# io.github.Vordium/vordium-mcp (pypi · vordium-mcp)

Vordium perps for any MCP client: markets, accounts, and orders you confirm, signed on your machine.

- Trust score: 89/100 (high trust)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `mcp.vordium.com`: 82/100, [markdown](https://verifymcp.io/servers/vordium-vordium-mcp/testnet-mcp.md), [page](https://verifymcp.io/servers/vordium-vordium-mcp/testnet-mcp)
- pypi · `vordium-mcp`: 89/100 (this document), [markdown](https://verifymcp.io/servers/vordium-vordium-mcp/vordium-mcp.md), [page](https://verifymcp.io/servers/vordium-vordium-mcp/vordium-mcp)

## Channel facts

- Registry: `pypi`
- Package: `vordium-mcp`
- Version: `0.7.0`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-21.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs setuptools.build_meta at install time, a recognised build step with no custom scripting around it.
  - No production dependencies, so there is no dependency health to assess.
- **Provenance & Transparency**: 100/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to Vordium/Vordium-MCP).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 2 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 84/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 3951 tokens (~101/item across 39 items; 36 tools + 3 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 40/100
  - Stability observed for 12 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 36 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 38 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the io.github.Vordium/vordium-mcp server?

io.github.Vordium/vordium-mcp runs locally as a PyPI package, launched with uvx vordium-mcp --network testnet --orders ask. Ready-made configuration for Claude, Cursor, VS Code, Codex and 3 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add vordium-vordium-mcp -- uvx vordium-mcp --network testnet --orders ask
```

### Cursor

```json
{
  "mcpServers": {
    "vordium-vordium-mcp": {
      "command": "uvx",
      "args": [
        "vordium-mcp",
        "--network",
        "testnet",
        "--orders",
        "ask"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "vordium-vordium-mcp": {
      "command": "uvx",
      "args": [
        "vordium-mcp",
        "--network",
        "testnet",
        "--orders",
        "ask"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add vordium-vordium-mcp -- uvx vordium-mcp --network testnet --orders ask
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "vordium-vordium-mcp": {
      "type": "local",
      "command": [
        "uvx",
        "vordium-mcp",
        "--network",
        "testnet",
        "--orders",
        "ask"
      ],
      "enabled": true
    }
  }
}
```

### Hermes

```yaml
mcp_servers:
  vordium-vordium-mcp:
    command: "uvx"
    args: ["vordium-mcp", "--network", "testnet", "--orders", "ask"]
```

### Netclaw

```json
{
  "McpServers": {
    "vordium-vordium-mcp": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "vordium-mcp",
        "--network",
        "testnet",
        "--orders",
        "ask"
      ]
    }
  }
}
```

### Other

```json
{
  "mcpServers": {
    "vordium-vordium-mcp": {
      "command": "uvx",
      "args": [
        "vordium-mcp",
        "--network",
        "testnet",
        "--orders",
        "ask"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-21 (score 89, +16)

- [security improvement] Malware scan: unverified → pass

### 2026-11-19 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-18 (score 72, 0)

- [functional] Package version: 0.6.6 → 0.7.0

### 2026-11-17 (score 72, −14)

- [security regression] Malware scan: pass → unverified
- [functional] Package version: 0.6.4 → 0.6.6
- [functional] Package version: 0.6.4 → 0.6.5

### 2026-11-14 (score 86, +16)

- [security improvement] Malware scan: unverified → pass

### 2026-11-13 (score 70, +1)

- [security improvement] Malware scan: unverified → pass
- [functional improvement] Security disclosure: fail → pass
- [functional] Package version: 0.6.3 → 0.6.4

### 2026-11-12 (score 69, −15)

- [security regression] Malware scan: pass → unverified

### 2026-11-11 (score 84, +16)

- [security improvement] Malware scan: unverified → pass

## MCP tools (36)

### `get_status` (~42 tokens)

Network status

Is the network live: block height, blocks per second, validators agreeing, and whether trading and deposits are open. Ask: "Is Vordium up right now?"

Output parameters:

- `agent_trading_on` (boolean|null)
- `blocks_per_second` (number|null)
- `deposits_open` (boolean|null)
- `finalized_height` (number|null)
- `height` (number|null)
- `live` (boolean|null)
- `network` (string): testnet or mainnet
- `summary` (string): one plain sentence
- `trading_blockers` (array)
- `trading_open` (boolean|null)

### `get_network` (~75 tokens)

Network identity

Which Vordium network this server reads, checked against the network itself, and the facts it vouches for (chain id, genesis, finalized block, agent trading on or off), and whether it matches the chain id and genesis this release is pinned to (nothing is signed otherwise). Ask: "Which network am I connected to?"

Output parameters:

- `identity` (object|null)
- `network` (string): testnet or mainnet
- `pin_warning` (string|null)
- `pinned` (object|null)
- `summary` (string): one plain sentence
- `truth` (object|null)

### `get_markets` (~42 tokens)

Markets

Every market the network lists, with its state, leverage, fees and trading rules (tick, lot, minimum size). Ask: "Which markets can I trade?"

Output parameters:

- `count` (number|null)
- `markets` (array)
- `network` (string): testnet or mainnet
- `summary` (string): one plain sentence

### `get_fees` (~106 tokens)

Fees and margins

Maker and taker fees, maximum leverage, initial and maintenance margin, and the liquidation terms as the network publishes them (the fee, or none), for every market or one. Ask: "What does it cost to trade BTC with 10x?"

Input parameters:

- `pair_id` (integer): or the market's pair id, e.g. 1
- `symbol` (string): market symbol as get_markets lists it, e.g. BTC, ETH or ETHUSDT

Output parameters:

- `count` (number|null)
- `liquidation` (object|null)
- `markets` (array)
- `network` (string): testnet or mainnet
- `summary` (string): one plain sentence

### `get_oracle` (~75 tokens)

Prices

Oracle and mark prices, for every market or one. Ask: "What is the ETH price?"

Input parameters:

- `pair_id` (integer): or the market's pair id, e.g. 1
- `symbol` (string): market symbol as get_markets lists it, e.g. BTC, ETH or ETHUSDT

Output parameters:

- `network` (string): testnet or mainnet
- `prices` (array)
- `summary` (string): one plain sentence

### `get_orderbook` (~100 tokens)

Order book

Resting bids and asks for one market, best first, with the spread. Ask: "How deep is the BTC book?"

Input parameters:

- `depth` (integer): levels per side, 1-100 (default 20)
- `pair_id` (integer): or the market's pair id, e.g. 1
- `symbol` (string): market symbol as get_markets lists it, e.g. BTC, ETH or ETHUSDT

Output parameters:

- `asks` (array)
- `best_ask` (number|null)
- `best_bid` (number|null)
- `bids` (array)
- `empty` (boolean|null)
- `market` (string|null)
- `network` (string): testnet or mainnet
- `pair_id` (number|null)
- `spread` (number|null)
- `summary` (string): one plain sentence

### `get_candles` (~134 tokens)

Candles

Price candles (open, high, low, close, volume) for one market. Ask: "How did ETH move over the last day?"

Input parameters:

- `limit` (integer): number of candles, 1-500 (default 24)
- `pair_id` (integer): or the market's pair id, e.g. 1
- `price` (string): mark price (default) or last traded price
- `resolution` (string): candle length (default 1h)
- `symbol` (string): market symbol as get_markets lists it, e.g. BTC, ETH or ETHUSDT

Output parameters:

- `candles` (array)
- `count` (number|null)
- `market` (string|null)
- `network` (string): testnet or mainnet
- `pair_id` (number|null)
- `resolution` (string|null)
- `summary` (string): one plain sentence

### `get_trades` (~98 tokens)

Recent trades

The latest trades in one market: time, side, price, size and value. Ask: "Show the last 10 BTC trades."

Input parameters:

- `limit` (integer): 1-100 (default 20)
- `pair_id` (integer): or the market's pair id, e.g. 1
- `symbol` (string): market symbol as get_markets lists it, e.g. BTC, ETH or ETHUSDT

Output parameters:

- `count` (number|null)
- `market` (string|null)
- `network` (string): testnet or mainnet
- `pair_id` (number|null)
- `summary` (string): one plain sentence
- `trades` (array)

### `get_funding` (~104 tokens)

Funding

The funding rate, interval and next settlement for one market, and optionally its past settlements. Ask: "What has ETH funding been over the last day?"

Input parameters:

- `history` (integer): also return this many past settlements, 1-400
- `pair_id` (integer): or the market's pair id, e.g. 1
- `symbol` (string): market symbol as get_markets lists it, e.g. BTC, ETH or ETHUSDT

Output parameters:

- `history` (array)
- `interval_secs` (number|null)
- `market` (string|null)
- `network` (string): testnet or mainnet
- `next_funding` (number|null)
- `pair_id` (number|null)
- `rate_per_interval_pct` (number|null)
- `summary` (string): one plain sentence

### `get_account` (~74 tokens)

Account

One account at a glance: USDC balances, positions with entry, mark, unrealized PnL and liquidation price, and open orders. Ask: "Check my account 0x…"

Input parameters:

- `address` (string, required): 0x-prefixed 20-byte account address (0x followed by 40 hex characters)

Output parameters:

- `address` (string|null)
- `explorer` (string|null)
- `network` (string): testnet or mainnet
- `orders` (array)
- `positions` (array)
- `summary` (string): one plain sentence
- `usdc` (object|null)

### `get_fills` (~85 tokens)

Trade history

An account's recent trades with price, size, fee and realized PnL, as the explorer records them. Ask: "What did 0x… trade today?"

Input parameters:

- `address` (string, required): 0x-prefixed 20-byte account address (0x followed by 40 hex characters)
- `limit` (integer): 1-50 (default 20)

Output parameters:

- `address` (string|null)
- `network` (string): testnet or mainnet
- `summary` (string): one plain sentence

### `get_balance` (~71 tokens)

Balance

An account's USDC: available to trade, in positions, reserved by orders, unrealized PnL. Ask: "How much USDC does 0x… have?"

Input parameters:

- `address` (string, required): 0x-prefixed 20-byte account address (0x followed by 40 hex characters)

Output parameters:

- `address` (string|null)
- `network` (string): testnet or mainnet
- `summary` (string): one plain sentence
- `usdc` (object|null)

### `get_positions` (~57 tokens)

Positions

An account's open positions as the chain stores them. Ask: "What positions does 0x… hold?"

Input parameters:

- `address` (string, required): 0x-prefixed 20-byte account address (0x followed by 40 hex characters)

Output parameters:

- `address` (string|null)
- `count` (number|null)
- `network` (string): testnet or mainnet
- `positions` (array)
- `summary` (string): one plain sentence

### `get_orders` (~58 tokens)

Open orders

An account's resting orders, with their order ids. Ask: "Which orders does 0x… have open?"

Input parameters:

- `address` (string, required): 0x-prefixed 20-byte account address (0x followed by 40 hex characters)

Output parameters:

- `address` (string|null)
- `count` (number|null)
- `network` (string): testnet or mainnet
- `orders` (array)
- `summary` (string): one plain sentence

### `get_agents` (~47 tokens)

Agents

An owner's AI agents: status, limits and policy, usage, and each agent's latest actions. Ask: "What are my agents doing?"

Input parameters:

- `address` (string, required): the owner account

Output parameters:

- `agents` (array)
- `count` (number|null)
- `network` (string): testnet or mainnet
- `owner` (string|null)
- `summary` (string): one plain sentence

### `get_policy` (~61 tokens)

Agent policy

Each agent's policy and market limits as the chain stores them, and whether the network enforces them now. Ask: "What limits does my agent trade under?"

Input parameters:

- `address` (string, required): the owner account
- `agent` (string): optional agent address

Output parameters:

- `agents` (array)
- `available` (boolean|null)
- `count` (number|null)
- `network` (string): testnet or mainnet
- `owner` (string|null)
- `summary` (string): one plain sentence

### `get_risk` (~58 tokens)

Agent usage

Each agent's usage against its policy, as the chain accounts it. Ask: "How much of its daily loss limit has my agent used?"

Input parameters:

- `address` (string, required): the owner account
- `agent` (string): optional agent address

Output parameters:

- `agents` (array)
- `available` (boolean|null)
- `count` (number|null)
- `network` (string): testnet or mainnet
- `owner` (string|null)
- `summary` (string): one plain sentence

### `get_tiers` (~36 tokens)

Tiers

Agent limits by tier and the referral tier table, where the network serves them. Ask: "How many agents can each tier run?"

Output parameters:

- `agent_limits` (object|null)
- `network` (string): testnet or mainnet
- `referral_tiers` (object|null)
- `summary` (string): one plain sentence

### `get_season` (~54 tokens)

Rewards season

The current rewards season: status, VORD budget, rules, participants and how many qualify. Ask: "What is the current season?"

Input parameters:

- `season_id` (integer): a season number (default: the current season)

Output parameters:

- `name` (string|null)
- `network` (string): testnet or mainnet
- `season_id` (number|null)
- `summary` (string): one plain sentence

### `get_points` (~81 tokens)

Points

An address's season points by source, its rank, whether it qualifies and its VORD estimate. Ask: "What's my rank in the season?"

Input parameters:

- `address` (string, required): 0x-prefixed 20-byte account address (0x followed by 40 hex characters)
- `season_id` (integer): a season number (default: the current season)

Output parameters:

- `address` (string|null)
- `network` (string): testnet or mainnet
- `qualified` (boolean|null)
- `rank` (number|null)
- `season_id` (number|null)
- `summary` (string): one plain sentence

### `get_leaderboard` (~110 tokens)

Leaderboard

The season's points leaderboard, or the trading leaderboard by PnL, ROI or volume. Ask: "Who leads the season?"

Input parameters:

- `board` (string): points (default) or trading
- `limit` (integer): 1-100 (default 10)
- `season_id` (integer): a season number (default: the current season)
- `sort` (string): trading board only (default pnl)
- `window` (string): trading board only (default 7d)

Output parameters:

- `board` (string|null)
- `network` (string): testnet or mainnet
- `rows` (array)
- `summary` (string): one plain sentence

### `get_referrals` (~58 tokens)

Referrals

An address's referral code, tier, referred volume and earnings. Ask: "How much have my referrals earned?"

Input parameters:

- `address` (string, required): 0x-prefixed 20-byte account address (0x followed by 40 hex characters)

Output parameters:

- `address` (string|null)
- `code` (string|null)
- `network` (string): testnet or mainnet
- `summary` (string): one plain sentence
- `tier` (string|null)

### `get_tx` (~80 tokens)

Transaction

One EVM transaction by hash: block, sender, receiver, value and result, with its explorer link. The hash is sent to the explorer to look it up, so give only a transaction hash, never a key. Ask: "Explain transaction 0x…"

Input parameters:

- `hash` (string, required): 0x-prefixed 32-byte transaction hash

Output parameters:

- `network` (string): testnet or mainnet
- `summary` (string): one plain sentence

### `get_block` (~47 tokens)

Block

One block by height: time, proposer, operations, with its explorer link. Ask: "What happened in block 152,000,000?"

Input parameters:

- `height` (integer, required): block number

Output parameters:

- `network` (string): testnet or mainnet
- `summary` (string): one plain sentence

### `get_address` (~65 tokens)

Address

An address summary: account value, open positions, agents and EVM transactions, with its explorer link. Ask: "Look up 0x…"

Input parameters:

- `address` (string, required): 0x-prefixed 20-byte account address (0x followed by 40 hex characters)

Output parameters:

- `account_value_usdc` (number|null)
- `address` (string|null)
- `explorer` (string|null)
- `network` (string): testnet or mainnet
- `open_positions` (number|null)
- `summary` (string): one plain sentence

### `get_order` (~93 tokens)

One order

One resting order by its id: market, side, price, size left. An order that is not resting now (it filled or was cancelled) is reported as gone. Ask: "What is the state of order 8840974?"

Input parameters:

- `address` (string): the account (default: the server's configured owner)
- `order_id` (integer, required): the chain's order id, as get_orders lists it

Output parameters:

- `address` (string|null)
- `found` (boolean|null)
- `network` (string): testnet or mainnet
- `order` (object|null)
- `order_id` (number|null)
- `summary` (string): one plain sentence

### `check_outcome` (~290 tokens)

Request outcome

What a write whose answer was lost did, read from the node only (never the explorer): an order by its client nonce, a cancel by its order id, or a cancel-all by the order ids open before it. One check of up to 20 seconds (8 on a hosted server): applied, refused (with the chain's reason), still being checked, or still not known after 2 minutes. A write tool whose answer was lost names this call with its arguments. Ask: "Did my lost order go through?"

Input parameters:

- `address` (string): the account (default: the server's configured owner)
- `agent` (string): kind order, optional: the agent that signed it (its refusal records are read too)
- `client_nonce` (integer): kind order: the order's client nonce, as the write tool returned it
- `kind` (string, required): which write: order, cancel or cancel_all
- `order_id` (integer): kind cancel: the id of the order that was being cancelled
- `order_ids` (array): kind cancel_all: the order ids open before it was sent, as the write tool returned them
- `pair_id` (integer): optional: the market the order or cancel-all was for
- `since_ms` (integer): when it was sent (unix milliseconds): past 2 minutes, not proven reads as still not known

Output parameters:

- `address` (string|null)
- `client_nonce` (number|null)
- `follow_up` (object|null)
- `kind` (string|null)
- `network` (string): testnet or mainnet
- `next` (string|null)
- `read` (object|null)
- `refusal_meaning` (string|null)
- `refusal_reason` (string|null)
- `resend` (object|null)
- `state` (string|null): pending_checking, applied, applied_other, refused or still_unknown
- `summary` (string): one plain sentence
- `text` (string|null)

### `check_order` (~259 tokens)

Check an order

Check an order against every rule the network runs (market, size, price band, margin, the agent's limits) for the configured owner and agent, without signing or sending anything: whether it would be taken, each rule it breaks with the real numbers, and fixes that pass. Ask: "Can I buy 0.1 ETH at 20x?"

Input parameters:

- `leverage` (number): default: the highest the limits allow
- `order_type` (string): limit (default) rests at its price; market fills now
- `pair_id` (integer): or the market's pair id, e.g. 1
- `post_only` (boolean): rest on the book or be refused; never take liquidity
- `price` (number): limit price in USD (limit orders only)
- `reduce_only` (boolean): only reduce an open position, never open or add
- `side` (string, required): buy opens or adds to a long, sell to a short
- `size` (number, required): in the market's base asset, e.g. 0.01 for 0.01 ETH
- `symbol` (string): market symbol as get_markets lists it, e.g. BTC, ETH or ETHUSDT

Output parameters:

- `can_place` (boolean|null)
- `failed` (array)
- `figures` (object|null)
- `fixes` (array)
- `network` (string): testnet or mainnet
- `not_checked` (array)
- `summary` (string): one plain sentence

### `my_buying_power` (~94 tokens)

My buying power

Per market, the largest long and short the configured owner can open at each allowed leverage, from free margin and the agent's limits together. Ask: "How much ETH can I buy?"

Input parameters:

- `pair_id` (integer): or the market's pair id, e.g. 1
- `symbol` (string): market symbol as get_markets lists it, e.g. BTC, ETH or ETHUSDT

Output parameters:

- `markets` (array)
- `network` (string): testnet or mainnet
- `summary` (string): one plain sentence

### `place_order` (~289 tokens)

Place order

Place a market or limit order as the configured agent, after checking it against every network rule (an order the network would refuse is not signed). Signed on this machine with the agent key (OS keychain or key file); the chain enforces the agent's policy and limits. Refused before anything is signed while the network reports agent trading off, or after stop_all. Every order is first confirmed by you in your AI app, unless you started the server with --orders auto.

Input parameters:

- `leverage` (number): e.g. 2 for 2x (default 1)
- `order_type` (string): limit (default) rests at its price; market fills now
- `pair_id` (integer): or the market's pair id, e.g. 1
- `post_only` (boolean): rest on the book or be refused; never take liquidity
- `price` (number): limit price in USD (limit orders only)
- `reduce_only` (boolean): only reduce an open position, never open or add
- `side` (string, required): buy opens or adds to a long, sell to a short
- `size` (number, required): in the market's base asset, e.g. 0.01 for 0.01 ETH
- `symbol` (string): market symbol as get_markets lists it, e.g. BTC, ETH or ETHUSDT

Output parameters:

- `accepted` (boolean|null)
- `agent` (string|null)
- `already_received` (boolean|null)
- `chain_answer`
- `chain_status` (number|null)
- `client_nonce` (number|null)
- `confirmation` (object|null)
- `delivery_unknown` (boolean|null)
- `follow_up` (object|null)
- `network` (string): testnet or mainnet
- `next` (string|null)
- `note` (string|null)
- `read` (object|null)
- `refusal_meaning` (string|null)
- `refusal_reason` (string|null)
- `refused` (boolean|null)
- `resend` (object|null)
- `sent` (boolean|null)
- `state` (string|null): pending_checking, applied, applied_other, refused or still_unknown
- `summary` (string): one plain sentence
- `text` (string|null)

### `close_position` (~211 tokens)

Close position

Close the owner's position in one market — all of it, or a fraction — with a reduce-only order (market by default), with the full pre-trade check. Signed on this machine with the agent key (OS keychain or key file); the chain enforces the agent's policy and limits. Refused before anything is signed while the network reports agent trading off, or after stop_all. Every order is first confirmed by you in your AI app, unless you started the server with --orders auto.

Input parameters:

- `fraction` (number): how much of the position, above 0 and at most 1 (default 1: all)
- `order_type` (string): market (default) or limit
- `pair_id` (integer): or the market's pair id, e.g. 1
- `price` (number): limit price in USD (limit only)
- `symbol` (string): market symbol as get_markets lists it, e.g. BTC, ETH or ETHUSDT

Output parameters:

- `accepted` (boolean|null)
- `agent` (string|null)
- `already_received` (boolean|null)
- `chain_answer`
- `chain_status` (number|null)
- `client_nonce` (number|null)
- `confirmation` (object|null)
- `delivery_unknown` (boolean|null)
- `follow_up` (object|null)
- `network` (string): testnet or mainnet
- `next` (string|null)
- `note` (string|null)
- `read` (object|null)
- `refusal_meaning` (string|null)
- `refusal_reason` (string|null)
- `refused` (boolean|null)
- `resend` (object|null)
- `sent` (boolean|null)
- `state` (string|null): pending_checking, applied, applied_other, refused or still_unknown
- `summary` (string): one plain sentence
- `text` (string|null)

### `set_tpsl` (~219 tokens)

Set take-profit / stop-loss

Set, move or remove the take-profit and stop-loss of the owner's position in one market. A leg you do not name stays as it is; remove takes a leg off. A take-profit sits on the profit side of the mark, a stop-loss on the loss side. Signed on this machine with the agent key (OS keychain or key file); the chain enforces the agent's policy and limits. Refused before anything is signed while the network reports agent trading off, or after stop_all. Every order is first confirmed by you in your AI app, unless you started the server with --orders auto.

Input parameters:

- `pair_id` (integer): or the market's pair id, e.g. 1
- `remove` (string): take a leg off
- `stop_loss` (number): new stop-loss price in USD
- `symbol` (string): market symbol as get_markets lists it, e.g. BTC, ETH or ETHUSDT
- `take_profit` (number): new take-profit price in USD

Output parameters:

- `accepted` (boolean|null)
- `agent` (string|null)
- `already_received` (boolean|null)
- `chain_answer`
- `chain_status` (number|null)
- `confirmation` (object|null)
- `delivery_unknown` (boolean|null)
- `follow_up` (object|null)
- `network` (string): testnet or mainnet
- `next` (string|null)
- `note` (string|null)
- `position_id` (number|null)
- `read` (object|null)
- `refusal_meaning` (string|null)
- `refusal_reason` (string|null)
- `refused` (boolean|null)
- `resend` (object|null)
- `sent` (boolean|null)
- `state` (string|null): pending_checking, applied, applied_other, refused or still_unknown
- `stop_loss` (number|null)
- `summary` (string): one plain sentence
- `take_profit` (number|null)
- `text` (string|null)

### `modify_order` (~181 tokens)

Modify order

Move one resting order to a new price and/or size: a signed cancel-and-replace (the new order gets a new id and no time priority); the new order is checked against the network's rules (its margin is the chain's to judge). Signed on this machine with the agent key (OS keychain or key file); the chain enforces the agent's policy and limits. Refused before anything is signed while the network reports agent trading off, or after stop_all. Every order is first confirmed by you in your AI app, unless you started the server with --orders auto.

Input parameters:

- `order_id` (integer, required): the chain's order id, as get_orders lists it
- `price` (number): new limit price in USD (default: unchanged)
- `size` (number): new size in the base asset (default: what is left)

Output parameters:

- `accepted` (boolean|null)
- `agent` (string|null)
- `already_received` (boolean|null)
- `chain_answer`
- `chain_status` (number|null)
- `client_nonce` (number|null)
- `confirmation` (object|null)
- `delivery_unknown` (boolean|null)
- `follow_up` (object|null)
- `network` (string): testnet or mainnet
- `next` (string|null)
- `note` (string|null)
- `read` (object|null)
- `refusal_meaning` (string|null)
- `refusal_reason` (string|null)
- `refused` (boolean|null)
- `replaced_order_id` (number|null)
- `resend` (object|null)
- `sent` (boolean|null)
- `state` (string|null): pending_checking, applied, applied_other, refused or still_unknown
- `summary` (string): one plain sentence
- `text` (string|null)

### `cancel_order` (~86 tokens)

Cancel order

Cancel one of the configured owner's resting orders, as the agent. Signed on this machine with the agent key (OS keychain or key file); the chain enforces the agent's policy and limits. Refused before anything is signed while the network reports agent trading off, or after stop_all.

Input parameters:

- `order_id` (integer, required): the chain's order id, as get_orders lists it

Output parameters:

- `accepted` (boolean|null)
- `agent` (string|null)
- `already_received` (boolean|null)
- `chain_answer`
- `chain_status` (number|null)
- `confirmation` (object|null)
- `delivery_unknown` (boolean|null)
- `follow_up` (object|null)
- `network` (string): testnet or mainnet
- `next` (string|null)
- `note` (string|null)
- `read` (object|null)
- `refusal_meaning` (string|null)
- `refusal_reason` (string|null)
- `refused` (boolean|null)
- `resend` (object|null)
- `sent` (boolean|null)
- `state` (string|null): pending_checking, applied, applied_other, refused or still_unknown
- `summary` (string): one plain sentence
- `text` (string|null)

### `cancel_all` (~123 tokens)

Cancel all orders

Cancel every resting order of the configured owner — in one market, or in all of them — as the agent. Signed on this machine with the agent key (OS keychain or key file); the chain enforces the agent's policy and limits. Refused before anything is signed while the network reports agent trading off, or after stop_all.

Input parameters:

- `pair_id` (integer): or the market's pair id, e.g. 1
- `symbol` (string): market symbol as get_markets lists it, e.g. BTC, ETH or ETHUSDT

Output parameters:

- `accepted` (boolean|null)
- `agent` (string|null)
- `already_received` (boolean|null)
- `chain_answer`
- `chain_status` (number|null)
- `confirmation` (object|null)
- `delivery_unknown` (boolean|null)
- `follow_up` (object|null)
- `network` (string): testnet or mainnet
- `next` (string|null)
- `note` (string|null)
- `read` (object|null)
- `refusal_meaning` (string|null)
- `refusal_reason` (string|null)
- `refused` (boolean|null)
- `resend` (object|null)
- `scope` (string|null)
- `sent` (boolean|null)
- `state` (string|null): pending_checking, applied, applied_other, refused or still_unknown
- `summary` (string): one plain sentence
- `text` (string|null)

### `stop_all` (~60 tokens)

Stop all (kill switch)

Stop this server from signing anything new (only cancels, until you run `vordium-mcp resume` on this machine), then cancel every resting order. Revoking the agent itself on the chain is the owner's step in Vordex → Agents.

Output parameters:

- `at` (string|null)
- `cancel_all` (object|null)
- `cancel_state` (string|null): the cancel part's own state
- `network` (string): testnet or mainnet
- `revoke_on_chain` (string|null)
- `stopped` (boolean|null)
- `summary` (string): one plain sentence

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/vordium-vordium-mcp/vordium-mcp#diagnostics

## Score history

- 2026-11-21: 89
- 2026-11-20: 73
- 2026-11-19: 73
- 2026-11-18: 72
- 2026-11-17: 72
- 2026-11-16: 86
- 2026-11-15: 86
- 2026-11-14: 86
- 2026-11-13: 70
- 2026-11-12: 69
- 2026-11-11: 84
- 2026-11-10: 68
- 2026-11-09: 68

## Common questions

### What is the io.github.Vordium/vordium-mcp server?

io.github.Vordium/vordium-mcp is listed in the public MCP registry as io.github.Vordium/vordium-mcp. Vordium perps for any MCP client: markets, accounts, and orders you confirm, signed on your machine. This page covers its PyPI package (vordium-mcp).

### Is the io.github.Vordium/vordium-mcp server safe to use?

io.github.Vordium/vordium-mcp scores 89 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 2026. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the io.github.Vordium/vordium-mcp server expose?

io.github.Vordium/vordium-mcp exposes 36 tools: get_status, get_network, get_markets, get_fees, get_oracle, and 31 more. Their descriptions and schemas cost roughly 3,723 tokens of context every time the server is loaded.

### Is the io.github.Vordium/vordium-mcp server still maintained?

io.github.Vordium/vordium-mcp is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the io.github.Vordium/vordium-mcp server under?

io.github.Vordium/vordium-mcp declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

### What did VerifyMCP test on the io.github.Vordium/vordium-mcp server?

VerifyMCP ran 16 checks on io.github.Vordium/vordium-mcp, covering Malware scan, Known CVEs, Install scripts, Dependency health and 12 more. Endpoint Security and Transport & Reachability do not apply to a PyPI package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- PyPI project: https://pypi.org/project/vordium-mcp/
- Socket report: https://socket.dev/pypi/package/vordium-mcp
- Repository: https://github.com/Vordium/vordium-mcp
- Website: https://docs.vordium.com/build/mcp/
- Changelog RSS feed: https://verifymcp.io/servers/vordium-vordium-mcp/vordium-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/vordium-vordium-mcp/vordium-mcp/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/vordium-vordium-mcp/vordium-mcp.json
- HTML version of this page: https://verifymcp.io/servers/vordium-vordium-mcp/vordium-mcp
