Skip to main content
POST
Call Tool
Execute a tool with the provided input parameters. The tool’s response format varies depending on the specific tool being called.

Example

Response envelope

On the MCP server the same three fields ride in _meta, and the error text opens with the owner: Danube error: ..., Apify error: ..., or Request error: ....

Body options

Alongside tool_input, the body accepts:

Secrets are redacted

Credential values an upstream hands back (environment variables, API keys, tokens, private keys) are masked as [REDACTED:<FIELD>] before the result reaches you, and the masked form is what Danube stores. This is Danube policy, not a broken tool. If a later call genuinely needs such a value, store it as a credential on the service, or reference it with env:// / vault://, rather than asking a tool to return the raw secret. Tools whose purpose is to return a newly created credential are marked as such and report redaction.passthrough_reason instead of masking.

Authorizations

danube-api-key
string
header
required

Your Danube API key

Path Parameters

tool_id
string
required

The unique identifier of the tool to execute

Body

application/json

Tool input parameters

tool_input
object

Input parameters for the tool. A body without tool_input is treated as the input itself, in which case the options below are not read.

max_response_chars
integer

Size cap on result (max 2000000)

fields
string[]

Dotted paths to keep in result

confirm_token
string

Completes the consent handshake

timeout_seconds
integer

Wait on a slow MCP-backed upstream for this one call

Required range: 1 <= x <= 300

Response

Tool execution result

Execution envelope; result varies by tool

tool_id
string
status
enum<string>
Available options:
success,
error
result
any

The tool's payload

error
string | null
error_type
string | null
fault
enum<string> | null
Available options:
danube,
upstream,
caller
retryable
boolean | null
execution_time
number

Seconds

execution_id
string | null

Handle for the stored full result

projection
object | null
defaults_applied
string[] | null
response_headers
object | null

Declared upstream response headers, e.g. usage-credit counters

truncated
boolean
response_meta
object | null
redaction
object | null
cost_cents
integer | null
balance_cents
integer | null
request_params
object | null