Which MCP servers actually work?
MCP Verdict independently installed and tested filesystem servers, then published the passing results with the method and evidence behind each score. This registry is now a retained historical snapshot, not an active testing or monitoring service.
No vendor pays for placement. The method is public, one click from every score.
Recent verdicts
mark3labs/mcp-filesystem-server
MCP server · 50% confidence
@neonlightdev/mcp-server-filesystem-ignore
MCP server · 50% confidence
mcp-filesystem (Develasquez)
MCP server · 50% confidence
Eight passing evaluations retained from the initial filesystem review.
The gap
Every other score reads the label. Almost none of them run the tool.
Several products now put a number on an MCP server. They score the packaging: GitHub stars, manifest quality, declared permissions, provenance, maintenance recency. A score assembled from a project's own metadata is a popularity-and-age score wearing a quality costume, and the author controls most of the inputs. One popular MCP score already has a published guide titled "how to hit 100." A number you can grind toward measures completeness, not quality.
None of that answers the question a builder actually asks. If I point an agent at this server, does it do what it claims, does it stay up across ten calls, how fast is it, and what can it reach on my machine. That answer only comes from running the thing.
The wedge
We run the server and take a side.
Every entry has been installed and exercised against a structured evaluation. We check whether it functions as advertised, how reliably it responds across repeated calls, how fast, and what it can touch on the host. The score is behavioral, built from running the tool, not from reading its npm page. Then a person writes a verdict that says use it or do not.
The public registry now retains only the eight passing evaluations from that review. The package version and test date travel with every score because a historical result must not be mistaken for continuous monitoring or current certification.
Function
Does it do what it says? We run every advertised tool. Pass, partial, or fail, with notes.
Reliability
How consistently does it respond correctly across repeated calls in one run?
Latency
How fast is it? Scored on a curve: under 250ms is full marks, past three seconds it falls hard.
Security
What can it reach? We test path scoping, allowlists, and escape routes. One high flag caps the score.
The neutrality thesis
We have no servers to sell and no platform to protect.
Every directory and marketplace that ranks these tools has a reason to. A vendor's store favors the tools that make its platform look good. A directory with a connector gateway favors the tools that route through it. The scorers built on metadata favor whoever fills in the most fields. MCP Verdict runs none of that. We do not host a directory, we do not sell placement, and the scoring weights and the method are published and versioned.
Everyone else scores the packaging. We tested the product. The retained passing scores follow the same published formula regardless of vendor or maintainer.
Read the neutrality thesisWhat a verdict looks like
A real score, explained.
This is a live entry from the registry. The grade, the composite, the four sub-scores, the confidence, the methodology version, and the written verdict are all public. Every entry looks like this.
@modelcontextprotocol/server-filesystem
MCP serverThe official Anthropic-maintained filesystem MCP server. Exposes 14 tools for read, write, edit, search, and directory operations. Enforces a configurable allowlist of directories via command-line arguments or the MCP Roots protocol.
The verdict
See the full entry and test historyThe reference implementation. All 14 advertised tools pass functional testing. Directory allowlist is enforced at startup and at every operation: both read and write outside allowed directories are blocked with a clear error. Setup is a single npx command. The only design note worth flagging: the server grants full read-write access to every allowed directory with no per-directory read-only mode at the server level. Use Docker volume mounts with the ro flag if you need a read-only allowed directory. For any production agent deployment, this is the server to start with.
Start here.
Find a server.
The registry is open. Filter by type and sort by score or confidence. Every entry shows its grade, its sub-scores, and the written verdict.
Browse the registryUnderstand the snapshot.
MCP Verdict is no longer accepting submissions, publishing negative findings, or scheduling re-tests. The retained entries describe the exact versions and dates shown on their pages.
Read publication statusHistorical snapshot · eight passing filesystem evaluations · no active monitoring