This listing identifies a third-party MCP server. MCPBundles is not affiliated with, sponsored by, or endorsed by the service or its operator unless stated on this page.
This server may ask you to sign in when your AI client connects.
Last probed Nov 16, 2026 · api.yourdatahub.co
25tools discovered
For AI agents — MCPBundles Directory API
For MCP client apps (human connect):
MCP connect URL: https://api.yourdatahub.co/mcp
Skill page: https://www.mcpbundles.com/skills/yourdatahub-mcp-ae6497bad8
Explore capabilities (25)
read 10
write 15
Upload Xero
6
List
3
Create
2
Describe
2
Get
2
Other capabilities
10
Current Client
read
current_client
Returns the name of the currently selected client/tenant.
Current Client — Returns the name of the currently selected client/tenant.
List Clients — List all clients/tenants available to you. Returns clientName for each. Use switch_client to switch to a different client.
Switch Client — Switch to a different client/tenants. All subsequent tool calls will use the selected client's data. Use list_clients to see available options.
List Views — List all data views and tables available to you. Returns view names, descriptions, and source types.
Describe View — Get the full schema for a specific view including column names, data types, and descriptions.
Query — Execute a read-only SQL query against your data. Only exposed views may be queried. Timeout is 5 minutes.
Search Help — Read-only keyword search over the dataSights product help guides: our own published documentation, stored inside dataSights and identical for every client. Returns text only. It reads no client business data, writes nothing, changes no settings, and makes no network requests. Use this when the user asks how to do something in dataSights: reporting group setup, mapping and eliminations, management reports, board packs, custom templates, FX rates. Each result carries the title, how the guide opens
Get Help Article — Read-only. Returns one dataSights product help guide in full, as markdown, from our own published documentation stored inside dataSights. Call it after search_help when the excerpt doesn't fully answer the question, so you can answer from the guide itself instead of handing over a link. It reads no client business data, writes nothing, and fetches nothing over the network. Pass the articleId from a search_help result; that result's page key or guide link also work, and are matched against the st
Create Report View
Get your MCP into directories
A working endpoint is step one. Directory coverage is the coordinated launch across ChatGPT, Claude, Cursor, the MCP Registry, and community indexes.
Yourdatahub is an MCP server at api.yourdatahub.co. MCPBundles discovered 25 tools on the live endpoint.
How do I connect Yourdatahub to my AI agent?
Use the MCP endpoint listed on this page in your MCP client configuration. One-click install pills support Claude, Cursor, VS Code, and other hosts. Copy the remote MCP URL if your client needs a manual entry.
How many tools does Yourdatahub provide?
Operate this server?
Request removal if you do not want Yourdatahub listed here, or claim the listing if you want to manage it on MCPBundles.
Operate Yourdatahub?
This server appears in the MCPBundles directory. Verify you operate it to take over the listing — name, description, logo, contact email, and skill content. We email a 6-digit code to a maintainer address your server publishes in /.well-known/security.txt or /.well-known/mcpbundles.json. Free, takes about a minute.
MCPBundles publishes this directory for MCP discovery. Except where we host or operate an offering, third-party services run under their own terms. Product and company names on this page are used in a descriptive, identifying way (including under nominative fair use where applicable); they remain the property of their owners. Nothing here grants you rights in those marks, and nothing here is an offer to sell a third party's services. Terms · Request removal
More in developer tools
Other MCP servers in this category from the directory index
— Create a new SQL report view in this client's database. Pass the full CREATE VIEW <name> AS SELECT ... statement. The view's SELECT body may only reference exposed views/tables. If a view with that name already exists, the tool automatically creates a new version (e.g. vw_X_V2, vw_X_V3) — the original view is never altered. The response tells you the actual name that was created (createdName, wasVersioned), so report that back to the user. Requires the 'Create Report View' permission.
Clone Board Pack And Kpi Report — Generate a new board pack by copying an existing PUBLISHED board pack (the template) into a new DRAFT for a specific reporting period. The original template is never modified and the new pack is always created as a Draft. Before calling this tool: (1) confirm the reporting group with the user (query the XeroConsolidationGroups view to list groups); (2) list the user's Published templates by querying the XeroConsolidationBoardPack table (WHERE XeroConsolidationGroupId = <group id> AND Status = 'P
Upload Xero Accounts — Upload (create new and/or update existing) Chart of Accounts records across one or more connected Xero files for the current tenant. **Send accounts in batches of 200 or fewer per call** — call this tool repeatedly for larger workloads. Each account row carries its own xeroFileName so a single call can target multiple Xero organisations — the server groups by file + (create vs update) and dispatches one batch per group. Accounts with a populated accountId are updated; accounts without an account
Upload Xero Invoices — Upload **invoices and supplier bills** (and auto-converted credit notes / refunds) to one or more connected Xero files for the current tenant. **Use this tool whenever a user asks to upload invoices, customer invoices, bills, supplier bills, or supplier invoices** — Xero treats them as the same record type, distinguished by the `type` field (ACCREC = Customer Invoice; ACCPAY = Supplier Invoice / Bill). **Send up to 200 rows per call** — chunk client-side and call repeatedly for larger workloads.
Upload Xero Manual Journals — Upload manual journals to one or more connected Xero files for the current tenant. **Send manual journals in batches of 200 or fewer per call** — call this tool repeatedly for larger workloads. Each manual journal carries its own xeroFileName so a single batch can target multiple Xero organisations — the server groups by file and dispatches per file. Each journal must balance to 0 (debits = credits, where debits are positive lineAmounts and credits are negative — standard Xero convention). Retur
Upload Xero Purchase Orders — Upload purchase orders to one or more connected Xero files for the current tenant. **Send purchase orders in batches of 200 or fewer per call** — call this tool repeatedly for larger workloads. Each purchase order carries its own xeroFileName so a single batch can target multiple Xero organisations — the server groups by file and dispatches per file. Returns per-file summaries and counts. Requires the 'Upload Xero Purchase Orders' permission.
Upload Xero Contacts — Upload (create new and/or update existing) contacts to one or more connected Xero files for the current tenant. **Send contacts in batches of 200 or fewer per call** — call this tool repeatedly for larger workloads. Each contact carries its own xeroFileName so a single batch can target multiple Xero organisations — the server groups by file + (create vs update) and dispatches one batch per group. Contacts with a populated contactId are updated; contacts without a contactId are created. Returns p
Upload Xero Attachments — Upload file attachments (e.g. PDF receipts, supporting documents) against existing Xero records. Supports Invoice, Receipt, CreditNote, RepeatingInvoice, BankTransaction, BankTransfer, Contact, Account, ManualJournal, and Quote records — Purchase Orders are not supported (Xero's own API for that record type has no attachment endpoint in the version this integration uses). **Send attachments in batches of 20 or fewer per call, and no more than 50MB of total file content per call** — call this too
Trigger Xero Sync — Trigger an asynchronous Xero data sync. **Before calling this tool you MUST first fetch the available options and present them to the user — do not ask the user to recall organisation names from memory.** The sync runs against live Xero data, can take several minutes, and re-runs the same heavy import the Angular 'Sync data' modal triggers, so explicit confirmation is required.
**Discovery workflow (run this BEFORE calling trigger_xero_sync):**
1. Call the `query` tool with `SELECT DISTINCT Xer
Get Xero Sync Status — Return the current Xero sync status for one or more Xero organisations, one result row per organisation. Per-organisation status (SyncStatus + LastSyncedDateTimeUtc) is read from the XeroConsolidationGroupAndEntitiesContext view. The top-level `overallStatus` rolls up every matched organisation's SyncStatus plus the Account Transactions import views; when no organisation matched (check `unmatchedOrganisations`) it is UNKNOWN, never a sync verdict. When Account Transactions is enabled for the ten
List Editable Tables — List user-data tables in the current client's database that can be created, altered, or have their rows replaced via MCP. Returns each table with its current columns (column name + SQL data type). Connector-imported tables (e.g. XeroOrganisation, Xero/GoogleSheets source tables), connector mapping tables (e.g. AccountType, XeroMappingLookup), system tables (__MigrationHistory, sysdiagrams), and views are intentionally excluded — those cannot be edited via MCP. Requires the 'Edit User Data via MC
Describe Editable Table — Get the columns and SQL data types for a single editable table. Use this before calling add_table_column / edit_table_column / save_table_data so you know the existing schema. The table must appear in list_editable_tables — connector and system tables are rejected with a 403. Requires the 'Edit User Data via MCP' permission.
Create User Table — Create a new user-data table in the current client's database. An [Id] bigint IDENTITY column is added automatically unless the caller already supplies a column literally named 'Id'. Table and column names must match ^[A-Za-z_][A-Za-z0-9_]*$ (letters/digits/underscores, not starting with a digit). Column dataType uses C#-style names: STRING, INT16, INT32, INT64, DECIMAL, SINGLE, DOUBLE, BOOLEAN, DATETIME — STRING maps to nvarchar(length) (defaults to 200, becomes nvarchar(max) if length >= 4000)
Add Table Column — Add a single new nullable column to an existing editable user-data table (ALTER TABLE ADD COLUMN). The target table must appear in list_editable_tables. Column dataType uses the same C# data-type vocabulary as create_user_table. Requires the 'Edit User Data via MCP' permission.
Edit Table Column — Rename and/or change the data type of an existing column on an editable user-data table. Internally runs sp_rename (only if oldColumnName != columnName) followed by ALTER TABLE ALTER COLUMN. WARNING: changing a column's data type can fail if existing rows can't be converted — SQL Server may roll back the alter. The target table must appear in list_editable_tables. Requires the 'Edit User Data via MCP' permission.
Delete Table Column — Drop a single column from an editable user-data table (ALTER TABLE DROP COLUMN). Destructive: row values in that column are lost permanently. The target table must appear in list_editable_tables. Requires the 'Edit User Data via MCP' permission.
Save Table Data — Replace ALL rows of an editable user-data table with the provided JSON rows. WARNING: this is destructive — the existing rows are truncated before the new rows are bulk-inserted. To append rather than replace, fetch existing rows via the read-only 'query' tool first and merge them into the rows argument. Column names in each row object must match the table's existing columns exactly (use describe_editable_table). Values are coerced to each column's SQL data type — empty/whitespace strings become
MCPBundles probed 25 tools on the live server. The tool list on this page reflects what was discovered at the last refresh — connect your client to see the full set available to your session.
What authentication does Yourdatahub require?
Yourdatahub may require signing in to the provider before tools can run. Connect through MCPBundles or your MCP client and complete any provider login when prompted.
Don't want this listed?
Request removal from the MCPBundles directory. We stop publishing this listing on mcpbundles.com.
MCPBundles is an independent platform built on the open Model Context Protocol standard. MCPBundles is not affiliated with, sponsored by, or endorsed by Anthropic PBC.