TeamOhana MCP Server

v0.6.0 beta

The TeamOhana Model Context Protocol (MCP) server lets AI models and agents access and interact with your TeamOhana data through a standardized interface. Connect it to Claude, ChatGPT, Cursor, or any other MCP-compatible tool to query your headcount data, hiring pipeline, employee ledger without leaving your AI Agent.

Getting Started

Add this remote MCP endpoint to your AI client.

Claude.ai

  1. Open Settings, then Connectors.
  2. Add a custom connector. Enter the TeamOhana name and MCP endpoint.
  3. Complete the TeamOhana OAuth sign-in and consent flow.
  4. Enable TeamOhana from the Connectors menu in a conversation.

Team and Enterprise users may need an organization owner to enable custom connectors first.

ChatGPT.com

  1. Open Settings, then Apps.
  2. Enable developer mode when your plan or workspace makes it available.
  3. Create a custom MCP connector. Enter the TeamOhana name and MCP endpoint.
  4. Complete the TeamOhana OAuth sign-in and consent flow.
  5. Enable TeamOhana for the conversation.

ChatGPT MCP support and workspace controls vary by plan and administrator settings.

Others

Add the URL in the appropriate MCP config settings section.

Available tools

Once you've connected the TeamOhana MCP server, just describe what you want in plain language and your MCP client will pick the right tools and run them for you.

Below is the list of available tools. TeamOhana will be adding more tools over time, including write actions. To request a tool or capability, please contact TeamOhana Support.

MCP tool inputs and outputs may change without notice. If you need a stable contract for either, build against our public API instead.

Headcounts

get_headcount_stats

Get aggregate headcount statistics across a hiring plan. Choose count, cost_fy, or cost_annualized values for high-level totals, status breakdowns, and hiring progress.

get_headcounts

Get individual headcount requisitions and their current hiring progress. Use this when you need to review specific roles rather than an aggregate summary.

Employees

get_employees

Get employee records using workforce filters such as department, location, manager, or employment status.

Your Profile

whoami

Return the authenticated user’s TeamOhana profile, including name, email, role, job title, division, and department.

Reference Data

list_reference_data

Lists the canonical reference-data sets available to your TeamOhana account. Use this first when you need to find valid values for a filter or another tool input.

Available reference data

  • departments
  • locations
  • hiring_plans
  • team_members
  • budget_envelope
  • job_roles_and_levels

get_reference_data

Returns one canonical data set, such as departments, locations, hiring plans, team members, budget settings, or job roles and levels. Call list_reference_data to choose a set.

TAQL Schema

get_taql_schema_index

Returns the general TAQL query guide and the tables currently available to your account. Use it before writing a TAQL query or choosing a table for detailed schema documentation.

get_taql_schema_for_table

Returns the full schema documentation for one table. Get the table name from get_taql_schema_index, then use this tool before querying that table with taql_query.

Analytics Queries via TAQL

taql_query

TAQL is TeamOhana's Abstract Query Language. It is a dialect of ANSI SQL that's carefully constructed to provide access to all of your data in TeamOhana while keeping in mind all aspects of Access Control, Permissions and query safety. TAQL provides a simple interface for AI agents to pull your data for analysis when pre-existing MCP tools won't suffice.

Reference data and schema tools

Use list_reference_data and get_reference_data to find canonical TeamOhana values before filtering data. Use get_taql_schema_index for TAQL guidance and available tables, then get_taql_schema_for_table before querying a table.

Rate limits

TeamOhana MCP enforces per-minute rate limits for each authenticated organization, user, and tool. This keeps the service reliable for everyone.

What to do if you're rate-limited

Most workflows won't hit these limits. If you receive a rate-limit error, wait for the retry period shown in the response before trying again, or ask your MCP client or AI agent to run fewer operations in parallel.

FAQs

Can the MCP server access data I cannot see in TeamOhana?

No. The MCP server uses user-level OAuth, which means it authenticates as you and inherits your existing TeamOhana ABAC & permissions. It cannot return headcounts, compensation or other records you do not already have access to in TeamOhana.

Do other users see the data I query through the MCP server?

No. Each user connects their own account through a separate OAuth flow. Queries and responses are scoped to your individual session and your TeamOhana permissions.

Can I use the MCP server with a client not listed here?

Yes. The TeamOhana MCP server is standards compliant & client-agnostic and works with any MCP-compatible tool. See Getting Started for the endpoint and complete the OAuth flow when prompted.

What should I do if a tool is not working as expected?

Please contact TeamOhana Customer Support team or your TeamOhana administrator. Include as much detail as possible about what you asked and what the server returned.