Behavioral trust grades (A–F) for MCP servers. Use when an agent needs to check whether an MCP server is safe before using it, verify an onchain attestation before trusting or paying a server, look up a server's published grade, get a project graded, or understand why a server received a grade. Polygraph connects to an MCP server the way an agent would, fingerprints its exact tool surface, and runs behavioral probes — prompt-injection (C-01), permission/egress overreach (C-02), sensitive-data leak (C-03), and adversarial-input handling (C-04) — then publishes a reproducible grade as an onchain EAS attestation on Base. Triggers on mentions of MCP server safety, is this MCP server safe, tool poisoning, prompt injection, data leak, permission overreach, unexpected egress, trust grade, attestation, verify before paying, polygraph, litmus, grade my MCP server, adversarial input, robustness, crash, jailbreak, CI gate, fail the build, GitHub Action, gate my skill.
Steady3 mentions in 2 weeks
2 projects use a version of this
1.2k7mo agoReviewMountCreate a free account to mount
Serverless and microservices development guidelines covering FastAPI, cloud-native patterns, API gateways, and best practices for scalable serverless architectures.
27539d agoReviewMountCreate a free account to mount
Use when editing `server/` — the SRouter Rust crate (axum 0.8, tokio, sqlx/SQLite, specta). Covers HTTP routes and router layering, middleware, `APIError` and `constants.rs` wire copy, provider drivers and registries, SQLite stores and migrations, SSE streaming, and the integration test harness. Trigger on changes under `server/src`, `server/tests`, or `server/migrations`, or when a task mentions a provider, executor, gateway route, or upstream.
2630d agoReviewMountCreate a free account to mount
Guide and boilerplate for developing stdio Model Context Protocol (MCP) servers in Node.js and Python. Covers JSON-RPC 2.0 framing, stdin/stdout buffering, and avoiding log contamination.
Use this skill when the user wants to run or debug MLX-VLM server inference, including uv run mlx_vlm.server, /v1/models, /v1/chat/completions, /v1/responses, streaming, OpenAI-compatible clients, health checks, metrics, model unload/reload, adapters, trust-remote-code, and server request/response failures.
5.8k2d agoReviewMountCreate a free account to mount
The user's Hetzner servers – web (Kirby sites) and dev (remote Claude Code and T3 Code): provisioning, patching, debugging, and adding or deploying a site.
A folder with a SKILL.md file: a name, a description of when to use it, and instructions. Claude loads a skill only when the task matches its description.
How do I use one I find here?
Copy the folder into your project's .claude/skills/ directory, or into your own skills folder to use it everywhere.
What do the warnings mean?
We read each file for commands that read secrets, delete things or pipe downloads into a shell, and say so before you copy it. No warning is not a promise that a file is safe.
Which skills worked for people?
Open a skill to see its discussion. Reports from people and their agents are coming.