From edf89cb3d396145a3d241548bf88e8209a8aeb5c Mon Sep 17 00:00:00 2001 From: Kendall Miller Date: Tue, 2 Sep 2025 09:22:20 -0600 Subject: [PATCH 1/9] Add the Maybe Don't AI Policy Engine to the list of MCP Servers --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index ae90632c..3e43f65d 100644 --- a/README.md +++ b/README.md @@ -862,6 +862,7 @@ A growing set of community-developed and maintained servers demonstrates various - **[Matlab-MCP-Tools](https://github.com/neuromechanist/matlab-mcp-tools)** - An MCP to write and execute MATLAB scripts, maintain workspace context between MCP calls, visualize plots, and perform section-by-section analysis of MATLAB code with full access to MATLAB's computational capabilities. - **[Maton](https://github.com/maton-ai/agent-toolkit/tree/main/modelcontextprotocol)** - Connect to your SaaS tools like HubSpot, Salesforce, and more. - **[Maven Tools MCP](https://github.com/arvindand/maven-tools-mcp)** - Maven Central dependency intelligence for JVM build tools. Supports all build tools (Maven, Gradle, SBT, Mill) with Context7 integration for documentation support. +- **[Maybe Don't AI Policy Engine](https://www.maybedont.ai/download/)** - Yet another MCP security gateway, Maybe Don't AI provides policy checks on any call before it reaches downstream MCP servers to protect users from agents behaving poorly. - **[MCP-Airflow-API](https://github.com/call518/MCP-Airflow-API)** - Model Context Protocol (MCP) server for Apache Airflow API integration. Provides comprehensive tools for managing Airflow clusters including service operations, configuration management, status monitoring, and request tracking. - **[MCP Compass](https://github.com/liuyoshio/mcp-compass)** - Suggest the right MCP server for your needs - **[MCP Create](https://github.com/tesla0225/mcp-create)** - A dynamic MCP server management service that creates, runs, and manages Model Context Protocol servers on-the-fly. From 521d4454728f55d9a4d5658f472d60bd91015637 Mon Sep 17 00:00:00 2001 From: Algis Dumbris Date: Tue, 9 Sep 2025 16:47:02 +0300 Subject: [PATCH 2/9] Add MCPProxy server to catalog - Added MCPProxy entry in correct alphabetical position (between Multiplayer and NanoVMs) - Open-source local app enabling access to multiple MCP servers and thousands of tools - Features intelligent discovery via MCP protocol and quarantine protection - Runs servers in isolated environments for enhanced security --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index eb7aedf4..88cf3004 100644 --- a/README.md +++ b/README.md @@ -293,6 +293,7 @@ Official integrations are maintained by companies building production ready MCP - MotherDuck Logo **[MotherDuck](https://github.com/motherduckdb/mcp-server-motherduck)** - Query and analyze data with MotherDuck and local DuckDB - Mulesoft Logo **[Mulesoft](https://www.npmjs.com/package/@mulesoft/mcp-server)** - Build, deploy, and manage MuleSoft applications with natural language, directly inside any compatible IDE. - Multiplayer Logo **[Multiplayer](https://www.multiplayer.app/docs/ai/mcp-server)** - Analyze your full stack session recordings easily. Record a bug with Multiplayer, analyze and fix it with LLM +- MCPProxy Logo **[MCPProxy](https://github.com/smart-mcp-proxy/mcpproxy-go)** - Open-source local app that enables access to multiple MCP servers and thousands of tools with intelligent discovery via MCP protocol, runs servers in isolated environments, and features automatic quarantine protection against malicious tools. - NanoVMs Logo **[NanoVMs](https://github.com/nanovms/ops-mcp)** - Easily Build and Deploy unikernels to any cloud. - Needle AI Logo **[Needle](https://github.com/needle-ai/needle-mcp)** - Production-ready RAG out of the box to search and retrieve data from your own documents. - Neo4j Logo **[Neo4j](https://github.com/neo4j-contrib/mcp-neo4j/)** - Neo4j graph database server (schema + read/write-cypher) and separate graph database backed memory From 2769fae31d775ad8ff73aa16324567c43c509738 Mon Sep 17 00:00:00 2001 From: Algis Dumbris Date: Tue, 23 Sep 2025 08:34:32 +0300 Subject: [PATCH 3/9] Move MCPProxy from servers to Resources section Address review feedback by moving MCPProxy to the Resources section as it's more of an application for managing MCP servers rather than a specific MCP server implementation. Maintained alphabetical order in the Resources section. --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 34ff639d..0ada8f62 100644 --- a/README.md +++ b/README.md @@ -300,7 +300,6 @@ Official integrations are maintained by companies building production ready MCP - MotherDuck Logo **[MotherDuck](https://github.com/motherduckdb/mcp-server-motherduck)** - Query and analyze data with MotherDuck and local DuckDB - Mulesoft Logo **[Mulesoft](https://www.npmjs.com/package/@mulesoft/mcp-server)** - Build, deploy, and manage MuleSoft applications with natural language, directly inside any compatible IDE. - Multiplayer Logo **[Multiplayer](https://www.multiplayer.app/docs/ai/mcp-server)** - Analyze your full stack session recordings easily. Record a bug with Multiplayer, analyze and fix it with LLM -- MCPProxy Logo **[MCPProxy](https://github.com/smart-mcp-proxy/mcpproxy-go)** - Open-source local app that enables access to multiple MCP servers and thousands of tools with intelligent discovery via MCP protocol, runs servers in isolated environments, and features automatic quarantine protection against malicious tools. - Nango Logo **[Nango](https://docs.nango.dev/guides/use-cases/mcp-server)** - Integrate your AI agent with 500+ APIs: Auth, custom tools, and observability. Open-source. - NanoVMs Logo **[NanoVMs](https://github.com/nanovms/ops-mcp)** - Easily Build and Deploy unikernels to any cloud. - Needle AI Logo **[Needle](https://github.com/needle-ai/needle-mcp)** - Production-ready RAG out of the box to search and retrieve data from your own documents. @@ -1330,6 +1329,7 @@ Additional resources on MCP. - **[Discord Server (ModelContextProtocol)](https://discord.gg/jHEGxQu2a5)** – Connect with developers, share insights, and collaborate on projects in an active Discord community dedicated to the Model Context Protocol by **[Alex Andru](https://github.com/QuantGeekDev)** - Klavis Logo **[Klavis AI](https://www.klavis.ai)** - Open Source MCP Infra. Hosted MCP servers and MCP clients on Slack and Discord. - **[MCP Badges](https://github.com/mcpx-dev/mcp-badges)** – Quickly highlight your MCP project with clear, eye-catching badges, by **[Ironben](https://github.com/nanbingxyz)** +- MCPProxy Logo **[MCPProxy](https://github.com/smart-mcp-proxy/mcpproxy-go)** - Open-source local app that enables access to multiple MCP servers and thousands of tools with intelligent discovery via MCP protocol, runs servers in isolated environments, and features automatic quarantine protection against malicious tools. - **[MCPRepository.com](https://mcprepository.com/)** - A repository that indexes and organizes all MCP servers for easy discovery. - **[mcp-cli](https://github.com/wong2/mcp-cli)** - A CLI inspector for the Model Context Protocol by **[wong2](https://github.com/wong2)** - **[mcp-dockmaster](https://mcp-dockmaster.com)** - An Open-Sourced UI to install and manage MCP servers for Windows, Linux and macOS. From befbacdb79723d427f674975379e35f2fe04e2d9 Mon Sep 17 00:00:00 2001 From: Zihao Lin Date: Tue, 23 Sep 2025 13:20:54 -0700 Subject: [PATCH 4/9] add Strata MCP Server to readme --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index 3b271258..350060b5 100644 --- a/README.md +++ b/README.md @@ -417,6 +417,7 @@ Official integrations are maintained by companies building production ready MCP - Steadybit Logo **[Steadybit](https://github.com/steadybit/mcp)** - Interact with [Steadybit](https://www.steadybit.com/) - Steuerboard Logo **[Steuerboard](https://github.com/steuerboard/steuerboard-mcp-typescript)** - Interact with the accounting data in your business using our official MCP server - Storybook Logo **[Storybook](https://github.com/storybookjs/addon-mcp)** - Interact with [Storybook](https://storybook.js.org/) to automate UI component testing and documentation +- Strata Logo **[Strata](https://www.klavis.ai/)** - One MCP server that guides your AI agents through thousands of tools in multiple apps progressively. It eliminates context overload and ensures accurate tool selection, enabling agents to handle complex, multi-app workflows with ease. - Stripe Logo **[Stripe](https://github.com/stripe/agent-toolkit)** - Interact with Stripe API - Sunra AI Logo **[Sunra AI](https://github.com/sunra-ai/sunra-clients/tree/main/mcp-server)** - Search for and run AI models on [Sunra.ai](https://sunra.ai). Discover models, create video, image, and 3D model content, track their status, and manage the generated media. - Supabase Logo **[Supabase](https://github.com/supabase-community/supabase-mcp)** - Interact with Supabase: Create tables, query data, deploy edge functions, and more. From a753cd6f3a64372b806b17aa40dbba97a0fbcc1c Mon Sep 17 00:00:00 2001 From: evalstate <1936278+evalstate@users.noreply.github.com> Date: Sun, 28 Sep 2025 17:40:11 +0100 Subject: [PATCH 5/9] fix sampling and elicitation calls for streamable http --- src/everything/everything.ts | 45 +++++++++++++++++++++++++----------- 1 file changed, 31 insertions(+), 14 deletions(-) diff --git a/src/everything/everything.ts b/src/everything/everything.ts index e8b2f672..e059b8be 100644 --- a/src/everything/everything.ts +++ b/src/everything/everything.ts @@ -1,10 +1,13 @@ import { Server } from "@modelcontextprotocol/sdk/server/index.js"; +import type { RequestHandlerExtra } from "@modelcontextprotocol/sdk/shared/protocol.js"; import { CallToolRequestSchema, ClientCapabilities, CompleteRequestSchema, CreateMessageRequest, CreateMessageResultSchema, + ElicitRequest, + ElicitResultSchema, GetPromptRequestSchema, ListPromptsRequestSchema, ListResourcesRequestSchema, @@ -14,6 +17,8 @@ import { ReadResourceRequestSchema, Resource, RootsListChangedNotificationSchema, + ServerNotification, + ServerRequest, SubscribeRequestSchema, Tool, ToolSchema, @@ -36,6 +41,8 @@ type ToolInput = z.infer; const ToolOutputSchema = ToolSchema.shape.outputSchema; type ToolOutput = z.infer; +type SendRequest = RequestHandlerExtra["sendRequest"]; + /* Input schemas for tools implemented in this server */ const EchoSchema = z.object({ message: z.string().describe("Message to echo"), @@ -220,7 +227,8 @@ export const createServer = () => { const requestSampling = async ( context: string, uri: string, - maxTokens: number = 100 + maxTokens: number = 100, + sendRequest: SendRequest ) => { const request: CreateMessageRequest = { method: "sampling/createMessage", @@ -241,22 +249,24 @@ export const createServer = () => { }, }; - return await server.request(request, CreateMessageResultSchema); + return await sendRequest(request, CreateMessageResultSchema); + }; const requestElicitation = async ( message: string, - requestedSchema: any + requestedSchema: any, + sendRequest: SendRequest ) => { - const request = { + const request: ElicitRequest = { method: 'elicitation/create', params: { message, - requestedSchema - } + requestedSchema, + }, }; - return await server.request(request, z.any()); + return await sendRequest(request, ElicitResultSchema); }; const ALL_RESOURCES: Resource[] = Array.from({ length: 100 }, (_, i) => { @@ -334,12 +344,12 @@ export const createServer = () => { throw new Error(`Unknown resource: ${uri}`); }); - server.setRequestHandler(SubscribeRequestSchema, async (request) => { + server.setRequestHandler(SubscribeRequestSchema, async (request, extra) => { const { uri } = request.params; subscriptions.add(uri); // Request sampling from client when someone subscribes - await requestSampling("A new subscription was started", uri); + await requestSampling("A new subscription was started", uri, undefined, extra.sendRequest); return {}; }); @@ -615,7 +625,8 @@ export const createServer = () => { const result = await requestSampling( prompt, ToolName.SAMPLE_LLM, - maxTokens + maxTokens, + extra.sendRequest ); return { content: [ @@ -734,14 +745,20 @@ export const createServer = () => { type: 'object', properties: { color: { type: 'string', description: 'Favorite color' }, - number: { type: 'integer', description: 'Favorite number', minimum: 1, maximum: 100 }, + number: { + type: 'integer', + description: 'Favorite number', + minimum: 1, + maximum: 100, + }, pets: { type: 'string', enum: ['cats', 'dogs', 'birds', 'fish', 'reptiles'], - description: 'Favorite pets' + description: 'Favorite pets', }, - } - } + }, + }, + extra.sendRequest ); // Handle different response actions From 2550353d83ae5de8d25faddaf676757c3bfa586c Mon Sep 17 00:00:00 2001 From: mikeschecht <127637146+mikeschecht@users.noreply.github.com> Date: Mon, 29 Sep 2025 05:02:17 -0700 Subject: [PATCH 6/9] Added AX-Platform to the list of Community Servers. (#2723) * Added AX-Platform to the list of Community Servers. [AX-Platform](https://github.com/AX-MCP/PaxAI)** - AI Agent collaboration platform. Collaborate on tasks, share context, and coordinate workflows. * Update README.md --------- Co-authored-by: michaelschecht Co-authored-by: adam jones --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index 151f0eb0..70d68cab 100644 --- a/README.md +++ b/README.md @@ -533,6 +533,7 @@ A growing set of community-developed and maintained servers demonstrates various - **[Attestable MCP](https://github.com/co-browser/attestable-mcp-server)** - An MCP server running inside a trusted execution environment (TEE) via Gramine, showcasing remote attestation using [RA-TLS](https://gramine.readthedocs.io/en/stable/attestation.html). This allows an MCP client to verify the server before connecting. - **[Audius](https://github.com/glassBead-tc/audius-mcp-atris)** - Audius + AI = Atris. Interact with fans, stream music, tip your favorite artists, and more on Audius: all through Claude. - **[AutoML](https://github.com/emircansoftware/MCP_Server_DataScience)** – An MCP server for data analysis workflows including reading, preprocessing, feature engineering, model selection, visualization, and hyperparameter tuning. +- **[AX-Platform](https://github.com/AX-MCP/PaxAI?tab=readme-ov-file#mcp-setup-guides)** - AI Agent collaboration platform. Collaborate on tasks, share context, and coordinate workflows. - **[AWS](https://github.com/rishikavikondala/mcp-server-aws)** - Perform operations on your AWS resources using an LLM. - **[AWS Athena](https://github.com/lishenxydlgzs/aws-athena-mcp)** - An MCP server for AWS Athena to run SQL queries on Glue Catalog. - **[AWS Cognito](https://github.com/gitCarrot/mcp-server-aws-cognito)** - An MCP server that connects to AWS Cognito for authentication and user management. From dad51a26ed7ea6e39e8100cdb4e037a0e14fc8c7 Mon Sep 17 00:00:00 2001 From: Jason Summer <58369680+jasonsum@users.noreply.github.com> Date: Mon, 29 Sep 2025 07:02:39 -0500 Subject: [PATCH 7/9] Add Snowflake-Labs mcp server (#2724) * Add Snowflake-Labs MCP server to community server * Shorten description --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index 70d68cab..b62f1813 100644 --- a/README.md +++ b/README.md @@ -1146,6 +1146,7 @@ A growing set of community-developed and maintained servers demonstrates various - **[Slack](https://github.com/zencoderai/slack-mcp-server)** - Slack MCP server which supports both stdio and Streamable HTTP transports. Extended from the original Anthropic's implementation which is now [archived](https://github.com/modelcontextprotocol/servers-archived/tree/main/src/slack) - **[Slidespeak](https://github.com/SlideSpeak/slidespeak-mcp)** - Create PowerPoint presentations using the [Slidespeak](https://slidespeak.com/) API. - **[Smartlead](https://github.com/jean-technologies/smartlead-mcp-server-local)** - MCP to connect to Smartlead. Additional, tooling, functionality, and connection to workflow automation platforms also available. +- **[Snowflake](https://github.com/Snowflake-Labs/mcp)** - Open-source MCP server for Snowflake from official Snowflake-Labs supports prompting Cortex Agents, querying structured & unstructured data, object management, SQL execution, semantic view querying, and more. RBAC, fine-grained CRUD controls, and all authentication methods supported. - **[Snowflake](https://github.com/isaacwasserman/mcp-snowflake-server)** - This MCP server enables LLMs to interact with Snowflake databases, allowing for secure and controlled data operations. - **[Snowflake Cortex MCP Server](https://github.com/thisisbhanuj/Snowflake-Cortex-MCP-Server)** -This Snowflake MCP server provides tooling for Snowflake Cortex AI features, bringing these capabilities to the MCP ecosystem. When connected to an MCP Client (e.g. Claude for Desktop, fast-agent, Agentic Orchestration Framework), users can leverage these Cortex AI features. - **[SoccerDataAPI](https://github.com/yeonupark/mcp-soccer-data)** - This MCP server provides real-time football match data based on the SoccerDataAPI. From be3fdee7358970db3599dea39b531c5ff0c7736b Mon Sep 17 00:00:00 2001 From: Javier Re Date: Mon, 29 Sep 2025 09:05:17 -0300 Subject: [PATCH 8/9] Add Lippia MCP Server entry to README (#2698) * Add Lippia MCP Server entry to README * Update README.md Change link to repo for getting started Co-authored-by: Ola Hungerford --------- Co-authored-by: Ola Hungerford --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index b62f1813..049c6a24 100644 --- a/README.md +++ b/README.md @@ -274,6 +274,7 @@ Official integrations are maintained by companies building production ready MCP - LiGo Logo **[LinkedIn MCP Runner](https://github.com/ertiqah/linkedin-mcp-runner)** - Write, edit, and schedule LinkedIn posts right from ChatGPT and Claude with [LiGo](https://ligo.ertiqah.com/). - Linkup Logo **[Linkup](https://github.com/LinkupPlatform/js-mcp-server)** - (JS version) MCP server that provides web search capabilities through Linkup's advanced search API. This server enables AI assistants and development tools to perform intelligent web searches with natural language queries. - Linkup Logo **[Linkup](https://github.com/LinkupPlatform/python-mcp-server)** - (Python version) MCP server that provides web search capabilities through Linkup's advanced search API. This server enables AI assistants and development tools to perform intelligent web searches with natural language queries. +- Lippia.io **[Lippia](https://github.com/Lippia-io/Lippia-MCP-Server/blob/main/getting-started.md)** - MCP Server to accelerate Test Automation using Lippia Framework. - Lisply **[Lisply](https://github.com/gornskew/lisply-mcp)** - Flexible frontend for compliant Lisp-speaking backends. - Litmus.io Logo **[Litmus.io](https://github.com/litmusautomation/litmus-mcp-server)** - Official MCP server for configuring [Litmus](https://litmus.io) Edge for Industrial Data Collection, Edge Analytics & Industrial AI. - Liveblocks Logo **[Liveblocks](https://github.com/liveblocks/liveblocks-mcp-server)** - Ready‑made features for AI & human collaboration—use this to develop your [Liveblocks](https://liveblocks.io) app quicker. From 28dcd95b3b01354b692a4843079065656f26d284 Mon Sep 17 00:00:00 2001 From: "Abraham J. Olaobaju" <39011309+bajoski34@users.noreply.github.com> Date: Mon, 29 Sep 2025 13:06:28 +0100 Subject: [PATCH 9/9] Add Flutterwave API integration to README (#2748) * Add Flutterwave API integration to README * Update README.md --------- Co-authored-by: adam jones --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index 049c6a24..5327c818 100644 --- a/README.md +++ b/README.md @@ -198,6 +198,7 @@ Official integrations are maintained by companies building production ready MCP - FIXParser Logo **[FIXParser](https://gitlab.com/logotype/fixparser/-/tree/main/packages/fixparser-plugin-mcp)** - A modern FIX Protocol engine for AI-powered trading agents - Fluid Attacks Logo **[Fluid Attacks](https://github.com/fluidattacks/mcp)** - Interact with the [Fluid Attacks](https://fluidattacks.com/) API, enabling vulnerability management, organization insights, and GraphQL query execution. - ForeverVM Logo **[ForeverVM](https://github.com/jamsocket/forevervm/tree/main/javascript/mcp-server)** - Run Python in a code sandbox. +- Flutterwave Logo **[Flutterwave](https://github.com/bajoski34/mcp-flutterwave/tree/main)** - Interact with Flutterwave payment solutions API, to manage transactions, payment links and more. - GibsonAI Logo **[GibsonAI](https://github.com/GibsonAI/mcp)** - AI-Powered Cloud databases: Build, migrate, and deploy database instances with AI - Gcore Logo **[Gcore](https://github.com/G-Core/gcore-mcp-server)** - Interact with Gcore platform services via LLM assistants, providing unified access to CDN, GPU Cloud & AI Inference, Video Streaming, WAAP, and cloud resources including instances and networks. - Gitea Logo **[Gitea](https://gitea.com/gitea/gitea-mcp)** - Interact with Gitea instances with MCP.