Name: Benchwarmers
Author: WendellResearch-AI

Benchwarmers MCP

Ask a collection of LLMs at once through your Benchwarmers server; verdicts pick the next panel.

Grade A Local · stdio API key 4 tools v0.5.5 · 2 Nov 2026 MIT

No reviews yet by WendellResearch-AInpm 3,171 Runs on your machine, nothing hosted

94/100

trust score

887

downloads a day

local

runs on your machine

downloads in 30d

What it does

Ask a collection of LLMs at once through your Benchwarmers server; verdicts pick the next panel.

Quickstart

# 1 — add it to Claude Code
claude mcp add --scope user benchwarmers-mcp '--' npx -y @wendellresearch-ai/benchwarmers mcp

# 2 — ask your agent for something these tools do
#   list_collections, ask, verdict and 1 more

Benchwarmers costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.

Publishernot claimed

WendellResearch-AI1 server

1 category

All 1 server

Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.

Installation

Where are you running it?

Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Benchwarmers as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.

Claude Codedeclared by this listing

This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.

claude mcp add --scope user benchwarmers-mcp '--' npx -y @wendellresearch-ai/benchwarmers mcp

Reconnect, or start a new session, and the tools appear in the model’s tool list.

Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.

What it asks of you

Nothing is required, but it can take BENCHWARMERS_URL (Your Benchwarmers server (default http://127.0.0.1:8122). Needs Python 3.11 or later on PATH), BENCHWARMERS_KEY (A gateway key, needed beyond this machine or where the server requires keys), BENCHWARMERS_TIMEOUT (Seconds to wait for a panel (default 900)) if you want to set them.

What it writes

One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.

What you approve

4 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.

Tool surface

What the model actually sees. Descriptions are diffed on every release — see version history.

Only tools that write or reach the network

Read from its source code. A server that builds its tool list when it starts can list more tools than this.

The collections this Benchwarmers server offers: name, what each is for, tags, members,

No parameter schema on file.

Put a prompt to every seat of one collection at once and get every answer back, each

Parameter	Type	Required	Notes
collection	string	yes	A collection name, core or bench/core (list_collections).
prompt	string	yes	The question, with everything it needs.
system	string	no	A system message for every seat.
merged	boolean	no	true: one reconciled answer, every seat still called and listed; false: every answer. Omit for the collection's own.
with	array	no	Model aliases to seat in explorer chairs, this request only.

Judge one seat's answer by its call id, once you have checked it against the source. One

Parameter	Type	Required	Notes
call	string	yes	The seat's call id, e.g. p20261022-101500-ab12.member1.
useful	boolean	yes	—
note	string	no	One or two sentences on why.
real	array	no	Claims it made that are true, one sentence each.
false	array	no	Claims it made that are untrue, one sentence each.

For the Benchwarmers Claude Code plugin's Stop hook, which calls it at the end of a

Parameter	Type	Required	Notes
session	string	no	The Claude Code session id.
transcript	string	no	The session's transcript_path.
active		no	The hook's stop_hook_active: true says nothing.

Free

$0 forever

Every tool, no call limit
No card, and mcprush charges nothing for it
Source published under MIT
Runs on your machine — nothing of it reaches our gateway
Nothing to cap, because mcprush bills nothing

Nothing here is billable: mcprush charges nothing to install Benchwarmers or to call it, at any volume.

ATrust score 94 / 100

Release 0.5.5 · scanned 3 Nov 2026

Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.

Threat score100

Client score94

Findings11 threat · 0 capability

Capabilityhigh

Coveragesource

Verificationsource

Surface digestb8d9c197046495e840c556e962ddbf8511a3f0a8268b1e560a4bac7571d81d32

Score vectorthreat 100 → client 94

Term	Level	What it prices	Points
capability-exposure	high	capability blast radius (high) — client exposure if the model is manipulated	−6
verification-discount	source	publisher verification (provenance) — cryptographic build provenance ties the artifact to its source	−0
coverage-honesty	source	inspection depth (source) — how much of the target the scan could see	−0

score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.

What the scan could actually read

A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.

Tool surfacenot available

Implementation sourceread

Package metadataread

Live transportnot available

No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, scan the running server: --command "npx -y <package>".

Capability — what it could do if the model were manipulated

Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. high is the level these add up to.

Tool	Capability tags	Why the tag was assigned
No per-tool rows for this release — see the note below.

can send data / act on an external service

Toxic-flow graph

The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.

The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.

Supply chain and provenance

Integrityfirst-seen

Surface digestb8d9c197046495e8

Scanned2026-11-03

This is the first scan of this surface here, so there is nothing yet to compare it against.

Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.