🎸New!Tender Monitoring with Midesk's New TED Online Integration

MCP — Market data modeling inside MCP

MCP namespace

Market data modeling inside MCP

Stand up reusable data types, tables, and pipelines directly from your assistant.

Data namespace tools expose the Midesk repository model. Define a schema, push rows in bulk, or list existing assets so that your AI can blend qualitative monitoring with quantitative facts.

Give Claude or ChatGPT a governed data backbone to answer finance-grade questions.

  • Introspect existing data types and model versions before writing.
  • Bulk-load clean, structured datapoints with audit trails.
  • Fetch tables into the chat context for analysis or reporting.

Available MCP tools

Ask your assistant to call these functions by name. Each tool mirrors the behaviour available in the Midesk interface so your automation stays compliant and auditable.

Add Data Points Bulk

data__add_data_points_bulkData Models & Tables

Bulk import: identifier|period|start-date|values[|source]. Identifier=DataType ID or Name. Values are raw (e.g., 133300000 not 133.3M). LLM hint: validate with list tools first; prefer IDs to avoid collisions.

Parameters

  • model_id

    string

    Required
  • data

    string

    Required

    Multi-line: Data Type ID or Name (Quick Create)|period(y,q,m,w,d)|start-date(Y-m-d)|multiple values separated by semicolons(each value is a full raw values, such as 133300000 instead of 133.3M)|optional source. Example: `329289223|y|2024-01-01|100000000;200000000;300000000|SEC Filing Internal KPIx|y|2024-01-01|300000;200000;500000|SEC Filing`

  • mode

    string (strict, lenient, force)

    strict=fail on issues, lenient=auto-create and fix, force=import everything possible

    Allowed values: strict, lenient, force

Create Or Update Model

data__create_or_update_modelData Models & Tables

Create or update tracked entities (companies/products/markets). LLM hint: ask for missing name on create; on update, pass id only for changed fields.

Parameters

  • id

    string

    ID of existing model to update (leave empty to create new)

  • name

    string

    Name of the entity (e.g., 'Netflix', 'Stanford University', 'TED Online')

  • description

    string

    Description of the entity being tracked

  • currency

    string

    Default currency for financial data (e.g., USD, EUR, JPY)

  • website_url

    string

    Primary website URL

  • linkedin_url

    string

    LinkedIn profile URL

  • youtube_id_or_username

    string

    YouTube channel ID or username

  • twitter_handle

    string

    Twitter/X handle (without @)

Get Data Table

data__get_data_tableData Models & Tables

Generate KPI tables and comparisons. LLM hint: prefer exact IDs; if missing, call list tools first. Supports json or markdown_table output.

Parameters

  • model_ids

    array

    Required

    Array of model IDs to include in the table

    Array items

    • [item]

      string

  • data_type_ids

    array

    Array of data type IDs to include (leave empty for all)

    Array items

    • [item]

      string

  • start_date

    string

    Required

    Start date for the data range (YYYY-MM-DD)

  • end_date

    string

    Required

    End date for the data range (YYYY-MM-DD)

  • period

    string (d, w, m, q, y)

    Required

    Time period for grouping: d=day, w=week, m=month, q=quarter, y=year

    Allowed values: d, w, m, q, y

  • aggregation_method

    string (sum, average, min, max)

    Options: sum, average, min, max (default: sum)

    Allowed values: sum, average, min, max

  • output_format

    string (markdown_table, json)

    Output format: markdown_table or json (default: markdown_table)

    Allowed values: markdown_table, json

List Data Types

data__list_data_typesData Models & Tables

List KPI types with optional filtering. LLM hint: discover/verify IDs and value_type before data entry.

Parameters

  • q

    string

    Search query using %ilike% to filter data types by name.

  • value_type

    string (text, date, number, boolean, money, json)

    Filter by specific value type

    Allowed values: text, date, number, boolean, money, json

List Models

data__list_modelsData Models & Tables

List all data models (repositories). Returns name, description, currency, and data types. LLM hint: use this to discover IDs before writing.

Parameters

  • search

    string

    Search term to filter models by name

Manage Data Type

data__manage_data_typeData Models & Tables

Create or update KPIs (data types): find_or_create (default), create_only, update_only. LLM hint: keep value_type stable; use description to explain intent.

Parameters

  • name

    string

    Required

    Name of the data type

  • value_type

    string

    Required

    Type of values this data type will store (text, date, number, boolean, money, json)

  • description

    string

    Description of what this data type represents

  • operation

    string (find_or_create, create_only, update_only)

    Operation mode: find_or_create (default), create_only, or update_only

    Allowed values: find_or_create, create_only, update_only

Last refreshed from MCP: Sep 22, 2025, 3:45 AM

Playbook ideas

Use these prompts as starting points. They combine multiple tools from this namespace with other MCP capabilities to deliver analyst-grade output.

Provision a new KPI repository

Call `data__create_or_update_model` to define measures and dimensions, then sync sample records with `data__add_data_points_bulk`.

Audit available data sources

Combine `data__list_models` and `data__list_data_types` so your assistant can recommend reuse instead of recreating models from scratch.

Pull tables into your working memory

`data__get_data_table` returns rows that can be summarized, charted, or exported without opening another tool.

Keep exploring

Hop back to the MCP catalog to combine these tools with monitoring, data, and reporting workflows.

View all MCP areas

Need guided onboarding?

Our team can help you script MCP playbooks tailored to your processes.

See our solution in action

Let's discuss your particular Market & Competitive Intelligence needs and see how Midesk can address them.

© 2019 - 2025 Midesk UG (haftungsbeschränkt)