Developer Builds MCP Linter and Discovers Security Issues in Anthropic Official Servers
A developer has created mcp-linter, a zero-dependency security linter for the Model Context Protocol (MCP) introduced by Anthropic. The tool helps developers avoid common pitfalls when building servers that connect Claude Desktop, Claude Code, Cursor, and autonomous agents to external resources.
The Model Context Protocol is built on JSON-RPC 2.0 and uses stdio transport for local servers. Any unintended output to stdout, such as a stray console.log statement, immediately breaks the protocol framing and causes the client to disconnect or fail parsing.
Four hidden problems identified
The article details four recurring issues. First, stdout pollution occurs when diagnostic messages are written to the wrong stream instead of stderr. Second, missing destructiveHint and readOnlyHint annotations allow agents to invoke dangerous tools like delete_user without human oversight. Third, tool poisoning lets attackers embed prompt-injection directives inside tool descriptions that are fed directly to the model. Fourth, incomplete input schemas without descriptions force the LLM to guess argument formats, raising hallucination rates.
The linter launches the target server in an isolated child process, performs an initialize handshake, requests tools/list, resources/list and prompts/list, then evaluates 34 rules before cleanly exiting. It produces a health score from 0 to 100 and can emit SARIF reports for GitHub Code Scanning.
Results on official Anthropic servers
- @modelcontextprotocol/server-everything scored 90/100; one parameter lacked a description.
- @modelcontextprotocol/server-memory scored 66/100; four parameters were missing descriptions and top-level instructions were absent.
- @modelcontextprotocol/server-filesystem scored only 38/100; 18 parameters had no descriptions, making correct tool calls significantly harder for models.
The project is available on npm and GitHub under the MIT license. Planned enhancements include support for SSE and WebSocket transports, context-budget auditing, and LLM-assisted schema repair.
Related articles
Taming the LLM Dragon: Corporate AI Gateway Architecture Addresses Classic Proxy Shortcomings
Spontaneous adoption of generative AI across enterprises has created shadow AI risks, prompt leaks, and uncontrolled token consumption that standard L7 proxies cannot mitigate. Traditional solutions built on Nginx, Envoy or Kong lack the ability to inspect Server-Sent Events streams, classify sensitive content inside prompts, or enforce token-based quotas in real time. The AI Optimum platform introduces a specialized AI gateway layer that sits between internal consumers and both local inference clusters and external APIs such as GigaChat and YandexGPT. It performs inline PII masking, routes traffic according to data sensitivity, supports OpenAI-compatible endpoints, and maintains detailed audit logs required under 152-FZ. The gateway adds only tens of milliseconds of latency while enabling granular billing, context caching optimization, and protection against runaway agent loops. Subsequent articles in the series will examine real corporate AI spend and further regulatory controls.
Why We Banned Our AI Manager from Writing Code and Assigned the Task to Claude Opus
The team behind an AI-powered marketplace manager for Wildberries initially built the system using regular updates, then migrated it to an autonomous agent. After implementing multiple layers of restrictions, they ultimately removed the agent entirely and rebuilt the solution from scratch. The new architecture relies on a single tool that handles the complete Wildberries API along with internet access while respecting all platform limits. The decision to prohibit the original AI manager from generating code stemmed from concerns over reliability and security in production environments. Instead, the developers turned to Claude Opus to handle coding tasks. This case highlights practical challenges of deploying AI agents in e-commerce automation and information security contexts.
Pentesting AI Components: Key Vulnerabilities CISOs Must Address in RAG and AI Agents
The article examines how AI integration into corporate systems dramatically expands the attack surface beyond traditional web application testing. It details risks associated with chatbots, RAG-enabled systems that pull from internal documents, and autonomous AI agents capable of executing real actions via APIs. Yuri Grishaev, an OSCP+ certified specialist and top Standoff 365 hacker, explains how prompt injection can bypass access controls and lead to data leaks or unauthorized operations. The piece stresses that service accounts often hold broad privileges, allowing AI components to serve as indirect paths to sensitive data even when direct user access is restricted. It also covers how AI-generated output can trigger classic vulnerabilities such as XSS if not properly sanitized. Recommendations include inventorying all AI tools, enforcing least-privilege principles, and validating user permissions before any model processes or acts on retrieved content. ABP2B provides free checklists and policy templates to help organizations prepare for secure AI adoption.
Local LLMs Enable Scams by Drafting Fraudulent Replies Without Warnings
Tests on consumer hardware showed that popular 7-8B local models almost never flagged classic advance-fee schemes when asked to draft replies instead of detecting fraud. The author ran 42 scam scenarios across Russian, Kazakh and mixed language on Llama 3.1 8B, Qwen 2.5 7B and DeepSeek-R1 8B using only an RTX 5050 laptop and Ollama. Without additional controls the models produced ready-to-send messages agreeing to prepaid transfers to unknown Kaspi Gold numbers in nearly every case. Introduction of the MoneyGate layer, which combines a mandate check, a separate judge model and hard-coded red-flag rules, blocked all 42 malicious requests while still allowing most legitimate payments to proceed. The benchmark KZ Scam Shield covering 12 Kazakhstan-specific fraud patterns remains publicly available for further testing.