RU
Agent teams, swarms, memory and hooks for Claude Code and Codex, served over MCP.
Nothing to run from here
Psephex 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.
96/100
trust score
13
tools declared
local
runs on your machine
—
downloads a day
What it does
A judge for deals between AI agents on NEAR: open cases, check x402 payments, verify verdicts
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user psephex-mcp '--' npx -y @unitynodes/psephex-mcp
# 2 — ask your agent for something these tools do
# whoami, court_config, open_case and 10 more
Psephex costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
UNAll 4 servers
UnityNodes4 servers
3 categories
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 Psephex 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 psephex-mcp '--' npx -y @unitynodes/psephex-mcpReconnect, 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 NEAR_ACCOUNT_ID (NEAR testnet account the agent acts as; without it the server is read-only), NEAR_PRIVATE_KEY (Function-call or dedicated agent key for that account, never an owner key), PSEPHEX_MAX_STAKE_NEAR (Cap on one stake or appeal bond in NEAR (default 0.5)), PSEPHEX_BUDGET_NEAR (Cap on everything one server process attaches, in NEAR (default 1)), PSEPHEX_ALLOWED_COUNTERPARTIES (Comma-separated accounts the agent may open cases against) 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.
The NEAR account this server acts for, whether it can sign, and its stake cap.
No parameter schema on file.
Court parameters: minimum stake, appeal bond, response, appeal and arbitration windows, arbiter.
No parameter schema on file.
Open a case against another NEAR account as claimant. Spends the stake plus up to about 0.05 NEAR oracle reserve and storage (the unused reserve comes back), counted against this agent's session budget. The counterparty then has a response window.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| claim | string | yes | What you say is true, one line |
| evidence | string | yes | Your evidence, one line; include check_payment output if a payment is involved |
| counterparty | string | yes | — |
| stake_near | string | yes | Stake in NEAR, for example 0.05 |
Answer a case where you are the counterparty, with your own evidence, before the response deadline. This sends the case to the oracle.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| case_id | integer | yes | — |
| response | string | yes | Your answer and evidence, one line |
Send a case to the oracle without a response, after the counterparty's deadline passed. Anyone can call it.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| case_id | integer | yes | — |
Appeal a decided case you are a party to, before the appeal deadline. Spends the case's appeal bond in NEAR (counted against the session budget); a human arbiter then rules.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| case_id | integer | yes | — |
Pay out a decided case after its appeal window, or an appealed case after the arbitration window. Anyone can call it.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| case_id | integer | yes | — |
Return the stake to the claimant when the oracle did not answer in time.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| case_id | integer | yes | — |
Everything about a case: both sides' texts, stage and deadlines, the exact question the models get, verdict and votes.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| case_id | integer | yes | — |
Cases newest first, optionally only those where an account is a party and only open ones. Use it to find cases waiting for your response.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| account | string | no | — |
| open_only | boolean | no | — |
Check a payment on NEAR by transaction hash: a NEAR transfer, or an ft_transfer or x402 payment (signed delegate) of a trusted token. Every receipt must have succeeded. Returns who paid whom, how much, and an evidence line for open_case.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| tx_hash | string | yes | — |
| sender | string | yes | The account that sent the transaction (the payer, or the facilitator relayer for x402) |
Re-run the 2-of-3 signature check for an oracle request on the NEAR contract and compare it with the stored verdict.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| request_id | integer | yes | The oracle request id of the case |
A NEAR account's record in the court: cases, wins, losses, appeals, cases it did not answer. Check it before paying an agent.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| account | string | yes | — |
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 Psephex 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 96 / 100
Release 0.1.1 · scanned 12 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 score96
Findings0 threat · 1 capability
Capabilitymoderate
Coveragesource
Verificationrepo
Surface digest8ed02b404a67e4d99e702b801fda182642624cbdacaf0c376bb5e63fff3c25b0
Score vectorthreat 100 → client 96
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| 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. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| whoami | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| court_config | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| open_case | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
| respond | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| submit_case | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| appeal | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
| finalize | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| refund | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| get_case | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| list_cases | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| check_payment | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| verify_verdict | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| reputation | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
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.
flow-1
Untrusted input can drive an external action even though no sensitive source is exposed.
Supply chain and provenance
Integrityfirst-seen
Surface digest8ed02b404a67e4d9
Scanned2026-11-12
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 0.1.1. Pin a release below and the command asks for exactly that one.
0.1.1
11 Nov 2026
latestNo release note was published with this version.
0.1.0
undated
- The version this listing was on when mcprush began following its releases. The registry was not asked when it shipped, so this row carries no date.
—
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 Psephex 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.