# MCP Everything (reference) server 1.0.0 (Node 20) / 2.0.1 (Node 24): our test log

Canonical: https://theagenticweekly.com/tests/mcp-server-everything · Last verified: 2026-10-25 · Published: 2026-10-25 · Author: Agentic Weekly (operated independently from Texas, US) · Evidence: Tested by us on 2026-10-25. Local open-weight model, not the vendor's hosted models. A smoke test on a CPU-only box, not a benchmark.

> MCP Everything (reference) server answered over stdio in 356 ms cold (v1.0.0, Node 20) and 252 ms (v2.0.1, Node 24); median call 0.5 to 0.4 ms.

## Result at a glance

Table: MCP Everything (reference) server test record

| Field | Value |
|---|---|
| Result | Passed |
| Version tested | 1.0.0 (Node 20) / 2.0.1 (Node 24) |
| Date and time | 2026-10-25, 22:37 to 23:08 CDT (America/Chicago) |
| Task | A small Python client written with the official MCP Python SDK (2.3.0) spawns the server as a child process over stdio, times the initialize handshake (cold start: spawn to initialize result), times one tools/list, then times 30 sequential tools/call requests and reports the median and 95th percentile. Numbers are milliseconds on the rig described on the methodology page. |
| Model used | none (no language model involved) |
| Hardware | Linux x86_64 virtual machine (Debian 13), 8 vCPU (Intel Xeon, 1 thread per core), 15 GiB RAM, no GPU |
| Node 20 / mcp-servers/everything 1.0.0 | cold start 356 ms; tools/list 8.6 ms (13 tools); 30 x echo: median 0.5 ms, p95 1.4 ms |
| Node 24 / mcp-servers/everything 2.0.1 | cold start 252 ms; tools/list 6.4 ms (16 tools); 30 x echo: median 0.4 ms, p95 1.2 ms |

## What we found

- On Node 20 npm resolved version 1.0.0; on Node 24 it resolved 2.0.1. The 2.x line needs Node 24 or newer, and npm picks an older version on Node 20 without telling you.
- Cold start fell from 356 ms (1.x, Node 20) to 252 ms (2.x, Node 24), and the median call from 0.5 ms to 0.4 ms; both are well under a frame of video, so the practical difference is the startup, not the calls.
- The server exposed 13 tools on 1.x and 16 on 2.x.

## What we ran, step by step

Table: Commands run, wall-clock time and exit code

| Step | Wall time | Exit code | Notes |
|---|---|---|---|
| npm install on Node 20.19.2 (cold) | 2.6 s | 0 | Resolved 1.0.0; 32 MB in 124 packages; load 3.45. |
| npm install on Node 24.22.1 (cold) | 1.6 s | 0 | Resolved 2.0.1; 31 MB in 105 packages; load 1.73. |
| Latency run: Node 20 / mcp-servers/everything 1.0.0 | n/a | 0 | mcp-servers/everything 1.0.0 (protocol 2025-11-25). cold start 356 ms; tools/list 8.6 ms (13 tools); 30 x echo: median 0.5 ms, p95 1.4 ms. Load 2.50. |
| Latency run: Node 24 / mcp-servers/everything 2.0.1 | n/a | 0 | mcp-servers/everything 2.0.1 (protocol 2025-11-25). cold start 252 ms; tools/list 6.4 ms (16 tools); 30 x echo: median 0.4 ms, p95 1.2 ms. Load 1.45. |

Exact commands (paths shortened)

```
# npm install on Node 20.19.2 (cold)
npm install --no-audit --no-fund --cache /tmp/npmcache @modelcontextprotocol/server-everything

# npm install on Node 24.22.1 (cold)
npm install --no-audit --no-fund --cache /tmp/npmcache @modelcontextprotocol/server-everything

# Latency run: Node 20 / mcp-servers/everything 1.0.0
node work/npm/mcp-server-everything/node_modules/.bin/mcp-server-everything

# Latency run: Node 24 / mcp-servers/everything 2.0.1
/workspace/tests2/tools/node-v24.22.1-linux-x64/bin/node work/npm24/mcp-server-everything/node_modules/.bin/mcp-server-everything
```

## Raw output (excerpts)

Output of the timed call (Node 20 / mcp-servers/everything 1.0.0), first 300 characters

```
echo({"message": "hi"})
Echo: hi
```

## Gotchas and things that broke

- If a tutorial says 'npx -y @modelcontextprotocol/server-everything' and you are on Node 20 or 22, you will not get the latest 2.x server; check the version string the server reports in its initialize result.

## What we did not test

- Remote (HTTP) transport, authentication and concurrent clients: only local stdio with one client was measured.
- Large payloads: calls used tiny inputs, so these latencies are protocol and process overhead, not throughput.
- Anything about answer quality: no model was involved in the latency numbers.
- These are single smoke-test runs; it is not a benchmark. The machine was shared with other jobs.

## Reproduce it

Versions change. These commands install whatever is latest on the day you run them unless a version is pinned, so expect different results later. The version we measured is in the table above.

```
npm install @modelcontextprotocol/server-everything
# then drive it with any MCP client over stdio; we used the Python SDK client in the research page's script description
node node_modules/.bin/mcp-server-everything 
```

## How to read this test

Every number on this page was measured on this one machine, which also ran other jobs, so timings are indicative and vary run to run. A pass means our small task worked once or as stated, a fail means it did not work as we ran it; neither says how the tool behaves with a vendor's frontier model, on a GPU, or at scale. Where a tool could not run without an account or a GPU, we say so instead of guessing.

See the [testing rig](https://theagenticweekly.com/methodology#testing-rig) for the hardware, the local model and the rules we follow, and the [test hub](https://theagenticweekly.com/tests) for every other test.

## FAQ

### How fast is the MCP Everything (reference) server?

On our shared 8 vCPU VM: 356 ms to start and answer initialize on Node 20 (v1.0.0) and 252 ms on Node 24 (v2.0.1); a call took 0.4 ms at the median.

## Sources

- [MCP reference servers repository](https://github.com/modelcontextprotocol/servers) (fetched 2026-10-25)

## Related

- [All test logs](https://theagenticweekly.com/tests)
- [Methodology and testing rig](https://theagenticweekly.com/methodology#testing-rig)
- [Study: MCP server startup and call latency over stdio](https://theagenticweekly.com/research/mcp-servers-latency-and-failures)
- [Study: the silent version downgrade on older Node, and other install traps](https://theagenticweekly.com/research/older-node-silent-downgrades)
- [MCP servers facts and sources](https://theagenticweekly.com/tools/mcp-servers)

## How to cite

Agentic Weekly, "MCP Everything (reference) server 1.0.0 (Node 20) / 2.0.1 (Node 24): our test log", last updated 2026-10-25, https://theagenticweekly.com/tests/mcp-server-everything