"AWS Organizations" matching MCP servers:

Provides tools for discovering, building, deploying, and troubleshooting AWS Deep Learning Containers (DLC) images. Supports multiple frameworks and instance recommendations.

Automates the AWS Foundational Technical Review (FTR) partner self-assessment by evaluating SOC 2 and WAFR reports against defined controls, returning structured PASS/FAIL decisions with reasoning.

Enables natural-language analysis of AWS cloud spending and Amazon Bedrock model invocation usage, including breakdowns by service, region, day, user, model, and cross-account data.

Enables users to query and analyze AWS cloud spending and Amazon Bedrock model usage through natural language, with breakdowns by day, region, service, instance type, user, and model, including cross-account cost visibility.

Enables natural-language queries of AWS spend and Bedrock usage data, providing detailed breakdowns by service, region, account, user, instance type, and model, including cross-account cost analysis.

Enables natural-language analysis of AWS cloud spending by exposing Cost Explorer API functionality, including EC2, Bedrock, and per-service cost breakdowns by day, region, user, model, and instance type. It also retrieves Amazon Bedrock usage data from CloudWatch model invocation logs and can pull spend information from other accounts via assumed IAM roles.

Enables users to query and visualize AWS spend and Amazon Bedrock usage data through natural language, including EC2 and service cost breakdowns and Bedrock usage by region, user, and model.

Enables natural-language querying of AWS cloud spending and Amazon Bedrock usage logs, with detailed breakdowns by day, region, service, instance type, user, and model, including cross-account cost retrieval.

Enables users to query AWS spend data and Amazon Bedrock usage from CloudWatch model invocation logs through natural language. Supports detailed cost breakdowns by service, region, day, and instance type, including cross-account AWS spend retrieval.

Enables users to query AWS spending and Amazon Bedrock usage in natural language through MCP clients, with breakdowns by service, region, day, model, and user, plus optional cross-account access.

Enables users to ask natural-language questions about their AWS cloud spending, retrieving granular cost breakdowns by day, region, service, and instance type, along with Amazon Bedrock model usage pulled from CloudWatch invocation logs. It also supports cross-account spend analysis by assuming a role in other accounts.

Enables users and agents to query and analyze AWS spending and Amazon Bedrock model usage through natural-language interactions via MCP. It provides tools for service, EC2, region, and Bedrock usage/cost breakdowns, with optional cross-account retrieval.

Enables querying AWS Cost Explorer spend data and Amazon Bedrock model invocation logs through CloudWatch in natural language. Supports EC2, Bedrock, and cross-account cost analysis via local or remote MCP transports.

Enables users to query and analyze AWS spend and Amazon Bedrock usage data through natural language, including breakdowns by service, region, user, model, and instance type.

Enables MCP-compatible AI clients to retrieve FinOps-aligned knowledge and runbooks on demand, covering cloud cost optimization across AWS, Azure, GCP, and OCI, AI inference economics, Kubernetes, data platforms, allocation, chargeback, anomaly management, and waste detection.

Rewrites resumes to beat ATS screening (Workday, Greenhouse, iCIMS, Taleo) against a specific job description, with strict truthfulness guardrails — never invents dates, metrics, titles, or seniority. Pay-what-you-want access codes ($0 works).

Pay-per-use IBM Granite AI over MCP — chat, code, embeddings, analysis, and forecasting, billed in USDC on Solana. No IBM account required.

MCP server for multi-provider AI image generation (AWS Bedrock, OpenAI, Google Gemini) enabling image generation, transformation, and editing through a unified interface.

Enable AI agents such as Claude, Co-Pilot, Codex and other compatible tools to create, manage, and optimize advertising campaigns on ChatGPT.

Open-source AWS security scanner with Attack Chains, Breach Cost Estimation, and MCP Server. 47 checks across 15 AWS services. Every finding includes copy-paste remediation (CLI + Terraform) and a dollar-risk estimate with verified source. First free standalone AWS security MCP server - Prowler and Wiz require paid SaaS.

Read-only MCP server exposing Ads AI Creator's image styles, pricing, and FAQ for AI clients to generate ad knowledge.

MCP server that delegates Claude Code subagents to alternative backends such as local models, DeepSeek, or AWS Bedrock, while keeping your Claude Code orchestrator session intact.

Exposes product-style completion tools (OpenAI chat-completions-shaped and Anthropic messages-shaped) that are fulfilled by sampling the host agent's own LLM over MCP, so no model API keys are ever needed. Also offers a model listing endpoint aliasing the host's model.

VibOps MCP is the control plane between your AI agents and your GPU infrastructure. 74 tools covering: GPU fleet management (deploy, scale, monitor across NVIDIA, AMD, Intel, AWS, Google, Groq), Agent Infrastructure Control Plane (per-agent GPU cost, budget enforcement, model policies, dependency graph), governance (AI Act, SOC 2, immutable HMAC audit chain), and GPU FinOps (chargeback, waste..)..

Provides tools to validate SageMaker workloads against the six pillars of the AWS Well-Architected Framework, returning findings with severity levels and recommendations.

An MCP server for the OpenAI Ads (ChatGPT Ads) Advertiser API, providing tools for agent-led performance marketing such as finding dead ads, auditing near-duplicate copy, and auditing ad-group context hints.

Connects AI assistants to OpenTelemetry trace backends (Jaeger, Grafana Tempo, Traceloop, Datadog, Sentry, AWS X-Ray, New Relic and Honeycomb) for natural-language trace and span search, error triage, cross-backend correlation, and LLM analytics such as token usage, model performance and the most expensive or slowest traces.

This server enables agents to identify users and organizations, inspect versioned datasets and model lineage, start training jobs, run and read evaluations, verify deployments, and execute typed workflows through authenticated MCP endpoints.

Enables coding agents to add a bounded semantic-judgment layer for routing, ranking, extraction, verification, and escalation, returning typed signals and review recommendations.

An MCP server that gives AI agents the ability to generate, edit, and manipulate images using Stability AI models on AWS Bedrock.

Supervised Meta Ads operating system for Claude Code. 57 tools for campaign management, multi-asset ads, targeting, pixel diagnostics, catalogs, and safety gates. All ads created PAUSED - operator approves every action.

A sovereign Google marketing-agency control plane over the Model Context Protocol, enabling an AI agent to safely operate 20 Google marketing products with read and guarded write capabilities.

Fetches recent AI news from curated RSS feeds, summarizes them with OpenAI, and caches results in AWS DynamoDB for efficient access.

Dry-run-first Google Ads search-term intent analyzer and negative-keyword MCP for agents.

Professional AI-powered architecture diagram generator with multi-cloud support and MCP server integration. Generates beautiful, accurate diagrams with provider-specific icons for AWS, Azure, GCP, Kubernetes, and more.

Enables AI agents and finance teams to extract structured fields from messy invoices and audit them before payment, applying seven evidence-backed risk rules that catch total/tax mismatches, duplicate invoices, missing fields, future dates, and round amounts, then returning a 0–100 score with a payment link. Exposes four MCP tools over stdio and Streamable HTTP (spec 2025-11-25) plus a web UI, backed by an optional AWS Bedrock or OpenAI-compatible extraction brain that degrades gracefully to a zero-dependency offline engine.

Enables Claude and other MCP clients to manage Pankow organizations, projects, test cases, and CI/runs, configure AI targets, and run LLM evaluations directly from an agent.

Enables quant research organizations to log hypotheses and outcomes, count trials for honest statistical verdicts, explore novel methods, run significance gates, and evolve reusable skills from validated trajectories, all backed by SQLite.

Exposes configured language models as ordinary MCP tools, enabling a host agent to select a model, send explicit message lists, and receive normalized responses through provider-neutral OpenAI-compatible, Anthropic, and Gemini adapters.

Enables MCP-compatible clients to search a shared ChromaDB-backed PDF document store and generate grounded, citation-aware answers through AWS Bedrock, without calling the REST API.