Local MCP capabilities provider for Expo
Nothing to run from here
Quantum 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.
93/100
tool-list score
20
tools declared
remote
at its publisher
—
calls last 7d
What it does
QuantumOracle — 18 post-quantum crypto tools: Kyber, Dilithium, hybrid schemes, migration.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http quantum-mcp https://tooloracle.io/quantum/mcp/
# 2 — ask your agent for something these tools do
# quantum_join, quantum_trust_passport, quantum_rate and 17 more
Quantum costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
TOAll 61 servers
tooloracle61 servers
14 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. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
Claude Codedeclared by this listing
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it.
claude mcp add --scope user --transport http quantum-mcp https://tooloracle.io/quantum/mcp/Reconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it answers at its publisher’s own address: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
What you approve
20 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.
Join OracleNet in one call. Provide your agent card URL and get instant trust score, mesh visibility, and access to 1,065+ tools.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agent_card_url | string | no | URL to your A2A Agent Card. EITHER this OR mcp_endpoint is required. |
| did | string | no | Your W3C DID (optional, auto-detected) |
| mcp_endpoint | string | no | Your MCP server endpoint. EITHER this OR agent_card_url is required. |
| payout_address | string | no | Wallet for escrow payments (optional) |
Get a signed, portable Trust Passport (W3C Verifiable Credential) proving your trust level in OracleNet.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| node_id | string | yes | Your OracleNet node ID or DID |
Rate an agent after interaction. 1-5 stars. Adjusts neural weights and reputation.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| rated_did | string | yes | — |
| rating | number | yes | — |
| rater_did | string | no | — |
| feedback | string | no | — |
Query any agent reputation: score 0-100, grade A+ to F, trust level.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agent_did | string | yes | — |
| period_days | number | no | — |
Get referral to best oracle for your need. OracleNet points you to who CAN help.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| need | string | yes | — |
| current_oracle | string | no | — |
Your past OracleNet interactions. What worked, re-engagement suggestions.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agent_did | string | yes | — |
| limit | number | no | — |
OracleNet Offer Card: catalog with pricing, SLAs, payment methods.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| tool | string | no | Optional filter |
Deal Handshake: propose a deal, get terms, rate. Agent-to-agent commerce.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| action | string | yes | propose or rate |
| tool | string | yes | Tool name |
| did | string | no | Your DID |
OracleNet Intent Parser v2 (LLM-powered): describe what you need in natural language. Uses Gemma 4 to understand context, urgency, and multi-step workflows. Returns the best oracle, tools, workflow steps, and exact API call. The front door of OracleNet.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| need | string | yes | Describe what you need in natural language |
| llm | boolean | no | Use LLM for semantic understanding (default: true; set false for fast keyword routing in <50ms) |
Find the best oracle for a task. Considers trust, capabilities, availability. Returns ranked candidates.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| task | string | yes | What you need (e.g. sanctions screening, DORA audit) |
| constraints | object | no | Optional: {min_trust_grade, max_cost_usdc} |
Pre-flight check before agent-to-agent interaction. Verifies identity, trust, recommends escrow or direct.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agent_did | string | no | DID or node_id of agent to check |
| target_task | string | no | Planned interaction |
Record a completed deal settlement. Updates trust score and revenue tracking.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| task_id | string | no | Task/deal ID |
| result_hash | string | no | SHA-256 hash of deliverable |
| node_id | string | no | Node that delivered |
| revenue_usdc | number | no | Revenue in USDC |
Live status of the entire OracleNet: nodes, attestations, routes, revenue, and how to join.
No parameter schema on file.
List all registered OracleNet nodes with trust scores, grades, and activity.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| status | string | no | Filter: active, pending, all |
| limit | integer | no | Max results |
Show OracleNet mesh intelligence — learned weights, rewards, synapse history, top-performing oracles. The mesh gets smarter with every interaction.
No parameter schema on file.
Passively inspects public machine-readable discovery surfaces for a domain. Returns declared and observed evidence, coverage, assurance and a bounded NOMOS read-only admission decision. It does not execute third-party tools, make payments, certify identity or issue compliance verdicts.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| domain | string | yes | Bare public domain, e.g. example.com. URLs, IP literals, ports, credentials and local names are rejected. |
Subscribe to OracleNet events via webhook. Get notified when servers change, new capabilities appear, deals become available, or trust scores shift. Push-based — we come to you.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| action | string | no | register, unregister, or list |
| webhook_url | string | no | URL where we POST events. Required when action=register. |
| did | string | no | Your DID (optional) |
| events | string | no | Comma-separated event types or 'all' |
| webhook_id | string | no | For unregister: webhook ID |
OracleNet event feed — latest signals, changes, alerts. Poll this for updates if you cannot use webhooks.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| limit | number | no | Max events (default 20) |
| event_type | string | no | Filter: heartbeat, new_capability, mesh_event, etc. |
The front door of OracleNet. Describe what you need in natural language — OracleNet understands, finds the right oracle, executes, and delivers the result. One call. Full loop.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| need | string | yes | What you need in natural language (NOT "question" — use "need") |
| caller_did | string | no | Your DID (optional) |
| execute | boolean | no | Auto-execute (default: true). Set false to preview. |
| arguments | object | no | Pre-set tool arguments (optional, auto-inferred from query) |
Execute a tool on an OracleNet oracle. The muscle of the mesh. Routes to the right oracle, calls it, delivers the result, logs the neural synapse, and updates routing weights. Use quantum_intent first to find the right tool, then quantum_execute to run it.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| tool | string | yes | Tool name to execute (e.g. compliance_preflight, fed_rate) |
| oracle | string | no | Oracle name/key hint (optional, auto-detected from tool) |
| arguments | object | yes | Arguments to pass to the tool |
| caller_did | string | no | Your DID for tracking (optional) |
Free
$0 forever
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- 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 Quantum 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: —
ATool-list grade · score 93 / 100
Release 1.0.0 · scanned 20 Oct 2026
Graded from the tools this server lists, not from its source code.
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 score93
Findings0 threat · 1 capability
Capabilitymoderate
Coveragemanifest
Verificationnot in this report
Surface digestadf8e88e88549bf0598ee74b22a9011b94d16e2661d3c50912bdfdf71a8a4077
Score vectorthreat 100 → client 93
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| coverage-honesty | manifest | inspection depth (manifest) — how much of the target the scan could see | −4 |
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.
The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.
Tool surfaceread
Implementation sourcenot available
Package metadatanot available
Live transportnot available
The implementation source was not read — this reflects the declared tool metadata only.
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 |
|---|---|---|
| quantum_join | no tags | |
| quantum_trust_passport | no tags | |
| quantum_rate | no tags | |
| quantum_reputation | no tags | |
| quantum_refer | no tags | |
| quantum_history | no tags | |
| quantum_offer | no tags | |
| quantum_deal | no tags | |
| quantum_intent | no tags | |
| quantum_route | no tags | |
| quantum_preflight | no tags | |
| quantum_settle | no tags | |
| quantum_status | no tags | |
| quantum_nodes | no tags | |
| neural_status | no tags | |
| quantum_scan | no tags | |
| quantum_subscribe | external-sink | external-sink: keyword "webhook", parameter "webhook" |
| quantum_feed | no tags | |
| quantum_ask | no tags | |
| quantum_execute | 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 digestadf8e88e88549bf0
Scanned2026-10-20
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
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 1.0.0.
1.0.0
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 Quantum 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.