Local Markdown library of the papers an evidence review cites: metadata, abstract and full text
Its author marked it deprecated in the MCP Registry
Nothing to run from here
whoelse is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
100/100
trust score
13
tools declared
local
runs on your machine
—
downloads a day
What it does
Don't build it alone: what exists, who won, what nobody has, a merge plan, and who else works on it.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user whoelse-mcp '--' uvx whoelse
# 2 — ask your agent for something these tools do
# load_profile, find_overlaps, joint_work_brief and 10 more
whoelse costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
BCAll 1 server
beskvladimir-create1 server
1 category
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 whoelse 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 uv (docs.astral.sh/uv): uvx 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 whoelse-mcp '--' uvx whoelseReconnect, 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 GITHUB_TOKEN (Optional. Raises GitHub search limits; public_repo scope needed for publish_request, start_joint_work and the watcher.), WHOELSE_OPENALEX_KEY (Optional. Free OpenAlex API key; without it you share a small per-IP daily budget.), WHOELSE_MAILTO (Optional. Your email for OpenAlex's polite pool; sent nowhere else.) 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
13 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.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
Build the user's profile from their public work (OpenAlex, arXiv, GitHub, Hugging Face, ORCID) and save it locally. name as it appears on their papers. Pass an ORCID iD to avoid picking a namesake; a GitHub login and a Hugging Face user add code and models.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | — |
| orcid | string | no | — |
| github | string | no | — |
| huggingface | string | no | — |
| affiliation_hint | string | no | — |
Who else is working on this right now? Ranked list of people whose recent papers, code or models overlap the user's profile, with whatever contact they made public and a one-line reason for each. Candidates get an index for joint_work_brief / draft_outreach.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | — |
| limit | integer | no | — |
| recent_months | integer | no | — |
| include_code | boolean | no | — |
| include_models | boolean | no | — |
For one candidate: the evidence of overlap, what each side has, the formats that fit (ranked by fit and effort), venues in common, and how to reach them. Use it to write a concrete proposal in the user's voice.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | — |
| candidate_index | integer | yes | — |
Facts and structure for the first message to one candidate. The host model writes the text; whoelse never sends it. format_id is one of the ids from joint_work_brief.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | — |
| candidate_index | integer | yes | — |
| format_id | string | no | — |
Mark a candidate as one of the user's people. whoelse will then watch what they ship.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | — |
| candidate_index | integer | yes | — |
| note | string | no | — |
Stop following a peer.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| key_or_name | string | yes | — |
What the user's peers published in the last N days (papers, repos, models, datasets), with concrete ways to support each. No automated stars or likes: the user decides.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| days | integer | no | — |
Render the user's whoelse card. They publish it at https://<their site>/.well-known/whoelse.json and anyone running whoelse sees them as reachable, with what they're open to. No registry.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | — |
| working_on | array | yes | — |
| open_to | array | yes | — |
| contact | string | yes | — |
| languages | array | no | — |
Profiles built so far and peers being followed.
Takes no parameters.
Join the network: publish what the user wants to build and with whom. This writes the user's NAME, EMAIL and ids into a PUBLIC GitHub repository (the registry), so pass confirmed=true only after the user has seen exactly that and agreed. From then on anyone who installs whoelse with the same…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | — |
| contact | string | yes | — |
| topic | string | yes | — |
| format_id | string | no | — |
| by | string | no | — |
| site | string | no | — |
| languages | array | no | — |
| confirmed | boolean | no | — |
Start the work before the first message: a workspace with the outline, section 1 drafted from both sides' published abstracts, the comparison table with published numbers, a reproduction skeleton pointing at both codebases, a 14-day plan, and both names on it.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | — |
| candidate_index | integer | yes | — |
| format_id | string | yes | — |
| create_github_repo | boolean | no | — |
| private | boolean | no | — |
Call this BEFORE building anything the user describes ("build me a tool that..."). What already exists on GitHub for this idea: the cluster of repositories that do the same job, the leader, a feature matrix (who has what, what only one has, what none has) and a one-sentence verdict. Hundreds of…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| idea | string | yes | — |
| months | integer | no | — |
| max_stars | integer | no | — |
For a cluster of near-identical small repositories: a merge plan (the living leader as the base, what each one brings, every author a maintainer, a deadline) and the text of the issue each author would receive in their own repository. First call: returns the plan, the issue texts and a plan_id;…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| idea | string | yes | — |
| months | integer | no | — |
| max_stars | integer | no | — |
| open_issues | boolean | no | — |
| plan_url | string | no | — |
| plan_id | string | no | — |
| batch | boolean | no | — |
| sender_note | string | no | — |
| index_url | string | no | — |
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
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install whoelse or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 100 / 100
Release 0.1.0 · scanned 10 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 score100
Findings3 threat · 0 capability
Capabilityminimal
Coveragesource
Verificationsource
Surface digest16554143432bd0548c7cba6266f4219e676bc0711738f9979d0372854377f158
Score vectorthreat 100 → client 100
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | minimal | capability blast radius (minimal) — client exposure if the model is manipulated | −0 |
| 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 surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (13 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, 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. minimal is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| load_profile | no tags | |
| find_overlaps | no tags | |
| joint_work_brief | no tags | |
| draft_outreach | no tags | |
| add_peer | no tags | |
| remove_peer | no tags | |
| whats_new_from_peers | no tags | |
| make_card | no tags | |
| list_known | no tags | |
| publish_request | no tags | |
| start_joint_work | no tags | |
| find_duplicates | no tags | |
| propose_merge | no tags |
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 digest16554143432bd054
Scanned2026-11-10
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.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 0.1.0. Pin a release below and the command asks for exactly that one.
0.1.0
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish whoelse can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.