Skip to main content
Glama
Sign In

Autoview

by com.autoview
OverviewDiscussionsAdmin

link

Save a PAPER/TESTNET exchange's API keys to your account and link them to a webhook, in one step -- for an agent that has a practice account's keys and no browser. Only ALPACAPAPER, BINANCEDELIVERYTESTNET, BINANCEFUTURESTESTNET, BINANCETEST, BITGETDEMO, BITGETMIXDEMO, BITMEXTESTNET, BYBITCOPYTESTNET, BYBITSPOTTESTNET, BYBITTESTNET, CAPITALDEMO, CRYPTODEMO, DERIBITTESTNET, GATEFUTURESTESTNET, GEMINISANDBOX, HYPERLIQUIDTESTNET, OANDAPRACTICE, OKXDEMO, OKXEEADEMO, OKXUSDEMO, TRADOVATESIM are accepted (they never move real money); real-money exchanges are refused whatever your token's scope, and their keys must be added on autoview.com in a browser (see connect). The credentials object uses named keys (public, private, passphrase, email, vault, id, cid, sec); which of them an exchange takes, and what each is called on that exchange, is in catalog({ exchange }): its credentials schema lists the exact keys (titles are the exchange's own labels) and which are required. The keys are encrypted and stored exactly as the website's setup form stores them, and are never echoed back. hook_id, if given, must be one of your own hooks with no exchange linked yet (an order fires on every exchange a hook links); omit it to use an empty hook of yours or get a new one. Then call entry with the returned hook_id (dry-run by default) to check the keys work. Requires your Autoview account token; any token can link a paper exchange.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "exchange": "<exchange>",
      "credentials": "<credentials>"
    },
    "name": "link"
  }
}

Input Schema

NameRequiredDescriptionDefault
tokenNoyour Autoview account token — an av_mcp_ personal access token, generate one at /account/tokens/ on the Autoview site. Omit this if your MCP client already sends it as an `Authorization: Bearer` header (Claude Code, Cursor, and most non-browser clients do this automatically once configured).
hook_idNolink this specific hook of yours (it must have no exchange linked yet); omit to use an empty hook or create a new one
exchangeYesthe paper/testnet exchange these keys belong to
credentialsYesthe practice account's keys, one string per field: fill only the fields the chosen exchange takes. The credentials object uses named keys (public, private, passphrase, email, vault, id, cid, sec); which of them an exchange takes, and what each is called on that exchange, is in catalog({ exchange }): its credentials schema lists the exact keys (titles are the exchange's own labels) and which are required.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changed
    • removedInput schema / properties / credentials / additionalProperties / type
      Removed value: -"string"
    • changedInput schema / properties / credentials / description
      Previous value: -"the practice account's credential fields, keyed by field name (see this tool's description for each exchange's names), e.g. {\"public\": \"<api key>\", \"private\": \"<secret>\"} for CRYPTODEMO"New value: +"the practice account's keys, one string per field: fill only the fields the chosen exchange takes. The credentials object uses named keys (public, private, passphrase, email, vault, id, cid, sec); which of them an exchange takes, and what each is called on that exchange, is in catalog({ exchange }): its credentials schema lists the exact keys (titles are the exchange's own labels) and which are required."
    • addedInput schema / properties / credentials / properties
      Added value: +{
+  "cid": {
+    "description": "TRADOVATESIM: CID",
+    "type": "string"
+  },
+  "email": {
+    "description": "CAPITALDEMO: Email Address",
+    "type": "string"
+  },
+  "id": {
+    "description": "OANDAPRACTICE: Account ID",
+    "type": "string"
+  },
+  "passphrase": {
+    "description": "BITGETDEMO: Passphrase; BITGETMIXDEMO: Passphrase; OKXDEMO: Passphrase; OKXEEADEMO: Passphrase; OKXUSDEMO: Passphrase",
+    "type": "string"
+  },
+  "private": {
+    "description": "ALPACAPAPER: Secret Key; BINANCEDELIVERYTESTNET: Secret; BINANCEFUTURESTESTNET: Secret; BINANCETEST: Secret; BITGETDEMO: Secret Key; BITGETMIXDEMO: Secret Key; BITMEXTESTNET: Secret; BYBITCOPYTESTNET: Private Key; BYBITSPOTTESTNET: Private Key; BYBITTESTNET: Private Key; CAPITALDEMO: Custom Password; CRYPTODEMO: Secret Key; DERIBITTESTNET: Access Secret; GATEFUTURESTESTNET: API Secret; GEMINISANDBOX: API Secret; HYPERLIQUIDTESTNET: Secret Key; OANDAPRACTICE: Access Token; OKXDEMO: Secret Key; OKXEEADEMO: Secret Key; OKXUSDEMO: Secret Key; TRADOVATESIM: Password",
+    "type": "string"
+  },
+  "public": {
+    "description": "ALPACAPAPER: API Key ID; BINANCEDELIVERYTESTNET: API Key; BINANCEFUTURESTESTNET: API Key; BINANCETEST: API Key; BITGETDEMO: Access API Key; BITGETMIXDEMO: Access API Key; BITMEXTESTNET: ID; BYBITCOPYTESTNET: API Key; BYBITSPOTTESTNET: API Key; BYBITTESTNET: API Key; CAPITALDEMO: API Key; CRYPTODEMO: API Key; DERIBITTESTNET: Access Key; GATEFUTURESTESTNET: API Key; GEMINISANDBOX: API Key; HYPERLIQUIDTESTNET: Public Address (optional); OKXDEMO: API Key; OKXEEADEMO: API Key; OKXUSDEMO: API Key; TRADOVATESIM: Username",
+    "type": "string"
+  },
+  "sec": {
+    "description": "TRADOVATESIM: Secret",
+    "type": "string"
+  },
+  "vault": {
+    "description": "HYPERLIQUIDTESTNET: Sub-account / Vault Address (optional)",
+    "type": "string"
+  }
+}
    • removedInput schema / properties / credentials / propertyNames
      Removed value: -{
-  "type": "string"
-}
    • changedInput schema / properties / exchange / enum
      Previous value: -[
-  "OANDAPRACTICE",
-  "CRYPTODEMO",
-  "BYBITTESTNET",
-  "BYBITSPOTTESTNET",
-  "TRADOVATESIM"
-]New value: +[
+  "ALPACAPAPER",
+  "BINANCEDELIVERYTESTNET",
+  "BINANCEFUTURESTESTNET",
+  "BINANCETEST",
+  "BITGETDEMO",
+  "BITGETMIXDEMO",
+  "BITMEXTESTNET",
+  "BYBITCOPYTESTNET",
+  "BYBITSPOTTESTNET",
+  "BYBITTESTNET",
+  "CAPITALDEMO",
+  "CRYPTODEMO",
+  "DERIBITTESTNET",
+  "GATEFUTURESTESTNET",
+  "GEMINISANDBOX",
+  "HYPERLIQUIDTESTNET",
+  "OANDAPRACTICE",
+  "OKXDEMO",
+  "OKXEEADEMO",
+  "OKXUSDEMO",
+  "TRADOVATESIM"
+]
  2. Added

TDQS

A4.6/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the annotations (which only say not-read-only, not-destructive, not-idempotent, not-open-world), the description discloses that keys are encrypted and stored exactly as the website form stores them, are never echoed back, that hook_id must be one of your own hooks with no exchange linked yet, and that an order fires on every exchange a hook links. It also states the auth requirement and that any token scope can link a paper exchange.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose and the paper-only constraint are front-loaded in the first sentence, and most sentences carry operational information (refusal behavior, key storage, hook selection, next step). It is a dense single paragraph with some repetition of the schema's credential-key explanation, so it is slightly longer than strictly necessary.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 4-parameter mutating tool with no output schema, the description covers auth (token or Bearer header), the accepted-exchange allowlist and refusal of real-money venues, credential-field sourcing via catalog, hook_id semantics, storage/security behavior, and the recommended verification step. Nothing an agent needs to invoke it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3, and much of the description's parameter text (the named credential keys, the hook_id constraint) is duplicated verbatim in the schema. It does add the consequence-level nuance that a linked hook fires on every linked exchange, but this does not go materially beyond what the structured fields already document.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Save a PAPER/TESTNET exchange's API keys ... and link them to a webhook, in one step') and immediately scopes it to paper/testnet venues. It is clearly distinguishable from siblings like connect (real-money, browser-based) and setup, which an agent can tell apart without opening either schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit when-to-use ('for an agent that has a practice account's keys and no browser'), explicit when-not (real-money exchanges are refused whatever your token's scope; use connect on autoview.com instead), and it names the correct alternatives and follow-up ('call entry with the returned hook_id'). It also routes the agent to catalog({ exchange }) for key requirements.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Autoview toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources