도구

Official CLI for Tencent's open-source knowledge base platform WeKnora: upload documents, manage knowledge bases, run hybrid search and answer questions from them, or serve as a read-only MCP. Needs your own WeKnora deployment and a source build with Go 1.26+.

HashiCorp's secrets management system: the vault CLI reads and writes secrets, issues dynamic database and cloud credentials on demand, encrypts and decrypts data, and manages leases and revocation. Needs a reachable Vault server.

Community-maintained cybersecurity skill library: 800+ skills across 34 domains including threat hunting, incident forensics, penetration testing and cloud security, mapped to MITRE ATT&CK and NIST CSF. Not by Anthropic; offensive skills are for authorized testing only.

Compliance skill from Anthropic's official operations plugin: maps controls, owners and evidence for SOC 2, ISO 27001, GDPR, HIPAA and PCI DSS, schedules audits, runs gap analyses, and outputs audit-readiness checklists and evidence collection plans. Have legal or compliance experts review.

Runs the cognee memory engine as an MCP server whose remember, recall and forget tools write documents and conversations into a knowledge graph and vector store for cross-session retrieval. Start it with Docker or uv first; needs an LLM API key by default, or connect to Cognee Cloud.

Fast vulnerability scanner driven by YAML templates: uses a community template library to detect known vulnerabilities over HTTP, DNS, TCP, SSL and more, supports custom templates and plugs into CI/CD. Use only on targets you're authorized to test.

Writes conversations and business data into Graphiti's temporal knowledge graph so agents can retrieve long-term memory by entity, fact and time. Open source from Zep; start FalkorDB or Neo4j and the server with Docker first, and configure an LLM API key.

Detects hardcoded passwords, API keys and tokens in Git repos, files and stdin, and can run as a pre-commit hook or GitHub Action to block leaks. Now feature-frozen with security fixes only, as the author has moved on to Betterleaks.

Finds leaked credentials in Git, GitHub, S3, filesystems and more, recognizing 800+ secret types and checking with each service whether a key is still live to cut false positives.

CLI and library for evaluating and red-teaming LLM apps: compare prompts and model outputs in bulk, scan for security vulnerabilities and plug into CI/CD, with evals running locally. Now part of OpenAI and still open source under MIT.

Open-source reverse engineering framework and CLI: disassemble, debug, emulate and patch binaries across many architectures and file formats, scriptable through r2pipe or built-in JavaScript.

Google's official skill library, focused on Google Cloud: 100+ skills for gcloud, Cloud Run, GKE, BigQuery, IAM, monitoring and logging, and the Well-Architected Framework, plus Ads and Analytics.

Google's official skill library and plugin marketplace: nearly 150 skills focused on Google Cloud (GKE, BigQuery, Cloud Run, IAM and more), plus 17 product plugins pairing skills with MCP for Cloud SQL, Spanner, AlloyDB, BigQuery, GCS and others.

Encrypts secret values in YAML, JSON, ENV and INI config files using AWS, GCP or Azure KMS, age or PGP, so secrets can be safely committed to Git alongside code. A CNCF sandbox project.

Industrial-grade open-source speech recognition toolkit from Alibaba's ModelScope, with an agent-friendly funasr command that turns audio into text, JSON or SRT subtitles in one step, with speaker diarization and timestamps. Strong on Chinese. Requires PyTorch.

AI2's tool for converting PDFs and scans to Markdown with a vision LLM, handling equations, tables, handwriting and multi-column layouts, suited to bulk digitizing papers and archives. Local runs need an NVIDIA GPU with 12GB+ VRAM; otherwise use a paid OpenAI-compatible remote endpoint.

Browser control from the browser-use team: an editable CDP connection lets agents drive the Chrome you are already using, writing missing helper functions as they go and keeping them for reuse. Also offers an MCP server. Allow remote debugging in Chrome on first use.

Lets Claude Code push ML research forward unattended: literature review, topic selection, experiment deployment, cross-model review loops and paper writing through rebuttal, in 80+ skills. Codex acts as the independent reviewer by default; other model pairings work too.

Context and harness engineering skills covering context compression and optimization, multi-agent architectures, memory systems, tool design and LLM-as-judge evaluation, activated automatically by task. Aimed at building production-grade agent systems.

Context and harness engineering skills: context fundamentals, degradation diagnosis and compression, multi-agent architectures, memory systems, tool design, LLM-as-judge evaluation and self-improvement loops. Focused on principles and design patterns, not tied to any agent platform.

Semantic multi-language static analysis: find vulnerabilities and bugs with rules that look like source code, across 30+ languages with custom rules. Scans locally by default without uploading code; cross-file analysis and Pro rules require sign-in.

Semgrep's official MCP server, now part of the main semgrep repo and started with semgrep mcp: lets agents run static security scans, find issues with custom rules and inspect syntax trees. Requires the Semgrep CLI; connecting to the AppSec platform needs SEMGREP_APP_TOKEN.

ModelScope's official training framework for LLMs and multimodal models: the swift command covers pretraining, fine-tuning, RL, inference, evaluation, quantization and deployment for 600+ text and 400+ multimodal models, with Megatron parallelism and a web UI. Usually needs a GPU.

Version datasets and models the way Git versions code: data lives in remote storage like S3 or GCS while versions are tracked in your Git repo. Also offers reproducible pipelines and local experiment tracking, rerunning only the steps affected by a change.