AgenticMarketEverything MCP Server
ECOSYSTEM REFERENCENO AUTHApache-2.0Open SourceSource: @agenticmarket· community reference
The official MCP reference server that exercises every protocol feature — prompts, tools, resources, sampling, and all transports. Built for MCP client developers and testing.
Setup Guide
{
"mcpServers": {
"everything-mcp-server": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-everything"
]
}
}
}Tools
echo
Echoes back the provided message (string) and uses Zod to validate the input.
get-annotated-message
Returns a text message annotated with priority and audience based on messageType (error, success, or debug), and can optionally include an annotated image.
get-resource-reference
Accepts a resourceType (text or blob) and resourceId (positive integer), and returns a concrete resource content block including uri, mimeType, data, and surrounding explanatory text.
get-roots-list
Returns the last list of roots sent by the client.
gzip-file-as-resource
Accepts a name and data (URL or data URI), fetches and validates size/time/domain constraints, compresses it, registers it as a session resource with MIME type application/gzip, and returns either a resource link or inline resource depending on outputType.
get-structured-content
Demonstrates structured responses by accepting a location input and returning both backward-compatible content (text block with JSON) and structuredContent validated against an outputSchema such as temperature, conditions, and humidity.
get-sum
Calculates and returns the sum of two numbers (a and b) with input validation using Zod.
get-tiny-image
Returns a tiny PNG MCP logo as an image content item, along with brief descriptive text before and after.
trigger-long-running-operation
Simulates a multi-step operation over a specified duration and number of steps, reporting progress via notifications when a progressToken is provided.
toggle-simulated-logging
Starts or stops simulated logging with random levels for the session, respecting the client’s selected minimum logging level.
toggle-subscriber-updates
Starts or stops simulated resource update notifications for URIs that the current session is subscribed to.
trigger-sampling-request
Sends a sampling/createMessage request to the client or LLM using a provided prompt and generation controls, returning the LLM’s response payload.
simulate-research-query
Simulates a multi-stage research task by accepting a topic and ambiguity flag, progressing through stages with updates, and optionally triggering elicitation requests for clarification if ambiguous.
trigger-sampling-request-async
Demonstrates asynchronous bidirectional tasks where a sampling request is sent to the client, executed in the background, and the server polls for status and retrieves the result when complete.
trigger-elicitation-request-async
Demonstrates asynchronous bidirectional tasks where an elicitation request is sent to the client for user input, executed in the background, and the server polls until a response is received.
Compatibility
About
The Everything MCP Server is the official reference implementation from Anthropic that exercises every feature of the MCP protocol. It is not designed for daily use — it's a test server for developers building MCP clients, IDE integrations, or debugging MCP protocol compliance.
When to use this
- Building an MCP client? Use this server to verify your client handles all protocol features correctly.
- Testing IDE integration? It exposes prompts, tools, resources, and sampling — great for checking your IDE's MCP panel renders everything.
- Learning MCP? The source code is the best reference for how to implement each MCP primitive.
What it demonstrates
The server showcases the full MCP feature set:
| Feature | What it tests |
|---|---|
| Tools | Echo, add, long-running operations, binary content |
| Resources | Dynamic resource listing and content retrieval |
| Prompts | Prompt templates with argument substitution |
| Sampling | Client-side LLM sampling (requesting completions from the host) |
| Progress | Progress reporting during long-running operations |
| Transports | stdio, HTTP+SSE (deprecated), and Streamable HTTP |
All three transports
This is one of the few servers that supports all MCP transport modes:
bash# stdio (default) npx @modelcontextprotocol/server-everything # SSE (deprecated in MCP 2025-03-26) npx @modelcontextprotocol/server-everything sse # Streamable HTTP (recommended for remote servers) npx @modelcontextprotocol/server-everything streamableHttp
Not for production
This server includes intentionally simple tools (echo, add) and test fixtures. It adds unnecessary tools to your AI's context window if left enabled during normal work. Only enable it when actively testing or developing MCP integrations.
Install and Troubleshooting Intent Coverage
Developer-install and troubleshooting intent for community MCP server listings.
install mcp server / mcp server setup guide
mcp json config example / vscode mcp setup
mcp server not working / mcp tools not showing
mcp server compatibility matrix / cursor vs vscode mcp compatibility
mcp server monetization options / convert community mcp server to paid listing
Related Setup, Debug, and Learning Links
Server registry requirements
Devtool listings often graduate from explore to registry.
Publish server guide
Action path for maintainers ready to list production versions.
CLI installation guide
Install baseline for all IDEs before listing-specific setup.
Using servers guide
Covers runtime usage patterns and auth flow.
Cursor setup walkthrough
High-intent setup path for developer troubleshooting journeys.
Troubleshooting: server not working
Common failure modes for install and runtime issues.
Troubleshooting: tools not showing
Covers discovery/listing failures across major IDEs.
Related explore entry: FreshContext
Keeps same-intent users on matched category and tool shape.
Related explore entry: Memory
Keeps same-intent users on matched category and tool shape.
Related explore entry: Roundtable MCP
Keeps same-intent users on matched category and tool shape.
Related explore entry: Sequential Thinking
Keeps same-intent users on matched category and tool shape.
Install this server instantly with the AgenticMarket CLI — zero config, auto-detects your IDE.
$npx agenticmarket install everything-mcp-serverFreshContext
Freshness-aware MCP server with 21 tools for timestamped, decay-ranked retrieval signals across GitHub, HN, jobs, research, market data, and more.
Memory
Give your AI assistant persistent memory across conversations. The Memory server stores entities, relations, and observations in a local knowledge graph that persists between sessions.
Roundtable MCP
Multi-model AI council MCP server that enables collaborative reasoning for architecture, debugging, code review, and engineering decisions.
Sequential Thinking
Enhance your AI assistant's reasoning with structured, step-by-step thinking. Supports revisions, branching, and dynamic adjustment of reasoning depth.