Skip to content
Scalekit Docs
Talk to an Engineer Dashboard

Connect AI agents to the MT Newswires MCP server

Vendor MCP
Open markdown

The MT Newswires MCP connector routes your AI agent's tool calls to MT Newswires's own MCP server through Scalekit. Each user signs in to MT Newswires once, and Scalekit stores and refreshes their tokens, so your agent never handles credentials. It comes with 6 tools.

Tools
6
What they doRead · write · destructive
4 · 1 · 14 read1 write1 destructive
Users sign in with
OAuth app
Scalekit's or your own

Setup

  1. Install the SDK

    Terminal window
    npm install @scalekit-sdk/node dotenv

  2. Set your credentials

    Add your Scalekit credentials to your .env file. Find values in app.scalekit.com > Developers > API Credentials.

    .env
    SCALEKIT_ENVIRONMENT_URL=<your-environment-url>
    SCALEKIT_CLIENT_ID=<your-client-id>
    SCALEKIT_CLIENT_SECRET=<your-client-secret>

  3. Create the MT Newswires MCP connection

    In AgentKit > Connections, create a MT Newswires MCP connection. The name you give it is the connection_name your code passes. See Configure connections.

    Scalekit credentials are available for MT Newswires MCP server, so you don't need to register an OAuth app.

  4. Authorize a user and make your first call

    quickstart.mts
    import { ScalekitClient } from '@scalekit-sdk/node'
    import 'dotenv/config'
    import { createInterface } from 'node:readline/promises'
    

    const scalekit = new ScalekitClient(
      process.env.SCALEKIT_ENVIRONMENT_URL,
      process.env.SCALEKIT_CLIENT_ID,
      process.env.SCALEKIT_CLIENT_SECRET,
    )
    const actions = scalekit.actions
    

    const connector = 'mtnewswiresmcp'
    const identifier = 'user_123'
    

    // Generate an authorization link for the user
    const { link } = await actions.getAuthorizationLink({ connectionName: connector, identifier })
    console.log('Authorize MT Newswires MCP:', link)
    const rl = createInterface({ input: process.stdin, output: process.stdout })
    await rl.question('Press Enter after authorizing...')
    rl.close()
    

    // Make your first call
    const result = await actions.executeTool({
      connector,
      identifier,
      toolName: 'mtnewswiresmcp_current_date',
      toolInput: {},
    })
    console.log(result)
    Terminal window
    npx tsx quickstart.mts

    Each user signs in once. See Authorize a user for the full flow and statuses.

Tools

Pass the exact name to execute_tool
Try in PlaygroundRequest a tool
  • mtnewswiresmcp_current_dateProvides the current date.Read-only

    Current Date

    Provides the current date. Use this to ground relative date references (for example "today" or "this week") before searching datasets or fetching data.

    Inputs

    This tool takes no inputs.

  • mtnewswiresmcp_fetchRetrieve rows of data from a viaNexus / MT Newswires dataset.Read-only

    Fetch Dataset Data

    Retrieve rows of data from a viaNexus / MT Newswires dataset. Use the Search tool first to discover the dataset name and its supported parameters, then pass them here. Returns the dataset fields and their values.

    Inputs

    dataset_namestringrequired
    The dataset name to retrieve data from, as returned by the Search tool.
    countrystring
    Country code for country-keyed datasets that include a {country} path parameter (e.g. "US", "CA", "GB").
    endpointstring
    The dataset endpoint. Only "data" is supported.one of datadefault data
    filterstring
    Optional filter expression applied to the dataset query.
    from_datestring
    Start date of a date range (YYYY-MM-DD).
    lastinteger
    Lookback limit passed to the viaNexus API as the `last` query parameter. Interpretation is dataset-specific (days, bars, records, etc.).
    limitinteger
    Hard cap on the number of rows returned, applied client-side after the upstream fetch. Use for a deterministic row count (for example last=1, limit=3 on an intraday dataset returns 3 bars).
    on_datestring
    Retrieve data as of a single date (YYYY-MM-DD).
    productstring
    The product (workspace) the dataset belongs to.one of COREEDGEdefault CORE
    regionstring
    Region code for region-keyed datasets that include a {region} path parameter.
    subkeystring
    Optional sub-key path parameter for datasets that require one.
    symbolsstring
    Comma-delimited financial instrument identifiers. Supports symbol, FIGI, ISIN, and LEI (e.g. "MSFT", "AAPL,NVDA", "BBG000BPHFS9", "US5949181045").
    to_datestring
    End date of a date range (YYYY-MM-DD).
  • mtnewswiresmcp_get_rulesGet all alert rules associated with the user.Read-only

    Get Rules

    Get all alert rules associated with the user. Each rule includes its id, name, dateCreated, isActive, passed, failed, and conditions.

    Inputs

    This tool takes no inputs.

  • mtnewswiresmcp_create_ruleCreate an alert rule for one or more datasets that sends an email when the conditions are met.Write

    Create Rule

    Create an alert rule for one or more datasets that sends an email when the conditions are met. Supports single-dataset and cross-dataset rules, multiple conditions combined with AND/OR logic, and field-to-field comparisons (for example moving-average crossovers).

    Inputs

    conditionsarrayrequired
    List of structured condition objects evaluated by the rule.
    condition_typestring
    Whether all or any of the conditions must be met for the rule to trigger.one of allanydefault all
  • mtnewswiresmcp_delete_ruleDelete an alert rule by its id.Destructive

    Delete Rule

    Delete an alert rule by its id. Use the Get Rules tool to find the id of the rule to delete.

    • Idempotent

    Inputs

    idstringrequired
    Identifier of the rule to delete, as returned by the Get Rules tool.
All 37 in Accounting & Finance