118,035 servers from the official registry, GitHub and npm. Filter by category, transport and language.
Enables Claude to fetch GitHub repositories, maintain persistent memory across conversations, and extract facts using local Ollama models.
Provides autonomous agents access to the ai-skills engineering library to retrieve real-time skill definitions and rules.
Runs a comprehensive trust and safety audit on MCP servers using static analysis, fuzz testing, and output fidelity checks.
Audit MCP server tool declarations for security risks and pin them to detect unauthorized changes or tool poisoning.
Provides guardrails and project maps for AI coding agents to prevent context drift, token waste, and destructive refactoring.
Analyzes MCP configuration files to identify mutable package references that could lead to silent code changes during resolution.
Audits MCP server configurations to detect abandoned, deprecated, or unmaintained repositories and packages.
Tracks new research papers matching a team's open problems by monitoring a markdown ledger and repository history.
Provides a research and modding workbench for Metal Gear Solid V that searches community documentation, inspects file formats, and runs asset converters.
Monitor and protect AI spending using SDKs that track model costs, agent usage, and provide pull request cost reviews.
Audits GitHub Actions workflows for security vulnerabilities using 37 deterministic rules and provides evidence-based findings.
An LLM agent that triages GitHub issues by assigning type and area labels and identifying duplicates through an MCP server.
Compares GitHub issue-triage agents built with custom REST API tools against those using GitHub's official MCP server through a benchmarking suite.
Validates AER-1 receipt format conformance using a corpus of vectors and checks for the Zambo verifiable work layer.
Scans files and code snippets for credential leaks using 86 rules, entropy detection, and baseline diffing to prevent secrets from entering repositories.
Reduces Claude Code token usage by running tests, git operations, code reviews, and project searches using local models via Ollama.
Scans Claude Code agents, skills, and MCP configurations to detect security risks like over-privileged permissions and unpinned dependencies.
Aggregates domestic hot lists and international RSS feeds to provide AI-driven news analysis, translation, and trend monitoring.
A self-hosted gateway that connects Muse to MCP servers with granular, owner-approved access policies.
Provides a CI/CD feedback loop and guardrail for AI agents to prevent hallucinations by exposing build statuses, logs, and wait commands via MCP.
