Access control for AI agents and MCP servers: allow, hold for approval, or block each tool call
Nothing to run from here
Agentra 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.
6
tools declared
—
trust score
remote
at its publisher
—
calls last 7d
What it does
Identity oracle and trust layer for autonomous AI agents. Bidirectional KYA and trust scoring.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http agentra-mcp https://api.agentrapay.ai/mcp
# 2 — ask your agent for something these tools do
# agentra_create_wallet, agentra_verify_identity, agentra_check_reputation and 3 more
Agentra costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
AAAll 1 server
api.agentrapay.ai1 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. 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 agentra-mcp https://api.agentrapay.ai/mcpReconnect, 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
6 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.
Register as an agent and provision a non-custodial wallet. This is your FIRST CALL when onboarding to Agentra. Returns your agent_id, API key (agn_ prefix), and a Turnkey-managed wallet address on Base Sepolia. You hold the keys via Turnkey; Agentra never touches your private key. After this, call agentra_verify_identity to upgrade your trust tier.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | Human-readable name for your agent (e.g. 'ShoppingBot-v2') |
| operator | string | no | Optional. Your organization or operator name. |
| purpose | string | no | What this agent does (e.g. 'automated trading', 'API access'). Defaults to 'autonomous'. |
Submit identity verification to upgrade your trust tier. Higher tiers unlock larger transaction limits. Provide your agent_id (from agentra_create_wallet) and operator attestation. Verification is instant. Tiers: Unverified ($100/tx, $250/day) -> Basic ($1K/tx, $5K/day) -> Standard ($5K/tx, $10K/day) -> Enhanced ($25K/tx, $100K/day). Your API key (agn_ prefix) must be passed via X-API-Key header.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agent_id | string | yes | Your agent ID from registration |
| operator_attestation | object | no | Operator-signed attestation of agent identity and capabilities |
CALL THIS BEFORE paying or transacting with unknown agents. Returns the target agent's trust score (0-100), trust tier, reputation zone (Green/Yellow/Red), and transaction history summary. Agentra scores BOTH sides of every transaction: you and your counterparty. This is a read-only lookup with no side effects. Monetized endpoint: response detail varies by your plan tier.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agent_id | string | yes | The agent ID to check reputation for |
| include_history | boolean | no | Include recent transaction history summary (Standard+ plans) |
Request authorization for a payment to another agent or service. Agentra is NON-CUSTODIAL: this returns an authorization attestation and an unsigned transaction. Agentra never touches your private keys or moves your funds. YOU sign and submit the transaction yourself. Flow: (1) Call this endpoint -> (2) Receive unsigned tx + attestation -> (3) Sign with your Turnkey wallet -> (4) Submit to Base ne
| Parameter | Type | Required | Notes |
|---|---|---|---|
| amount_usdc | string | yes | Transaction amount in USDC as a string (e.g. '25.00') |
| purpose | string | no | Human-readable transaction purpose |
| receiver_address | string | yes | Recipient agent ID or external wallet address |
| require_counterparty_kya | boolean | no | Require counterparty to be KYA-verified. Default true. This is the viral growth hook: unverified counterparties must onboard to receive funds. |
| sender_agent_id | string | yes | Your agent ID (the sender) |
Create or update spending mandates that define your agent's autonomous transaction boundaries. Mandates enforce: max per-transaction amount, daily spending cap, allowed recipient types, minimum counterparty reputation score, and expiration. Your human operator sets these; your agent operates within them. require_counterparty_kya defaults to true. Recommended: true. This recruits counterparties int
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agent_id | string | yes | Your agent ID |
| daily_limit_usd | number | yes | Maximum total USD spend per rolling 24h |
| expires_at | string | no | Mandate expiration. Authorization rejected after this time. |
| max_per_tx_usd | number | yes | Maximum USD per single transaction |
| min_counterparty_score | number | no | Minimum reputation score (0-100) for counterparties. 40 = exclude Red zone. |
| require_counterparty_kya | boolean | no | Require counterparty KYA verification on all outbound transactions |
Get your agent profile and wallet details: trust tier, trust score, wallet address, registration status, and current verification level. Use to check your status before initiating transactions. Read-only, no side effects.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agent_id | string | yes | Your Agentra agent ID |
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 Agentra 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: —
—Grade not published
No rule-by-rule report on file for this release
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.
This listing is an address its publisher runs, and you connect to it directly — this marketplace is not in the path. The scanner reads packages and public source, and an address is neither. So there is no grade — not a withheld one, an unmeasured one.
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 Agentra 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.