MCP Server for Z.AI - A Model Context Protocol server that provides AI capabilities
Nothing to run from here
Cluster 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
18
downloads a day
local
or remote
2k
downloads in 30d
What it does
Self-hostable index of AI financial agents — tokenized stocks + crypto, memory, LLM gateway.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user cluster-mcp '--' npx -y @clusteragent/cluster-mcp
# 2 — ask your agent for something these tools do
# get_quotes, get_movers, get_news and 33 more
Cluster costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
CLAll 1 server
clusteragent1 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 can run either way — at an address its publisher runs, or as a process under your own user, with your files and your network — and this marketplace is in the path of neither.
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 cluster-mcp '--' npx -y @clusteragent/cluster-mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Or connect to its publisher’s address
Its publisher also runs it at https://mcp.clusteragent.dev/mcp: nothing to start on your machine, and this marketplace is not in the path.
claude mcp add --scope user --transport http cluster-mcp https://mcp.clusteragent.dev/mcpFree 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 CLUSTER_API_URL (Cluster backend base URL (default: https://clusteragent.dev)), CLUSTER_API_KEY (Cluster API key (clst_...) minted via wallet signature — required only for wallet-scoped tools), CLUSTER_WALLET (Default wallet address for wallet-scoped tools) 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
36 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.
Batch quotes + ~1 month of daily closes for tokenized stocks/ETFs and crypto on Robinhood Chain. Symbols: NVDA, SPY, TSLA, PONS, WETH, USDG, CLIPPY, KARMA, ...
No parameter schema on file.
Live gainers, losers and sector heat across the 192-instrument universe.
No parameter schema on file.
Yahoo Finance market headlines.
No parameter schema on file.
Price series + candles for a symbol (NVDA, SPY, PONS, ...).
No parameter schema on file.
Cluster index composition: 193 instruments, on-chain verified count, $CLST status.
No parameter schema on file.
The 19-name payout basket with weights — what $CLST holders get paid from.
No parameter schema on file.
Distribution cycles, per-cycle aggregates, basket buys and treasury balance — the public payout record. Recipient lists are never public.
No parameter schema on file.
Uniswap v3 route + amountOut for a swap on Robinhood Chain (4663). amount is in WEI of the input token. Read-only — execution happens in the user
No parameter schema on file.
Router, quoter, WETH, USDG, gas price, ETH USD rate for Robinhood Chain.
No parameter schema on file.
On-chain balances for any address on Robinhood Chain: native ETH + every held token. Read-only, no auth.
No parameter schema on file.
24-model LLM gateway list with context windows and USD pricing per 1M tokens.
No parameter schema on file.
One completion through the cluster LLM gateway (24 models). Set thinking=true for extended reasoning. Costs credit ($5 free per wallet).
No parameter schema on file.
Inference credit balance (granted/used/remaining) for a wallet.
No parameter schema on file.
Store a durable memory note. Works without a wallet (an anonymous agent bank is auto-created locally); pass a wallet/bank_id to use a private signature-gated wallet bank. Deduped — identical content is skipped. Persists across sessions.
No parameter schema on file.
Recall memory notes, scored by semantic relevance with recency decay. Works without a wallet (anonymous agent bank); pass bank_id for a wallet bank.
No parameter schema on file.
Create a cluster API key (clst_...) for a wallet. Shown exactly once.
No parameter schema on file.
Metered usage for a wallet
No parameter schema on file.
Safety scan for a Robinhood Chain token: liquidity depth, buy/sell ratio honeypot heuristic, holder count via explorer, launchpad-factory detection. Returns score, tier, flags.
No parameter schema on file.
Side-by-side token comparison: price, 24h change, liquidity, volume for 2+ tokens (stocks or crypto).
No parameter schema on file.
Sector heat: average day change, advancers/decliners per sector across the universe.
No parameter schema on file.
The 16 cluster agent capabilities: Relay, Scout, Argus, Vault, Oracle, ... with categories and triggers.
No parameter schema on file.
Queue a public agent capability run; returns run id/status, then poll get_run_status for cited result. No treasury or signing side effect.
No parameter schema on file.
Read a queued agent run
No parameter schema on file.
Wallet
No parameter schema on file.
Portfolio view + history for a wallet (wallet-auth required).
No parameter schema on file.
Chat conversation list for a wallet (wallet-auth required — titles are private).
No parameter schema on file.
Real quotes for every agent that has a market analogue (mapped symbols). No-auth market data.
No parameter schema on file.
Token metadata on-chain: symbol, decimals, total supply for any 4663 address.
No parameter schema on file.
X (Twitter) link status for a wallet.
No parameter schema on file.
Two-pass memory consolidation: recall fragments, LLM synthesizes, retain the summary. Reduces note bloat.
No parameter schema on file.
DCA plan calculator (dry-run, no txs): quote N buys of X ETH each into a token, returns per-buy expected amounts + total at current prices. Real execution = sign each buy with your wallet (see skills/swap).
No parameter schema on file.
Bracket preview for a held token: current price from DexScreener, suggested TP/SL offsets (±10/20%), and the sell-side quote at those levels. Dry-run — no orders stored.
No parameter schema on file.
USD valuation of a wallet: on-chain balances × live quotes, with concentration breakdown.
No parameter schema on file.
Compare a wallet
No parameter schema on file.
Headlines filtered for relevance to one symbol
No parameter schema on file.
Current gas price + ETH USD on 4663 (from trade status).
No parameter schema on file.
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 Cluster 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 1.0.12 · scanned 14 Oct 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
Findings1 threat · 0 capability
Capabilitymoderate
Coveragesource
Verificationrepo
Surface digest3c50acd98c41e3479f3d182963657a7ead0983ea3dad0948066282daec4c8551
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 (36 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 |
|---|---|---|
| get_quotes | no tags | |
| get_movers | no tags | |
| get_news | no tags | |
| get_chart | no tags | |
| get_index | no tags | |
| get_payout_basket | no tags | |
| get_distributions | no tags | |
| quote_swap | no tags | |
| trade_status | no tags | |
| wallet_balances | no tags | |
| get_models | no tags | |
| chat | no tags | |
| get_credits | no tags | |
| memory_retain | no tags | |
| memory_recall | no tags | |
| create_key | no tags | |
| key_usage | no tags | |
| token_safety | no tags | |
| compare_tokens | no tags | |
| sector_heat | no tags | |
| agent_list | no tags | |
| agent_run | no tags | |
| get_run_status | no tags | |
| get_position | no tags | |
| get_portfolio | no tags | |
| list_conversations | no tags | |
| agent_quotes | no tags | |
| token_info | no tags | |
| social_profile | no tags | |
| memory_consolidate | no tags | |
| dca_preview | no tags | |
| tpsl_preview | no tags | |
| wallet_value | no tags | |
| basket_vs_wallet | no tags | |
| news_for_symbol | no tags | |
| gas_now | 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 digest3c50acd98c41e347
Scanned2026-10-14
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 1.0.12. Pin a release below and the command asks for exactly that one.
1.0.12
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 Cluster 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.