Model Context Protocol servers that connect AI assistants to real services and data. Browse by domain.
Ranked by Discovery Score — our 0-100 composite of adoption, maintenance, community, and license health. How scoring works.
By Erik Loyd, SaaS CEO and former COO/CFO of an AWS Premier Partner.
FastMCP is the fastest way to build MCP servers in Python. Decorate a function and it becomes a tool your AI assistant can call, with schema generation, validation, auth, and transport handled for you. Apache 2.0 and free. Version 4 turned it from a server library into a full framework with three pillars: servers that wrap your functions, clients that connect to any server, and Apps that render interactive UIs directly in the conversation. Setup is one uv add and a few lines of code. Written a Flask route? You can write an MCP server. FastMCP 1.0 was folded into the official MCP Python SDK back in 2024, and the standalone project has kept moving well past it, so read the upgrade guides before assuming existing code carries forward. There is an official TypeScript counterpart from the same team if Python is not where you live. Free at every size, and the library is complete rather than a demo that funnels you toward a paid tier. Prefect sells Prefect Horizon separately: an enterprise MCP gateway that deploys servers from GitHub with branch previews, keeps a private registry of every MCP in the company, and adds SSO, tool-level RBAC, and audit logs. Free for personal projects, enterprise pricing on request. Solo builders and small teams will not need it. Anyone running many servers across many teams is buying governance, not the framework. The catch is churn. Version 4 is in beta while 3.4.x is still shipping patches, and the docs carry separate upgrade guides from FastMCP 3, FastMCP 2, and two different MCP SDK generations. That is the cost of being the default in a protocol that is still moving. Pin your version and read the release notes before you bump.
The framework is free and complete. Prefect Horizon is a separate enterprise gateway, priced on request, and you only need it once MCP governance becomes somebody's job.
**Free tier:** The framework is Apache 2.0 and complete. Servers, clients, Apps, auth, and transports all ship in the open source package. No key, no seat count, no feature gate. **Self-hosted:** This is the normal path and it is cheap. A FastMCP server is a Python process, so it runs anywhere Python runs: a container, a VM, a laptop for local tools. Your costs are whatever hosts the process plus whatever API the server talks to on your behalf. The operational work is version discipline more than infrastructure, because the project moves fast and there are upgrade guides from three prior generations. **Paid:** Prefect Horizon is the commercial product, and it is a separate gateway rather than hosted FastMCP. It deploys servers from GitHub with branch previews and rollback, gives you a private registry of every MCP server in the org, and enforces SSO and tool-level RBAC with audit logging across clients like Claude, Cursor, and VS Code. Free for personal projects, enterprise tiers priced through sales. You are buying governance across many servers, not the ability to build one.
Framework for building full MCP applications with interactive React widgets. Works across ChatGPT, Claude, and other MCP-compatible clients. Think of it as a starter kit for MCP app development. Scaffold a new project with one npx command. Includes 15+ templates, a web debugger, and multi-language support. TypeScript and Python both work. More opinionated than FastMCP, more focused on end-user apps than raw server tooling. Maintained by the Manufact team. Free and MIT licensed. Optional paid cloud hosting available but not required.
Free and open source. The underlying service may have its own costs.
## Free Tier The MCP server itself is completely free and open source. Install it, configure your MCP client, and use it without any cost. ## Self-Hosted Runs locally or on your own infrastructure. No external dependencies beyond the service it connects to. ## Paid No paid tier. The MCP server is free. The underlying service may have its own pricing.
Connects your AI assistant to Git repositories. It can read commit history, diff branches, stage changes, and commit code. The model gets real version control awareness instead of guessing at repo state. You get log inspection, diff generation, branch operations, and commit creation. Point it at any local repo and it works. No API keys, no GitHub account needed, just a local Git installation. Completely free. Maintained by the official Model Context Protocol team. Essential for any AI-assisted development workflow. If your agent writes code, it should understand the repo it is working in. Install it.
Free and open source. The underlying service may have its own costs.
## Free Tier The MCP server itself is completely free and open source. ## Self-Hosted Runs locally or on your own infrastructure. ## Paid No paid tier. The underlying service may have its own pricing.
Gives your AI assistant persistent memory via a local knowledge graph. It stores entities, relationships, and observations in a JSON file that survives between sessions. The model can remember context about you, your projects, and your preferences. You get entity creation, relationship mapping, and observation tracking. Data lives in a local file you control. No cloud, no API keys, no external dependencies. Completely free. Maintained by the official Model Context Protocol team. If you want your AI to build up context over time instead of starting fresh every session, this is the simplest path. Lightweight and effective.
Free and open source. The underlying service may have its own costs.
## Free Tier The MCP server itself is completely free and open source. ## Self-Hosted Runs locally or on your own infrastructure. ## Paid No paid tier. The underlying service may have its own pricing.
Gives your AI assistant direct access to your local file system. Read files, write files, create directories, move things around. The model becomes a hands-on collaborator instead of just a talker. You get full CRUD on files and directories, with configurable root paths to keep the model sandboxed where you want it. Setup takes one config entry. No API keys needed. Completely free with no underlying costs. Maintained by the official Model Context Protocol team. This is foundational infrastructure. If you want your AI to actually do work on your machine, not just talk about it, this is non-negotiable.
Free and open source. The underlying service may have its own costs.
## Free Tier The MCP server itself is completely free and open source. ## Self-Hosted Runs locally or on your own infrastructure. ## Paid No paid tier. The underlying service may have its own pricing.
A test and demo server that exercises every MCP capability: tools, resources, prompts, sampling, logging, completions. It exists so developers building MCP clients can verify their implementation handles all protocol features. You get synthetic endpoints for every MCP feature type. Useful for integration testing and learning the protocol shape. Zero setup, zero config. Completely free with no underlying costs. Maintained by the official Model Context Protocol team. This is not a production tool. It is a reference implementation for MCP client developers. If you are building or debugging an MCP client, grab it. Otherwise, skip it.
Free and open source. The underlying service may have its own costs.
## Free Tier The MCP server itself is completely free and open source. ## Self-Hosted Runs locally or on your own infrastructure. ## Paid No paid tier. The underlying service may have its own pricing.
Gives your AI assistant a structured reasoning tool. Instead of jumping straight to answers, the model can break problems into numbered steps, revise earlier thinking, and branch into alternative approaches. Think of it as a scratchpad for complex problem-solving. You get step-by-step reasoning with revision and branching capabilities. No external dependencies, no API keys, no data leaves your machine. Completely free. Maintained by the official Model Context Protocol team. Useful for complex debugging, architectural decisions, or any task where thinking out loud produces better results. Low-cost addition to any MCP setup.
Free and open source. The underlying service may have its own costs.
## Free Tier The MCP server itself is completely free and open source. ## Self-Hosted Runs locally or on your own infrastructure. ## Paid No paid tier. The underlying service may have its own pricing.
Connects your AI assistant to the open web. Point it at any URL and it pulls back clean, readable content, converting HTML to markdown so the model can actually process it. You get web fetching with automatic content extraction, robots.txt compliance, and configurable request headers. Setup is one line in your MCP config. No API keys, no dependencies beyond the server itself. Completely free, no underlying service costs. Maintained by the official Model Context Protocol team at Anthropic. This is the reference implementation for web access. If your AI workflow touches URLs at all, install this first. It is the baseline.
Free and open source. The underlying service may have its own costs.
## Free Tier The MCP server itself is completely free and open source. ## Self-Hosted Runs locally or on your own infrastructure. ## Paid No paid tier. The underlying service may have its own pricing.
Gives your AI assistant accurate time and timezone awareness. The model can get the current time in any timezone and convert between them. Simple, but it solves the real problem of models not knowing what time it is. You get current time queries and timezone conversions. No API keys, no external services, runs entirely locally. Completely free. Maintained by the official Model Context Protocol team. A small utility, but surprisingly useful when your AI workflow involves scheduling, deadlines, or coordinating across timezones. Trivial to install, no reason not to have it.
Free and open source. The underlying service may have its own costs.
## Free Tier The MCP server itself is completely free and open source. ## Self-Hosted Runs locally or on your own infrastructure. ## Paid No paid tier. The underlying service may have its own pricing.
Context7 pulls current library documentation into your coding agent so it stops inventing API signatures from two-year-old training data. It covers a wide range of popular libraries, pre-chunked for LLM consumption, so the agent gets the relevant section instead of an entire documentation site. Setup changed this summer. Running the ctx7 setup command handles OAuth, generates an API key, and installs either the CLI-plus-Skills path or classic MCP mode, with flags to target Cursor, Claude, or opencode. Manual configuration against the hosted server with a bearer token still works. It runs without a key, but you share a rate limit with everyone else who skipped that step, and the key is free. Maintained by Upstash, MIT licensed, and the server costs nothing. Install it. The catch is coverage: Context7 can only serve what it has indexed, so a brand-new or obscure library leaves your agent guessing exactly like before.
Free, but run the ctx7 setup and take the free API key. Without one you share a rate limit with every anonymous user.
### Free Tier The MCP server and the ctx7 CLI are MIT licensed and free. The hosted documentation service is free to query, with a free API key available from the Context7 dashboard for higher rate limits. ### Self-Hosted Not the normal path. The value is Upstash's indexed and chunked documentation corpus, which is served from their infrastructure. You run only the local client or point your MCP client at the hosted endpoint. ### Paid No paid tier for the connector. Context7 lists an Enterprise option on its site for organizations that want their own private documentation indexed, priced on request.
Connects your AI coding agent directly to Figma designs. Instead of screenshots or manual descriptions, the model reads your actual design files, including layout structure, styles, and component hierarchies. It bridges the gap between design and implementation. You get read access to Figma files, frames, and components with structured context the model can act on. Requires a Figma access token. The MCP server is free, Figma itself requires a paid plan for most team usage. Maintained by the community (GLips). This is the go-to Figma integration for AI coding workflows. If you are translating Figma designs into code, this saves serious time. Worth installing.
Free and open source. The underlying service may have its own costs.
## Free Tier The MCP server itself is completely free and open source. ## Self-Hosted Runs locally or on your own infrastructure. ## Paid No paid tier. The underlying service may have its own pricing.
GitHub's official MCP server gives your AI assistant direct access to repos, issues, PRs, code search, and file operations. No scraping, no workarounds. You talk to your assistant, it talks to GitHub. Setup is one config block plus a personal access token. Maintained by GitHub themselves, so it stays current with API changes. Covers the operations you actually use daily: creating branches, reviewing diffs, searching code across repos, managing issues. The scope is broad enough that it replaces most of your tab-switching. Worth installing immediately if you use GitHub. This is the one MCP server that pays for itself on day one. The catch: it can only do what the GitHub API allows, so anything requiring the web UI (like editing Actions workflows visually) is still manual.
Free and open source. Requires a GitHub account (free tier works).
## Free Tier The MCP server itself is completely free and open source. ## Self-Hosted Runs locally or on your own infrastructure. ## Paid No paid tier. The underlying service may have its own pricing.
Bedrock AgentCore MCP connects your AI assistant to Amazon Bedrock's agent orchestration layer. Manage agents, invoke actions, and inspect agent configurations. Setup requires Bedrock access and AgentCore resources provisioned. Bedrock AgentCore pricing includes per-invocation and per-step charges. The MCP is free. AWS Labs maintains it. Useful for teams building multi-step AI agents on Bedrock who want to manage them from their editor instead of the console. The catch: AgentCore is relatively new. The API surface is still evolving, so expect breaking changes as the service matures.
Free and open source. The underlying service may have its own costs.
## Free Tier The MCP server itself is completely free and open source. ## Self-Hosted Runs locally or on your own infrastructure. ## Paid No paid tier. The underlying service may have its own pricing.
Connects your AI assistant to Amazon Neptune graph databases. The model can inspect schema, check cluster status, and run openCypher or Gremlin queries against your graph data. Graph databases are notoriously hard to query by hand, so letting AI help is a genuine productivity win. You get schema inspection, status monitoring, and query execution. Requires AWS credentials and a running Neptune cluster. The MCP server is free, but Neptune pricing starts around $0.10/hour for the smallest instance. Maintained by AWS Labs, the official open source arm of AWS. If you run Neptune and want AI-assisted graph exploration, this is the only game in town. Solid choice for existing Neptune users.
Free and open source. The underlying service may have its own costs.
## Free Tier The MCP server itself is completely free and open source. ## Self-Hosted Runs locally or on your own infrastructure. ## Paid No paid tier. The underlying service may have its own pricing.
Connects your AI assistant to Amazon Keyspaces, AWS's managed Cassandra-compatible database. Create tables, run CQL queries, and manage schemas through natural language instead of wrestling with the Cassandra CLI. Setup needs AWS credentials and a Keyspaces endpoint. If you already use Keyspaces, this slots right in. The MCP server is free. Keyspaces pricing is pay-per-use based on reads, writes, and storage, with a modest free tier. Maintained by AWS Labs. Useful if you're already running Keyspaces workloads. For everyone else, there are simpler database MCP servers to start with.
Free MCP server. Amazon Keyspaces uses pay-per-use pricing with a free tier.
## Free Tier The MCP server itself is completely free and open source. ## Self-Hosted Runs locally or on your own infrastructure. ## Paid No paid tier. The underlying service may have its own pricing.
Connects your AI assistant to Amazon Q Business in anonymous mode. The model can query your Q Business application without user authentication, making it useful for internal knowledge retrieval and document search across your organization's indexed content. You get Q Business chat and query capabilities in anonymous access mode. Requires AWS credentials and an existing Q Business application. The MCP server is free, Q Business pricing is usage-based starting at $3/user/month. Maintained by AWS Labs. Useful if your org already runs Q Business and you want to pipe its knowledge into your AI workflow. Niche but practical for existing AWS enterprise setups.
Free and open source. The underlying service may have its own costs.
## Free Tier The MCP server itself is completely free and open source. ## Self-Hosted Runs locally or on your own infrastructure. ## Paid No paid tier. The underlying service may have its own pricing.
Connects your AI assistant to Amazon Kendra, AWS's enterprise search service. Query indexed documents, get ranked results, and retrieve answers from your corporate knowledge base without leaving your editor. Setup requires an existing Kendra index and proper IAM credentials. Not trivial if you're starting from scratch, but straightforward if your org already runs Kendra. The MCP server is free. Kendra itself starts at $810/month for the developer edition, so this is firmly enterprise territory. Maintained by AWS Labs. Worth installing if your team already pays for Kendra. Skip it otherwise, the underlying service cost makes this a non-starter for solo developers.
Free MCP server. Amazon Kendra starts at $810/month for developer edition.
## Free Tier The MCP server itself is completely free and open source. ## Self-Hosted Runs locally or on your own infrastructure. ## Paid No paid tier. The underlying service may have its own pricing.
Connects your AI assistant to AWS IoT SiteWise, the service that ingests and organizes industrial sensor data. You can query asset models, pull real-time measurements, and browse your equipment hierarchy without leaving your editor. The MCP server is free and open source. IoT SiteWise itself bills per metric ingested and stored, so costs scale with your sensor fleet. Setup requires active SiteWise assets and proper IAM permissions, which puts this firmly in "you already know if you need it" territory. Maintained by AWS Labs. If you're running an industrial IoT stack on AWS and want to debug sensor data from your AI assistant, this is a clean integration. Everyone else can skip it.
Free and open source. The underlying AWS service may have its own costs.
## Free Tier The MCP server itself is completely free and open source. ## Self-Hosted Runs locally or on your own infrastructure. ## Paid No paid tier. The underlying AWS service may have its own pricing.
Connects your AI assistant to AWS SNS topics and SQS queues. The model can publish messages, manage subscriptions, send and receive queue messages, and inspect queue state. Useful for AI-driven event orchestration and message debugging. You get full SNS/SQS management: topic and queue CRUD, message publishing, subscription handling, and queue polling. Requires AWS credentials. The MCP server is free, SNS/SQS pricing is usage-based and extremely cheap for normal volumes. Maintained by AWS Labs. If you debug message flows or manage event-driven architectures on AWS, this gives your AI direct access to the plumbing. Practical for ops-heavy workflows.
Free and open source. The underlying service may have its own costs.
## Free Tier The MCP server itself is completely free and open source. ## Self-Hosted Runs locally or on your own infrastructure. ## Paid No paid tier. The underlying service may have its own pricing.
Valkey MCP connects your AI assistant to Amazon ElastiCache running Valkey, the open source Redis fork. Get, set, and inspect keys. Run commands against your cache cluster. Setup is your cluster endpoint plus AWS credentials. ElastiCache bills per node-hour. The MCP is free. AWS Labs maintains it as the successor to their Redis MCP. Practical for debugging cache state during development. Beats writing throwaway redis-cli scripts. The catch: Valkey is Redis-compatible but not Redis. Some Redis modules and extensions are not available yet.
Free and open source. The underlying service may have its own costs.
## Free Tier The MCP server itself is completely free and open source. ## Self-Hosted Runs locally or on your own infrastructure. ## Paid No paid tier. The underlying service may have its own pricing.
Connects your AI assistant to AWS Glue and Athena for data processing. The model can build ETL jobs, run SQL queries against S3 data, manage crawlers, and monitor pipeline execution. Turns your AI into a data engineering co-pilot. You get Glue job management, Athena query execution, crawler configuration, and pipeline monitoring. Requires AWS credentials. The MCP server is free, Glue and Athena charge based on compute time and data scanned. Maintained by AWS Labs. If your data stack runs on Glue and Athena, this is a significant productivity multiplier. Writing Glue jobs and Athena queries with AI assistance beats the console experience by a wide margin.
Free and open source. The underlying service may have its own costs.
## Free Tier The MCP server itself is completely free and open source. ## Self-Hosted Runs locally or on your own infrastructure. ## Paid No paid tier. The underlying service may have its own pricing.
Step Functions MCP lets your AI assistant start and inspect AWS Step Functions workflows. Trigger state machines, check execution status, and review outputs. Config is AWS credentials in your MCP setup. Step Functions bills per state transition. The free tier covers 4,000 transitions per month. The MCP itself is free. AWS Labs maintains it. Useful for teams with complex orchestration workflows who want to test and debug without the console. The catch: starting workflows from your AI assistant with no confirmation step is risky. Scope your IAM to non-production state machines.
Free and open source. The underlying service may have its own costs.
## Free Tier The MCP server itself is completely free and open source. ## Self-Hosted Runs locally or on your own infrastructure. ## Paid No paid tier. The underlying service may have its own pricing.
Connects your AI assistant to AWS AppSync GraphQL APIs. The model can manage schemas, resolvers, data sources, and run GraphQL operations. Useful for building and debugging AppSync backends without constantly switching between console tabs. You get full AppSync management: schema updates, resolver configuration, data source setup, and query execution. Requires AWS credentials. The MCP server is free, AppSync charges per query and per real-time connection. Maintained by AWS Labs. If AppSync is your GraphQL layer, this collapses a lot of console clicking into AI-assisted commands. Solid productivity boost for teams deep in the AppSync ecosystem.
Free and open source. The underlying service may have its own costs.
## Free Tier The MCP server itself is completely free and open source. ## Self-Hosted Runs locally or on your own infrastructure. ## Paid No paid tier. The underlying service may have its own pricing.
Connects your AI assistant to AWS CloudTrail, giving you access to API activity logs across your AWS account. You can search for specific API calls, investigate who changed a resource, and audit access patterns. Essential for security investigations and debugging "who did what." The MCP server is free and open source. CloudTrail's first management trail is free. Data event logging and CloudTrail Lake queries have per-event costs. Setup is standard AWS credentials with CloudTrail read permissions. Maintained by AWS Labs. Excellent for incident response and security audits. When something breaks in production and you need to know which API call caused it, asking your AI assistant beats scrolling through the CloudTrail console.
Free and open source. The underlying AWS service may have its own costs.
## Free Tier The MCP server itself is completely free and open source. ## Self-Hosted Runs locally or on your own infrastructure. ## Paid No paid tier. The underlying AWS service may have its own pricing.
Connects your AI assistant to Amazon ECS for container management. You can check service health, inspect task definitions, view running tasks, and troubleshoot deployment issues. Covers both Fargate and EC2 launch types. The MCP server is free and open source. ECS itself is free (you pay for underlying Fargate or EC2 compute). Setup requires AWS credentials with ECS permissions. Be cautious with write operations, stopping tasks or updating services in production needs careful IAM scoping. Maintained by AWS Labs. If you manage ECS services and spend time checking deployments or debugging task failures, this puts that workflow in your editor. The ability to inspect stopped task reasons conversationally is worth the setup alone.
Free and open source. The underlying AWS service may have its own costs.
## Free Tier The MCP server itself is completely free and open source. ## Self-Hosted Runs locally or on your own infrastructure. ## Paid No paid tier. The underlying AWS service may have its own pricing.
roda-mcp-server connects your AI assistant to the Registry of Open Data on AWS: 1,000+ public datasets covering climate, genomics, and satellite imagery, all hosted on S3. Ask it to find datasets by keyword, organization, or license, then preview the S3 folder structure or sample a file before downloading anything. Setup is a one-line uvx install, no AWS account needed for the open datasets. The MCP is free. Most datasets are open and public; some need AWS credentials and requester-pays billing, and a few controlled-access sets require extra approval. AWS Labs maintains it directly. Worth installing if your work touches public research data and you would rather search it from your AI assistant than dig through S3 by hand.
Free and open source. The underlying service may have its own costs.
**Free (only option):** The MCP server itself is completely free. AWS Labs maintains it directly. **Datasets:** Most of RODA's 1,000+ datasets are open and public, no AWS account needed. Some require AWS credentials and requester-pays billing on the S3 side. A handful of controlled-access sets (mostly health data) need extra approval steps. **Paid:** None. This is purely a discovery and preview layer on top of a free public registry.
Connects your AI assistant to Amazon Q Index for enterprise search. The model can retrieve and search across documents indexed by Q Business, pulling structured results from your organization's knowledge base. You get document retrieval and search against your Q Index data sources. Requires AWS credentials and an existing Q Business index. The MCP server is free, underlying Q Business pricing applies. Maintained by AWS Labs. This is the retrieval-focused counterpart to the Q Business chat server. If you need your AI to search enterprise documents rather than chat with them, this is the right tool. Very specific to AWS enterprise stacks.
Free and open source. The underlying service may have its own costs.
## Free Tier The MCP server itself is completely free and open source. ## Self-Hosted Runs locally or on your own infrastructure. ## Paid No paid tier. The underlying service may have its own pricing.
Memcached MCP connects your AI assistant to Amazon ElastiCache Memcached clusters. Get, set, and inspect cache keys directly from your editor. Config is your cluster endpoint plus AWS credentials. ElastiCache bills per node-hour. The MCP is free. AWS Labs maintains it alongside the rest of their MCP suite. Useful for debugging cache issues without writing throwaway scripts. The catch: Memcached is simpler than Redis but also less capable. If you are already on Valkey or Redis, this is not the server you want.
Free and open source. The underlying service may have its own costs.
## Free Tier The MCP server itself is completely free and open source. ## Self-Hosted Runs locally or on your own infrastructure. ## Paid No paid tier. The underlying service may have its own pricing.
MySQL MCP connects your AI assistant to Aurora MySQL databases. Run queries, inspect schemas, and explore data without leaving your editor. Point it at your connection string and you are set. Aurora MySQL pricing is usage-based. The MCP adds zero cost. Maintained by AWS Labs with read-only defaults for safety. Solid for schema exploration and quick queries during development. The catch: it is tuned for Aurora MySQL specifically. Vanilla MySQL works but is not the primary target, so some Aurora-specific features may not translate.
Free and open source. The underlying service may have its own costs.
## Free Tier The MCP server itself is completely free and open source. ## Self-Hosted Runs locally or on your own infrastructure. ## Paid No paid tier. The underlying service may have its own pricing.
OpenAPI MCP takes any OpenAPI spec and turns it into callable MCP tools automatically. Point it at a spec file or URL and your AI assistant can call every endpoint. No hand-written tool definitions needed. Completely free. The underlying APIs you call may have their own costs, but the MCP itself is just a translation layer. AWS Labs maintains it. This is one of the most versatile servers in the AWS MCP suite. Any API with an OpenAPI spec becomes an AI tool instantly. The catch: auto-generated tools can be noisy. Large specs produce dozens of tools, and your AI assistant may struggle to pick the right one.
Free and open source. The underlying service may have its own costs.
## Free Tier The MCP server itself is completely free and open source. ## Self-Hosted Runs locally or on your own infrastructure. ## Paid No paid tier. The underlying service may have its own pricing.
Connects your AI assistant to the AWS Pricing API so you can look up on-demand pricing for any AWS service. Ask about EC2 instance costs, compare RDS pricing across regions, or estimate what a Lambda workload will run you. The MCP server is free and open source. The Pricing API itself is free to call. Setup is minimal, just AWS credentials. This is one of the simplest MCP servers in the AWS Labs collection. Maintained by AWS Labs. Genuinely useful for anyone building on AWS who regularly checks pricing. Beats opening the pricing calculator in a browser tab. Quick to install, no ongoing maintenance.
Free and open source. The underlying AWS service may have its own costs.
## Free Tier The MCP server itself is completely free and open source. ## Self-Hosted Runs locally or on your own infrastructure. ## Paid No paid tier. The underlying AWS service may have its own pricing.
Connects your AI assistant to AWS Location Service for maps, geocoding, route calculation, and place search. You can convert addresses to coordinates, calculate driving distances, and search for nearby points of interest directly from your editor. The MCP server is free and open source. AWS Location Service has a generous free tier (up to 100K geocoding requests/month), then pay-per-request pricing after that. Setup is straightforward if you already have AWS credentials configured. Maintained by AWS Labs. Solid choice if you're building location-aware features on AWS and want to prototype geocoding or routing queries conversationally. If you're using Google Maps or Mapbox already, this won't pull you over.
Free and open source. The underlying AWS service may have its own costs.
## Free Tier The MCP server itself is completely free and open source. ## Self-Hosted Runs locally or on your own infrastructure. ## Paid No paid tier. The underlying AWS service may have its own pricing.
Connects your AI assistant to AWS HealthOmics for genomics and bioinformatics workflows. The model can manage reference stores, sequence stores, annotation stores, and run genomics workflows. Highly specialized for life sciences teams. You get workflow management, data store operations, and run monitoring across HealthOmics services. Requires AWS credentials with HealthOmics permissions. The MCP server is free, HealthOmics pricing is usage-based. Maintained by AWS Labs. This is extremely niche. If you are doing genomics work on AWS, it is a welcome addition. For everyone else, it is irrelevant. Know your audience before installing.
Free and open source. The underlying service may have its own costs.
## Free Tier The MCP server itself is completely free and open source. ## Self-Hosted Runs locally or on your own infrastructure. ## Paid No paid tier. The underlying service may have its own pricing.
Connects your AI assistant to Amazon Bedrock Knowledge Bases for retrieval-augmented generation. You can query your indexed documents, get relevant passages with source citations, and use your company's knowledge base directly in conversation. The MCP server is free and open source. Bedrock Knowledge Bases charges for the underlying embedding model, vector store (OpenSearch Serverless or Aurora), and retrieval queries. Costs vary widely based on corpus size. Setup requires an existing Knowledge Base ID and proper IAM permissions. Maintained by AWS Labs. If you've already invested in Bedrock Knowledge Bases, this is the natural way to wire them into your AI workflow. Not useful until you have a knowledge base configured and populated.
Free and open source. The underlying AWS service may have its own costs.
## Free Tier The MCP server itself is completely free and open source. ## Self-Hosted Runs locally or on your own infrastructure. ## Paid No paid tier. The underlying AWS service may have its own pricing.
Connects your AI assistant to AWS VPC networking. You can inspect VPCs, subnets, security groups, route tables, and network ACLs. Useful for debugging connectivity issues or auditing your network configuration without clicking through the console. The MCP server is free and open source. VPC resources themselves have no hourly cost (NAT Gateways and some endpoints do). Setup just requires AWS credentials with the right IAM permissions, which most AWS developers already have configured. Maintained by AWS Labs. If you spend time troubleshooting security group rules or tracing packet paths through your VPC, having this in your AI assistant is genuinely useful. Pure read operations, low risk.
Free and open source. The underlying AWS service may have its own costs.
## Free Tier The MCP server itself is completely free and open source. ## Self-Hosted Runs locally or on your own infrastructure. ## Paid No paid tier. The underlying AWS service may have its own pricing.
This is the documentation site for the AWS Labs MCP project, built with Docusaurus. It is not a connector to anything. It is a reference site for the other MCP servers in the suite. Completely free. No underlying service costs. AWS Labs maintains it alongside the rest of their MCP servers. Not something you install as an MCP server. It is documentation. The catch: this gets indexed as a "tool" because it lives in the monorepo, but it is just a docs site. No AI integration here.
Free and open source. The underlying service may have its own costs.
## Free Tier The MCP server itself is completely free and open source. ## Self-Hosted Runs locally or on your own infrastructure. ## Paid No paid tier. The underlying service may have its own pricing.
Connects your AI assistant to Amazon DocumentDB, the MongoDB-compatible document database. You can query collections, inspect indexes, run aggregation pipelines, and browse your data model without switching to a MongoDB client. The MCP server is free and open source. DocumentDB instances start around $0.08/hour for the smallest size. The server needs a connection string to your DocumentDB cluster, which typically requires VPC access or a bastion host, adding setup complexity. Maintained by AWS Labs. If you're running DocumentDB and want to explore or debug your data from your editor, this works well. The VPC networking requirement means setup is not as quick as other MCP servers in this collection.
Free and open source. The underlying AWS service may have its own costs.
## Free Tier The MCP server itself is completely free and open source. ## Self-Hosted Runs locally or on your own infrastructure. ## Paid No paid tier. The underlying AWS service may have its own pricing.
Connects your AI assistant to Aurora DSQL, Amazon's distributed SQL database. The model can run queries, inspect schemas, and explore data across a globally distributed relational database. You get SQL query execution and schema inspection against Aurora DSQL clusters. Requires AWS credentials and a running DSQL cluster. The MCP server is free, Aurora DSQL pricing is based on compute and I/O usage. Maintained by AWS Labs. Aurora DSQL is still relatively new, so this server is early-stage but functional. If you are building on DSQL and want AI-assisted database work, it is currently the only option. Worth installing for DSQL users.
Free and open source. The underlying service may have its own costs.
## Free Tier The MCP server itself is completely free and open source. ## Self-Hosted Runs locally or on your own infrastructure. ## Paid No paid tier. The underlying service may have its own pricing.
Timestream InfluxDB MCP connects your AI assistant to Amazon Timestream for InfluxDB, AWS's managed time-series database. Query metrics, inspect databases, and explore time-series data. Config is your InfluxDB endpoint plus AWS credentials. Timestream for InfluxDB bills on instance size and storage. The MCP is free. AWS Labs maintains it. Good fit for IoT or monitoring teams already on this service. The catch: Timestream for InfluxDB is a niche AWS offering. If you are using standalone InfluxDB or Prometheus, this is not the right connector.
Free and open source. The underlying service may have its own costs.
## Free Tier The MCP server itself is completely free and open source. ## Self-Hosted Runs locally or on your own infrastructure. ## Paid No paid tier. The underlying service may have its own pricing.
Connects your Chrome browser to AI assistants via MCP. Claude can take screenshots, fill forms, manage bookmarks, and search across your open tabs using a local vector database. Twenty-plus tools, all running locally. No data leaves your machine. Install the Chrome extension and the bridge package, configure your MCP client, and your AI can see what you see. Setup takes about 10 minutes. Maintained by hangwin (community). Free, MIT licensed, no API keys or subscriptions. If you want your AI assistant to actually interact with your browser, this is the one to install.
Free and open source. The underlying service may have its own costs.
## Free Tier The MCP server itself is completely free and open source. Install it, configure your MCP client, and use it without any cost. ## Self-Hosted Runs locally or on your own infrastructure. No external dependencies beyond the service it connects to. ## Paid No paid tier. The MCP server is free. The underlying service may have its own pricing.