// SCAN REPORT

Humaans

33 tools. 0 can modify or destroy data without limits.

Read-only server. Low risk, but rate limits prevent runaway API costs.

Last updated: 3 Jul 2026

0 can modify or destroy data

33 read-only

33 tools total

Community server · catalogue entry verified 03/07/2026

How to control Humaans ↓

TOOL MAP

What Humaans exposes to your agents

Read (33) Write / Execute (0) Destructive / Financial (0)

Running more than one server? Check your whole stack →

THE RISK

What can go wrong

Even read-only tools carry cost. An agent in a retry loop can make thousands of API calls per minute, exhausting rate limits and running up bills.

POLICY

How to control Humaans

PolicyLayer is an MCP gateway — it sits between your AI agents and Humaans, and nothing reaches the server without passing your rules. These are the rules we recommend:

Cap read operations

{
  "count_reports": {
    "limits": [
      {
        "counter": "count_reports_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Humaans — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON HUMAANS →

Instant setup, no code required.

FULL CATALOGUE

All 33 Humaans tools

READ 33 tools

Read count_reports Count reports for a person. recursive=False gives direct reports only; True gives the full subtree size. Read find_person_by_email Find one person by exact email match. Returns the person object, or null if not found. Read get_company Retrieve a company by id. Read get_compensation Retrieve a single compensation record by id. Read get_compensation_type Retrieve a single compensation type by id. Read get_direct_reports List direct reports of the given person. Reads the directReports array on the person record. Read get_job_role Retrieve a single job role by id. Read get_me Return the authenticated user for the current API token. Read get_person Retrieve a single person by their Humaans id. Employee-scoped custom field values are merged onto the person o Read get_reporting_chain_down Build the subtree of reports under the given person, up to max_depth levels. Uses a single fetch of all people Read get_reporting_chain_up Walk the management chain upward from the given person. Returns an ordered list starting with the person and e Read get_time_away Retrieve a single time-away record by id. Read get_token_info Return metadata about the current API token (scopes, owner, etc.). Read list_bank_accounts List bank accounts. Optionally filter by personId. Read list_companies List all companies in the Humaans account. Read list_compensation_types List all compensation types configured in the account (salary, bonus, commission, equity, etc.). Read list_compensations List compensation records (salary, bonus, etc.). Optional filters: personId, typeId. Read list_custom_fields List all configured custom fields. Read list_custom_values List custom field values. Optionally filter by personId. Read list_documents List documents. Optionally filter by personId. Read list_emergency_contacts List emergency contacts. Optionally filter by personId. Read list_equipment List equipment assigned to people. Optionally filter by personId. Read list_job_roles List job roles (historical and current job assignments). Optionally filter by personId. Read list_locations List all configured work locations (typically countries/regions for remote teams). Read list_people List people (employees). Optional filters: email, locationId, status. Paginated via limit/skip (max 250). Note Read list_public_holiday_calendars List all configured public holiday calendars. Read list_public_holidays List public holidays. Optional filters: calendarId, year. Read list_spaces List all physical office spaces. Read list_time_away List time-away records. Optional filters: personId, startDate, endDate (YYYY-MM-DD). Read list_time_away_allocations List time-away allocations. Optionally filter by personId. Read list_time_away_policies List all time-away policies. Read list_time_away_types List all time-away types (vacation, sick, parental, etc.). Read search_people_by_name Case-insensitive substring search over firstName/lastName/preferredName across all people. Pulls the full peop

FAQ

Questions about Humaans

Is the Humaans MCP server safe to use without restrictions? +

The Humaans server is primarily read-only with 33 read tools. While it cannot modify data, an agent in a retry loop can make thousands of API calls per minute, exhausting rate limits and running up costs. Rate limiting is still recommended.

How many tools does the Humaans MCP server expose? +

33 tools across 1 categories: Read. 33 are read-only. 0 can modify, create, or delete data.

How do I enforce a policy on Humaans? +

Register the Humaans MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Humaans tool call.

Deterministic rules across all 33 Humaans tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON HUMAANS →

Instant setup, no code required.

33 Humaans tools catalogued and risk-classified — across an index of 43,000+ MCP servers.