Open-Source Tool mcp-security-scan Helps Teams Audit AI Agent MCP Servers

·1 views

MCP (Model Context Protocol) servers act as intermediaries between large language models and external tools, giving them broad system access and making them a high-value security target. Despite this, most development teams deploy MCP servers without any formal security review, a gap that contributed to the Moltbook breach, which exposed 35,000 emails and 1.5 million API tokens. An open-source CLI tool called mcp-security-scan has been released under the MIT license to address this problem, scanning MCP server source code and runtime behavior for risks including credential theft, data exfiltration, unsafe code execution, and filesystem vulnerabilities. The tool generates a structured JSON report and assigns a 0-100 trust score, with high-severity findings deducting 15 points each, and integrates with AgentGraph's identity layer. It is available as both a command-line tool and a GitHub Action at github.com/agentgraph-co/mcp-security-scan.

Read the full story at DEV Community

This is an AI-generated summary. ShortSingh links to the original source for the complete article.

Discussion (0)

NSF launches pilot program offering 4-year PhDs with industry research placements

The U.S. National Science Foundation (NSF) has announced a pilot initiative pairing universities with industry partners to offer four-year PhD programs. The program is designed to integrate hands-on industry research experience into doctoral training. NSF is partnering with select universities to test this model, aiming to better prepare graduates for careers beyond academia. The initiative reflects a broader push to align advanced research education with real-world industry needs.

0 comments Read more at Hacker News

ProgrammingDEV Community ·

Developer solves AI image generation crashes by freeing RAM, not closing editor

A developer running a local FLUX 12B AI image generation pipeline on a 16GB M4 Mac repeatedly hit memory-triggered safety kills that halted output while keeping the machine stable. The core problem was that the model's weights alone consumed around 7–9GB at runtime, leaving no headroom when the dev environment and other apps were also running. After experimenting with lower quantization and isolating variables, the developer found that raising available free memory from 51% to 71% before starting generation — primarily by closing a heavy browser — was the decisive fix. Switching from 4-bit to 3-bit quantization offered an additional ~2.5GB peak reduction, though it proved optional once sufficient RAM was freed. The debugging process highlighted how resident model weights, not output size, drive memory usage in large AI workloads.

0 comments Read more at DEV Community

ProgrammingDEV Community ·

Rob Pike: The Engineer Behind UTF-8 and the Go Programming Language

Rob Pike, born in 1956, began his career at Bell Labs in 1980, where he collaborated with Unix and C creators Ken Thompson and Dennis Ritchie on influential systems including Plan 9 and Inferno OS. In September 1992, Pike and Thompson designed UTF-8 in a single evening at a New Jersey diner, with Thompson sketching the encoding scheme on a placemat; within days, Plan 9 ran on UTF-8 as a full system. Today, UTF-8 powers nearly 98% of the web, enabling billions of users to exchange text in non-Latin scripts without data corruption. After joining Google in 2002, Pike teamed up with Thompson and Robert Griesemer in September 2007 to design a new programming language while waiting for a slow build to complete. Go was open-sourced by Google in November 2009, with its concurrency model — goroutines and channels — tracing a direct lineage back to Pike's experimental language Newsqueak from 1989.

0 comments Read more at DEV Community

ProgrammingDEV Community ·

Why Two Queries on the Same Table Can Return Different Row Counts

Two queries run against the same Iceberg table can return different row counts without either failing — one querying the catalog and another scanning storage directly returned results differing by over 211,000 rows. The discrepancy arises because Delta and Iceberg tables separate physical storage from logical table state, meaning a folder scan sees all Parquet files while a catalog query reads only those tied to a specific snapshot or version. Additional objects in storage may belong to older table versions, abandoned writes, or files superseded by delete metadata, none of which affect a committed snapshot's row count. To diagnose such differences, analysts should first resolve the exact Delta version or Iceberg snapshot used, follow the metadata chain to identify active data and delete files, and only then compare row counts. A query returning results successfully does not guarantee it read the intended table state or that all referenced files were accessible.

0 comments Read more at DEV Community