Search: cep
Search MCP servers and agent skills by name, description, category or topic — 51 results.
silenceper/mcp-k8s
MCP-K8S is an AI-driven Kubernetes resource management tool that allows users to operate any resources in Kubernetes clusters through natural language interaction, including native resources (like Deployment, Service) and custom resources (CRD). No need to memorize complex commands - just describe your needs, and AI will accurately execute the corresponding cluster operations, greatly enhancing th
testmu-ai/codeception-skill
Generate Codeception acceptance, functional, and unit tests in PHP
bighippoman/intercept-mcp
Multi-tier fallback chain for fetching web content as clean markdown. Handles tweets, YouTube, arXiv, PDFs, and regular pages with 9 fallback strategies.
malinoto/tracepass-mcp-server
EU Digital Product Passport automation for AI agents. Create products, build and audit DPPs (battery, electronics, textiles, and more), set economic-operator parties, and read or capture GS1 EPCIS 2.0 supply-chain events via the TracePass platform. 6 tools, hosted (`https://ai.tracepass.eu/mcp`) or local. Install via `npx -y tracepass-mcp-server`.
perceptdot/percept
AI-powered observability platform for agents. Auto-discovers and recommends MCP servers; built-in connectors for GA4, Vercel, GitHub, and Sentry with ROI tracking. `npx -y @perceptdot/core`
deanpeters/user-story
Write user stories with acceptance criteria using Mike Cohn and Gherkin formats
deanpeters/opportunity-solution-tree
Generate opportunities and solutions and recommend proof-of-concept tests
NVIDIA/TensorRT-LLM/kernel-cute-writing
Write and implement GPU kernels using NVIDIA CuTe DSL (CUTLASS 4.x Python API) — NOT for Triton, CUDA C++, or conceptual explanations.
NVIDIA/cuopt/numerical-optimization-formulation
Numerical optimization (LP, MILP, QP) — concepts, problem-text parsing, and formulation patterns.
mariocandela/beelzebub
Beelzebub is a honeypot framework that lets you build honeypot tools using MCP. Its purpose is to detect prompt injection or malicious agent behavior. The underlying idea is to provide the agent with tools it would never use in its normal work.
video-db/skills
Realtime and batch video workflows: capture screen/audio, ingest URLs/YouTube/RTSP, transcribe, index, search, generate subtitles, edit timelines, and stream HLS output
abrinsmead/mindpilot-mcp
Visualizes code, architecture and other concepts as mermaid diagrams in a locally hosted web app. Just ask your agent to "show me this in a diagram".
drolosoft/immich-photo-manager
Turn your self-hosted Immich photo library into a conversation — natural language search via CLIP, geographic album curation from GPS data, cross-source duplicate detection with perceptual hashing, library health reports, and offline-ready interactive HTML galleries. Claude Code plugin with 21 MCP tools, 11 skills, and 5 slash commands.
dkships/pm-copilot
Triangulates HelpScout support tickets and ProductLift feature requests to generate prioritized product plans. Scores themes by convergence (same signal in both sources = 2x boost), scrubs PII, and accepts business metrics from other MCP servers via `kpi_context` for composable prioritization.
avivsinai/langfuse-mcp
Query Langfuse traces, debug exceptions, analyze sessions, and manage prompts. Full observability toolkit for LLM applications.
buildepicshit/Wick
Native C# MCP server for Godot Engine — 53 tools across 5 pillars: Roslyn-enriched exception telemetry, scene tree inspection, C# symbol navigation, MSBuild orchestration, and GDScript analysis. .NET 10, TCP JSON-RPC bridge, 219 tests.
knaisoma/data-olympus
Governance-grade project knowledge MCP server for coding agents. Git-native Markdown knowledge base with proposed vs accepted guidance, validity windows, supersession chains, and status-aware retrieval of current in-force decisions and standards. `pip install data-olympus`
mastyf-ai/mastyf.ai
Open-source runtime security proxy for MCP. Transparently intercepts every tools/call through an 18-class attack defense pipeline (prompt injection, SSRF, shell injection, SQL injection, credential exfil, polyglot attacks) with a YAML policy engine and 304-entry adversarial corpus. Trust scoring for npm MCP packages with 0-100 badges. Cloud dashboard, Docker image, Python SDK. MIT.
magna-nz/aspnetcore-debugger-mcp
MCP server for interactive .NET / ASP.NET Core debugging via netcoredbg. 27 tools: breakpoints (line, function, exception, data), stepping, thread inspection, exception autopsy, hang/deadlock analysis, and request tracing.
enmanuelmag/heimdall-mcp
Transparent proxy for any MCP server that intercepts all JSON-RPC messages, measures latency, and stores traces in SQLite, PostgreSQL, or MySQL. Exports OpenTelemetry (OTLP) spans to Jaeger, Tempo, or Grafana. Supports stdio, HTTP, and SSE transports. `npx @cardor/heimdall-mcp`
humanforai/humanforai-mcp
Hire a real human operator for tasks that need physical presence, perception, or judgment: real-world verification, product testing, AI output review, data collection, and local errands. Remote streamable HTTP at https://humanforai.dev/mcp or local stdio via `npx -y humanforai`.
OHNLP/omop_mcp
Map clinical terminology to OMOP concepts using LLMs for healthcare data standardization and interoperability.
P4ST4S/mcp-audit
Transparent Go proxy that intercepts, signs, rate-limits, redacts, and audits all MCP JSON-RPC tool calls without modifying client or server.
wenb1n-dev/mysql_mcp_server_pro
Supports SSE, STDIO; not only limited to MySQL's CRUD functionality; also includes database exception analysis capabilities; controls database permissions based on roles; and makes it easy for developers to extend tools with customization
behrensd/mcp-firewall
Deterministic security proxy (iptables for MCP) that intercepts tool calls, enforces YAML policies, scans for secret leakage, and logs everything. No AI, no cloud.
makenotion/spec-to-implementation
Turn product/tech specs into concrete Notion tasks with acceptance criteria and progress tracking
cfpramod/open-museum-mcp
Federated, license-verified search across The Met, Cleveland, AIC, Wikimedia Commons, and Europeana. Strict-default-deny rights gate accepts only CC0 / Public Domain Mark. Tools: search, get, cite (full / caption / short), dynasty/region discovery. `npx -y open-museum-mcp`
bodyegypt/lobbyvoices-mcp
Official remote MCP server for [Lobby](https://lobbyvoices.com/developers), an AI receptionist for small businesses. Seven free no-auth tools: write business phone scripts and IVR menus (English + Mexican Spanish), generate ElevenLabs agent system prompts, calculate missed-call cost, get a hire-a-receptionist verdict, role-play a call against the live receptionist engine, and get a real demo numbe
ejentum/ejentum-mcp
MCP server with reasoning, code, anti-deception, and memory tools for AI agents.
adrianczuczka/mason
Context engineering MCP server. Generates CLAUDE.md from git history and architectural file sampling, and maintains a concept-map snapshot of features/flows → files so agents can skip grep/glob on repeat queries.
chrbailey/promptspeak-mcp-server
Pre-execution governance for AI agents. Intercepts and validates every agent tool call through an 8-stage pipeline before execution — risk classification, behavioral drift detection, hold queue for dangerous operations, and complete audit trail. 45 tools, 658 tests.
realkimbarrett/scroll-stopping-creative
Create ad concepts that stop attention in the first 3 seconds
botmonster/image2svg-mcp
Convert raster images (PNG/JPG/WEBP/TIFF) to SVG vector format. Single tool, accepts base64 or URL input; runs locally via `uvx image2svg-mcp` or as a Docker HTTP server.
alanpcf/brasil-data-mcp
Brazilian public data for AI agents — companies (CNPJ), addresses (CEP), banks (BACEN), national holidays — via [BrasilAPI](https://brasilapi.com.br). No auth, no API key. Install: `npx -y brasil-data-mcp`.
jamjet-labs/jamjet-policy
MCP stdio interceptor (`@jamjet/mcp-shim`) that applies one YAML policy file (block / require_approval / audit / budget cap) to `tools/call` requests before they reach the real MCP server. The same policy also runs in Claude Code PreToolUse hooks (`@jamjet/claude-code-hook`), OpenAI Agents SDK guardrails (`@jamjet/openai-guardrail`), and JamJet's Python/TS SDKs — `jamjet audit show` tails every de
EtienneChollet/ontomics
Semantic code index that extracts domain concepts, naming conventions, and behavioral similarity from codebases. One tool call instead of 19, ~20x fewer tokens for codebase understanding queries.
Connectry-io/connectrylab-architect-cert-mcp
Free certification prep for the Claude Certified Architect exam. 390 scenario-based questions, guided capstone build, 30 concept handouts, 6 reference projects, practice exams, interactive UI with clickable answer cards, glassmorphism progress dashboard, spaced repetition, and deterministic grading.
stevepridemore/graph-memory
Personal knowledge graph for Claude on Neo4j. Typed entities (Person/Project/Decision/Preference/Concept), bi-temporal edge validity (`valid_at`/`invalid_at`), per-type weighted decay, contradiction detection, and a nightly "dream" extraction process. Local bge-small-en embeddings, no API keys. Optional OAuth 2.1 + Cloudflare Tunnel for cross-device use across Claude Code, Desktop, web, and iOS.
Yang1Bai/claw-tsaver
Token-saving MCP proxy that intercepts oversized tool returns and replaces them with a preview + on-demand handle. Real benchmark: 11,507 tokens → 104 tokens (99.1% saved) on a Wikipedia fetch. Works with OpenClaw + Claude.
payclaw/mcp-server
Virtual Visa cards for AI agents. Just-in-time card issuance per transaction, human-approved spend authorization, MCP-native. Works anywhere Visa is accepted.
bruno-portfolio/agrobr-mcp
Brazilian agricultural data for LLMs — prices, crop estimates, climate, deforestation from 19 public sources via CEPEA, CONAB, IBGE, INPE and B3.
jcooley8/pincushion-plugin
Visual feedback as agent work packets. Stakeholders drop pins on your live app; your AI coding agent reads each pin (selector, screenshot, DOM snippet, thread, acceptance criteria) via MCP and ships the fix, recording the commit/branch/PR on resolve. Install: `npx pincushion-mcp`.
yuvalsuede/claudia
AI-native task management system for Claude agents. Hierarchical tasks, dependencies, sprints, acceptance criteria, multi-agent coordination, and MCP server integration.
Agnuxo1/benchclaw-integrations
Register LLMs/agents and submit research papers (Markdown) to the [BenchClaw](https://www.p2pclaw.com/app/benchmark) leaderboard. Papers are scored by a 17-judge Tribunal with 8 deception detectors across 10 dimensions. No API key required. Works with Claude Desktop, Cursor, Cline, Zed, Continue.dev.
ahmetakyurt/zipmem-mcp
Local-first long-term memory for terminal AI agents (Claude Code et al.) via Anchored Compacting. Stores blueprints, code anchors (file→line→concept), and distilled lessons in a single JSON under `.zipmem/`, restoring full cross-session project context at near-zero token cost. No DB, no API keys, no embeddings. `npx zipmem-mcp`
log-logn/langfuse-mcp-java
Query Langfuse traces, debug exceptions, analyze sessions, scores, datasets, schema, observations and manage prompts. Full observability toolkit for LLM applications. (https://github.com/langfuse/langfuse)