SkillAgentSearch skills...

awesome-mcp-servers

A curated list of MCP (Model Context Protocol) servers, tools, frameworks, and resources

Install / Use

claude mcp add Sagargupta16 -- npx -y github:Sagargupta16/awesome-mcp-servers

If the server publishes to npm under a different name, use that package instead — check the repo README.

About this skill
🔌

MCP Server

Model Context Protocol server

Quality Score

71/100

Supported Platforms

Claude Code
Claude Desktop

Tags

Our assessment of awesome-mcp-servers

awesome-mcp-servers scores 71/100 on our quality scale, 873rd of 952 AI & Machine Learning skills we index.

Its MCP Server is 61 KB long, well organised into 33 sections with 3 code examples: long enough that it reads more like full documentation than a focused instruction file, which agents can find harder to follow.

It has 10 GitHub stars, so there is little community track record yet; judge it on its content.

Substance
21/30
Structure
18/20
Description
12/15
Adoption
4/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated today, so awesome-mcp-servers is actively maintained.
  • It is released under the CC0-1.0 license, a permissive license that allows use, modification and commercial use with attribution.
  • Its trust signals score 92/100, with 1 caution from licensing, adoption, age or documentation. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

Safety scan

No issues found

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands.

Automated pattern scan on 2026-10-20. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.

awesome-mcp-servers compared with similar skills

All 4 of these similar skills score higher than awesome-mcp-servers; compare them before choosing.

SkillScoreStarsUpdatedFormat
awesome-mcp-servers (this skill)by Sagargupta167110todayMCP Server
claude-memby thedotmack100101.8ktodayCLAUDE.md
Agent-Reachby Panniantong10099.8k4d agoCLAUDE.md
Understand-Anythingby Egonex-AI10087.1k7d agoCLAUDE.md
headroomby headroomlabs-ai10076.3ktodayCLAUDE.md

Frequently asked questions

How do I install awesome-mcp-servers?
Run claude mcp add Sagargupta16 -- npx -y github:Sagargupta16/awesome-mcp-servers. The install tabs above show the steps for each supported agent.
Which AI agents does awesome-mcp-servers work with?
It is written for Claude Code and Claude Desktop, as a MCP Server file. Other agents that read the same format can often use it too.
Is awesome-mcp-servers safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. It is CC0-1.0-licensed and scores 92/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is awesome-mcp-servers still maintained?
The repository was last updated today, so awesome-mcp-servers is actively maintained.

Awesome MCP Servers

Awesome Lint License: CC0-1.0

A curated list of Model Context Protocol (MCP) servers, tools, frameworks, and resources.

Browse it as a searchable site: sagargupta.online/awesome-mcp-servers, with search, category and language filters, and live stars. It is rebuilt from this README every hour.

MCP is an open protocol that lets AI assistants (Claude, GPT, Cursor, Windsurf, etc.) connect to local and remote data sources through standardized server implementations.

This list is curated, not exhaustive, and open to anyone. Bigger MCP lists exist. The point of this one is that everything on it has been checked. Curated does not mean famous: your project needs no minimum star count or age, and submitting your own server is welcome. Every entry:

  • implements MCP for real -- not a README with a server.json next to it
  • states an open-source licence -- a LICENSE file, or a licence field in its package manifest
  • was pushed within the last 180 days, and is not archived
  • documents how to install and configure it, so someone else can actually run it
  • appears exactly once, in one category

Hosted servers with no public source are the one exception, marked Remote. Instead of a licence and a push date, each links the operator's own documentation naming the endpoint, the authentication and the tools; CI checks the endpoint answers; and, like every entry, it merges itself only once its author has starred the repository.

Those rules are enforced by CI, not by good intentions: a pull request that breaks the format, adds a dead link, or submits an unlicensed repo fails its checks. A monthly audit re-checks every listed repository and files what has rotted.

An MCP server runs as a trusted extension of your assistant, with your files and your credentials. Read the source before you configure one -- a place on this list is a filter, not an audit. See SECURITY.md.

Using a server from this list

Two shapes cover the list. A stdio server is one your client starts itself and talks to over stdin and stdout. A remote server is hosted by the vendor, so the client needs only the endpoint; those rows carry Remote in the Language column.

Two stdio servers, run straight from their published packages:

{
  "mcpServers": {
    "filesystem": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-filesystem", "/path/to/allowed/dir"]
    },
    "fetch": {
      "command": "uvx",
      "args": ["mcp-server-fetch"]
    }
  }
}

A remote server. type is not optional here: an entry with a url and no type is read as a stdio server and skipped by Claude Code, which reports that the server has a url but no type.

{
  "mcpServers": {
    "example": {
      "type": "http",
      "url": "https://mcp.example.com/mcp"
    }
  }
}

Where that JSON lives, and which extra keys it takes, differs per client -- check your own client's docs. The protocol's guide to connecting a local server walks through the stdio case, and each server's README lists the arguments, tokens and environment variables it expects.

Contents


Official

Servers

Data & Databases

| Server | Description | Language | |--------|-------------|----------| | Apache Doris MCP | Official Apache Doris analytics database queries and management | Python | | BigQuery MCP | Query Google BigQuery datasets and tables | TypeScript | | ClickHouse MCP | Official ClickHouse columnar analytics | Python | | Confluent MCP | Official Confluent Cloud Kafka topics, connectors and Flink | TypeScript | | Couchbase MCP | Official Couchbase and Capella cluster, scope and query access | Python | | DBHub | Universal database server for Postgres, MySQL, SQL Server, MariaDB, SQLite | TypeScript | | dbt MCP | Official dbt Labs server for dbt projects | Python | | DC Hub | Daily grid-power scores (DCPI) for data-center site selection in 300+ markets | JavaScript | | Elasticsearch MCP | Official Elasticsearch query interface | Rust | | GCP MCP Toolbox | Official Google DB toolbox (Postgres, MySQL, Spanner) | Go | | Invokely MCP Connector | Local stdio adapter for Invokely's hosted official statistics MCP service | JavaScript | | MCP Alchemy | SQLAlchemy-backed access to SQLite, Postgres, MySQL, Oracle and MS-SQL | Python | | Memgraph MCP | Official Memgraph graph database Cypher queries and schema | Python | | Milvus MCP | Official Milvus vector database search and collection management | Python | | MongoDB MCP | Official MongoDB and Atlas cluster management | TypeScript | | MotherDuck / DuckDB MCP | Local DuckDB and MotherDuck cloud access | Python | | MySQL MCP | MySQL database queries and management | TypeScript | | Neo4j MCP | Neo4j Labs Cypher, memory and Aura API graph database servers | Python | | Neon MCP | Neon serverless Postgres branching and management | TypeScript | | Pinecone MCP | Official Pinecone vector database | TypeScript | | PostgreSQL MCP (Pro) | Query, analyze and optimize PostgreSQL databases | Python | | Qdrant MCP | Official Qdrant vector database server | Python | | Redis MCP | Official Redis cache and data structures | Python | | Scout Packs | Pay-per-call B2B data: lead lookup, domain intel and email checks | Python | | Snowflake MCP | Official Snowflake Cortex AI + SQL orchestration | Python | | StarRocks MCP | Official StarRocks OLAP database query and schema access | Python | | Supabase MCP | Supabase database, auth, and storage | TypeScript | | Upstash MCP | Upstash Redis and Vector databases | TypeScript | | YunCMS | Inspect CMS schema and read or write collection data with YunCMS RBAC | JavaScript |

Developer Tools

| Server | Description | Language | |--------|-------------|----------| | Agentlas OS | Portable agent teams and cross-host orchestration over MCP | Python | | Apollo MCP Server | Official Apollo server exposing GraphQL operations as MCP tools | Rust | | Archcore | Spec-driven development and context engineering for AI coding agents | Go | | Argo CD MCP | Argo CD applications, syncs and GitOps state (argoproj-labs) | TypeScript | | ast-grep MCP | Structural code search and rewrite via ast-grep patterns | Python | | Atlassian MCP (Jira + Confluence) | Jira and Confluence integration | Python | | Azure DevOps MCP | Official Azure DevOps repos, pipelines, work items and wikis | TypeScript | | Buildkite MCP | Official Buildkite pipelines, builds, jobs and test runs | Go | | Chrome DevTools MCP | Official Chrome DevTools for coding agents - debug, trace and inspect pages | TypeScript | | CircleCI MCP | Official CircleCI workflow integration | TypeScript | | Codapult Guard | Architecture guardrails for AI coding agents | TypeScript | | Codebase Memory MCP | Code intelligence server that indexes repos into a queryable knowledge graph | C | | Dedicated Mac Mini AI Bot Setup MCP | Read-only lookup of a Mac mini AI bot setup service: its offer and queue | JavaScript | | [Desktop Commander MCP](https://github.com/wond

Truncated for display — read the full file on GitHub.

Related Skills

View on GitHub
GitHub Stars10
CategoryAI
Updated2h ago
Forks77

Languages

Python

Trust signals

92/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

1 low1 info