MCP Filesystem server 1.0.0 (Node 20) / 2.0.1 (Node 24): our test log

MCP Filesystem server answered over stdio in 279 ms cold (v1.0.0, Node 20) and 187 ms (v2.0.1, Node 24); median call 0.8 to 1.0 ms.

Result at a glance

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 279 ms (1.x, Node 20) to 187 ms (2.x, Node 24), and the median call from 0.8 ms to 1.0 ms; both are well under a frame of video, so the practical difference is the startup, not the calls.
• The server exposed 14 tools on 1.x and 14 on 2.x.
• Sandbox check (v2.0.1, allowed root work/fsroot): reading /etc/hostname and a path using ../ to leave the root were both refused with 'Access denied - path outside allowed directories'; listing the root and writing a file inside it worked. That is four requests, a smoke test and not a security audit.

What we ran, step by step

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

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

# Latency run: Node 20 / secure-filesystem-server 1.0.0
node work/npm/mcp-server-filesystem/node_modules/.bin/mcp-server-filesystem /workspace/tests2/work/fsroot

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

# Sandbox check
python mcpsec.py  # four tools/call requests (script uses the official MCP Python SDK client)

Raw output (excerpts)

read_text_file({"path": "/workspace/tests2/work/fsroot/notes.txt"})
hello from the fixture file
hello from the fixture file
hello from the fixture file
hello from the fixture file
hello from the fixture file
hello from the fixture file
hello from the fixture file
hello from the fixture file
hello from the fixture file
hello from the fixture file
hello from the fixtu

read_text_file {'path': '/etc/hostname'} -> ERROR Access denied - path outside allowed directories: /etc/hostname not in /workspace/tests2/work/fsroot
read_text_file {'path': '/workspace/tests2/work/fsroot/../gitrepo/f'} -> ERROR Access denied - path outside allowed directories: /workspace/tests2/work/gitrepo/f not in /workspace/tests2/work/fsroot
list_directory {'path': '/workspace/tests2/work/fsroot'} -> ok [FILE] notes.txt
write_file {'path': '/workspace/tests2/work/fsroot/new.txt', 'content': 'x'} -> ok Successfully wrote to /workspace/tests2/work/fsroot/new.txt

Gotchas and things that broke

• If a tutorial says 'npx -y @modelcontextprotocol/server-filesystem' 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.
• The server is a file-write tool: it can create and overwrite files inside its allowed directories. We only tested the path check with plain and ../ paths, not symlinks.

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-filesystem
# 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-filesystem /path/to/allowed/dir

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 for the hardware, the local model and the rules we follow, and the test hub for every other test.

Related tests: mcp servers and tooling

• MCP Git server: The MCP Git server 2026.10.19 started in 512 ms, listed 12 tools and answered git_status in 3.2 ms median.
• MCP Inspector (CLI mode): MCP Inspector listed the filesystem server's 14 tools from the command line on both 0.15.0 (Node 20) and 2.12.0 (Node 24) in under a second; the 2.x install is smaller.
• MCP Memory server: MCP Memory server answered over stdio in 284 ms cold (v1.0.0, Node 20) and 147 ms (v2.0.0, Node 24); median call 0.9 to 0.6 ms.
• MCP Sequential Thinking server: MCP Sequential Thinking server answered over stdio in 271 ms cold (v1.0.0, Node 20) and 159 ms (v2.0.0, Node 24); median call 0.8 to 0.4 ms.
• MCP Time server: The MCP Time server 2026.10.19 started in 483 ms and answered get_current_time in 0.8 ms median.
• Notion MCP server: Notion MCP server 2.5.2 (@notionhq/notion-mcp-server) started over stdio in a median 316 ms and listed 24 tools in a median 16 ms; we did not make any authenticated call.

All test logs · How we test

FAQ

Sources

• MCP reference servers repository (fetched 2026-10-25)

Related

• All test logs
• Methodology and testing rig
• Study: MCP server startup and call latency over stdio
• Study: the silent version downgrade on older Node, and other install traps
• MCP servers facts and sources