to OWASP Agentic Security Initiative risks ASI01 through ASI10 and severity scored using CVSS v4.0. Flint AI works with agent frameworks and SDKs including Claude Agents SDK, LangChain, CrewAI, Anthropic SDK, OpenAI SDK, MCP servers, and AutoGen.
Learn more
Pricing
Starting Price:
$0
Pricing Details:
The no-account tier allows 10 lookups per day. A free account includes 1,000 credits per month. Builder costs $19/month, and Team costs $49/month. One-time credit packs cost $9 for 1,000 credits.
Free Version:
Free Version available.
Company Information
MCP Census
Australia
mcpcensus.com
Videos and Screen Captures
Other Useful Business Software
Train ML Models With SQL You Already Know
Build and deploy ML models using familiar SQL. Automate data prep with built-in Gemini. Query 1 TB and store 10 GB free monthly.
Product Details
Platforms Supported
Cloud
Training
Documentation
