Security audit of Model Context Protocol (MCP) servers — tool poisoning, prompt injection via tool descriptions and results, unscoped/over-privileged tools, path traversal in file tools, command injection in shell/exec tools, SSRF in fetch tools, secret leakage through tool output, missing approval gates on state-changing actions, confused-deputy and rug-pull tool redefinition, token passthrough, and unsafe stdio/HTTP transport config. Covers auditing both first-party and third-party MCP servers (Python FastMCP, Node MCP SDK) and their client configs (Claude Desktop, Cursor, Cline, Windsurf, Zed). Use when reviewing, hardening, or hunting bugs in an MCP server, an agent's tool integrations, or a mcpServers config block. 中文触发词：MCP审计、工具投毒、提示注入、智能体安全、MCP服务器漏洞
5.9k5mo agoReviewMountCreate a free account to mount
Adding, removing or changing a tool on RedAmon's INBOUND MCP server, where external agents connect in with a personal access token. The wiki API reference is generated from the server's live tools/list and goes stale silently, and each tool's annotations and declared scopes are published to connected clients. Trigger: editing a registerTool call in webapp/src/lib/mcp/server.ts; editing tools.ts, writeTools.ts, scopeCopy.ts or apiReference.ts in webapp/src/lib/mcp/; changing the scope list, default scopes, expiry presets or token prefix in webapp/src/lib/mcpAuth.ts.
3.4k8mo agoReviewMountCreate a free account to mount
Use when finding, comparing, reading, or monitoring arXiv papers, including requests for abstracts, citation graphs, original LaTeX, section-level technical details, or literature reviews.
3.3k4mo agoReviewMountCreate a free account to mount
Install, configure, and troubleshoot the EKS MCP Server connection in your AI assistant (Claude Code, Cursor, Kiro). Use ONLY for MCP server setup problems — config file location (.mcp.json), IAM permissions for eks-mcp actions, uvx installation, choosing AWS-hosted vs self-hosted mode, or debugging why MCP tools fail to appear after config. Also activate if user mentions "eks mcp", "mcp server", "mcp.json", or "mcp tools not showing". Do NOT use for actual cluster operations once MCP is working — those go to eks-recon (discovery), eks-operation-review (audits), or eks-upgrade-check (upgrades). For setting up the Arm migration MCP server used for arm64 readiness scanning, use graviton-migration, not this skill.
skill
---
name: add-mcp-server
description: Add or integrate an MCP (Model Context Protocol) server for agent tools
---
# MCPServer Integration Skill
Integrate external tool servers via MCP protocol into
7410mo agoReviewMountCreate a free account to mount
Build MCP servers with Node/TypeScript SDK — tools, resources, prompts, Zod validation, stdio vs Streamable HTTP. Use Context7 or official MCP docs for latest API. Use when building or debugging an MCP server — tools, resources, prompts, validation, or transport choice.
Build MCP servers with Node/TypeScript SDK — tools, resources, prompts, Zod validation, stdio vs Streamable HTTP. Use Context7 or official MCP docs for latest API.
Use when testing MCP servers -- e2e tests with the sunpeak inspector, visual regression testing, live testing against real ChatGPT, multi-model evals, Playwright configuration, or scaffolding test infrastructure with "sunpeak test init". Works with any MCP server (Python, Go, TypeScript, etc.), not just sunpeak projects.
2196mo agoReviewMountCreate a free account to mount
MCP (Model Context Protocol) sunucusu yazma: kavramlar (tools, resources, prompts), TypeScript SDK ile sunucu (Zod girdi şemaları, yapılandırılmış çıktı), stdio ve Streamable HTTP taşıma, uzak sunucuda OAuth ile kimlik doğrulama, araç tasarımı (az ve net araç, iyi açıklama, düzeltici hata mesajları), sayfalama ve büyük çıktılar, güvenlik (en az yetki, onay gerektiren işlemler, prompt injection), MCP Inspector ile test ve Claude Code / Claude Desktop'a ekleme. "MCP sunucusu yaz", "uygulamamı Claude'a bağla" dendiğinde kullan.
Model Context Protocol server exposing 53 tools, 3 resource types, and 3 prompts for AI agent consumption — quoting, building transactions, fee management, analytics, AMM operations, social fees, wallet operations over stdio transport.
1508mo agoReviewMountCreate a free account to mount
Builds, secures and tests Model Context Protocol (MCP) servers - choosing MCP vs a CLI or API, tools, resources and prompts, stdio vs Streamable HTTP transport, task-shaped tool design, logging rules, OAuth for remote servers, input validation, testing with the MCP Inspector, and versioning. Use when creating or reviewing an MCP server, exposing an API or database to AI agents through MCP, or debugging an MCP server that fails to connect, hangs or confuses the model. Not for designing the agent loop itself (use building-agents).
Use with Codex, Claude Code, or another MCP client when lsp-mcp-server is connected and semantic code navigation, analysis, refactoring, or diagnostics are needed. Covers all 29 lsp_* tools for TypeScript, Python, Rust, Go, C/C++, Ruby, PHP, Elixir, Kotlin, Java, and user-configured languages. Prefer these tools to text search for definitions, references, types, diagnostics, rename, code actions, hierarchy, symbols, ranges, and indexing.
2440d agoReviewMountCreate a free account to mount
How to use the b1-mcp-server MCP tools against SAP Business One (HANA / MS SQL database and Service Layer OData). TRIGGER when: a `b1-mcp-server` tool (`connect_database`, `execute_sql`, `execute_service_layer`, `execute_service_layer_write`, `get_schema_info`, `check_connection`) is about to run or has just failed; a query is rejected ("Only SELECT is permitted", "Unterminated quote or bracket", a table hint "is not permitted"); a result shows `TRUNCATED`; a HANA query fails with `Socket recv timeout`; a Service Layer write is refused or waits for approval; a profile connects the database but not the Service Layer. SKIP for writing the SQL or OData request itself — this skill covers the server's behaviour, not SAP B1 data modelling.
Add or change a tool, a tool's input schema or description, or the step, Maily email-body, skip-condition or payload-property schemas in apps/mcp-server (the hosted Novu MCP server, also shipped in process to the enterprise Copilot as @novu/mcp-server/tools). Keeps tools/list small (per-tool budgets, no $ref), advertises loose.pipe(strict) inputs that stay fully validated, keeps errors actionable without the schema, and preserves backward compatibility. Use before editing apps/mcp-server/src/tools or apps/mcp-server/src/utils.
40k3d agoReviewMountCreate a free account to mount
Expert guide for DOKU Model Context Protocol (MCP) Server integration. Enables AI Agentic Commerce with tools for DOKU Checkout, payment links, Virtual Accounts, QRIS, and order status checks / Panduan ahli DOKU MCP Server untuk AI Agentic Commerce.
7541d agoReviewMountCreate a free account to mount
Proactive skill for setting up and configuring the dbt MCP server for use with Claude Code and Claude Desktop. Auto-activates when a user asks about connecting Claude to dbt, setting up dbt MCP, or accessing dbt Semantic Layer or Discovery API from Claude. Covers local vs remote server modes, credential handling, and Wire project setup.
1441d agoReviewMountCreate a free account to mount
Read-only inspection of a third-party MCP server BEFORE it is added or trusted: scans tool descriptions and scopes for poisoning, returns an add, decline or sandbox verdict for a human. Never installs. Do not use to vet a skill or plugin (use skill-vet), to review first-party code (use review-hard or security-review), or to fetch a remote server definition (record its origin via capture-references, then get a local copy out of band).
1037d agoReviewMountCreate a free account to mount
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.
awarexoneReads credentialsSkill
