Niches · HR & employee operations

Answer who someone is and where they sit

One company's docs show a full fit.

1companies, full fit
7companies, fit with a limit
12companies carry the tag
24share of the category's work
4first-hand accounts

What counts as done

Name, title, department, manager and work contact for each match from one search call, with no field returned that the user's own HR permissions hide (pay, personal address, ID numbers).

How agents ask for it: who is Priya's manager, who's in the design team, find the person who runs payroll, what's Sam's job title

Does the job 1

The docs show it meets the test above, and nothing we read says otherwise.

ListingWhy
Rippling B
People Center, Inc. dba Rippling
The MCP runs as the connected employee, with search_people among its tools and no SSNs, home addresses or tax IDs exposed; REST tokens see the intersection of the owner's permissions, with hidden fields listed in __meta.redacted_fields. Workers carry role, manager and department. source

Does the job, with a limit 7

It does the job, but something in the docs or a user's account will get in an agent's way. The limit is named in each row.

ListingWhy
BambooHR C
Bamboo HR LLC
GET /api/v1/employees takes filter, fields and cursor paging, so name, title, department, supervisor and work email come in one call, and the MCP enforces the user's own permissions. Restricted fields drop silently, and acc-01 got every column but the id back null. source
Deel BB
Deel, Inc.
GET /people takes search, teams and fields with offset paging, so matching people come back in one call, and the MCP runs on the user's OAuth consent. Whether an organisation token hides fields the user's role can't see is not documented. source
Factorial B
Everyday Software, S.L.
Reads all Employees returns a payload restricted to the caller's permission group, and a User Token works as one employee. The list filters by ids, not by name or team, and team membership comes from a separate endpoint, so one search call is not enough. source
HiBob D
Hi Bob Ltd.
POST /people/search returns chosen fields for many employees in one call, with field-level permissions applied. Calls run as an API service user, not the employee, so the token sees what its permission group allows, and unpermitted fields drop from a 200 with no warning. source
Humaans D
Humaans Software UK Ltd
GET /api/people pages with $limit and $skip, and a public:read token sees only company-public profile data while private:read adds banking and leave reasons, so scope caps what leaks. No name or team search parameter on people was found, and manager lines come through org units and reportingTo. source
Remote BB
Remote Europe Holding B.V.
GET /v1/employments filters by name, email and status with paging, but job title and manager come from separate endpoints (employment job, company structure nodes), so one search call doesn't return all fields. Customer API tokens carry chosen scopes, not the user's own HR permissions. source
Zoho People D
Zoho Corporation Private Limited
Search Records Based on Record Values queries the employee form by a field value, up to 200 records a call, returning the form's columns. OAuth tokens act as the authorising user, but the pages read don't say whether fields hidden by the user's role are withheld. source

What stops agents finishing

  • token sees fields the user cannot (or none at all, acc-01)
  • directory search not exposed, only full employee lists

Around it

Before: chat.user-question. After: productivity.post-message, scheduling.find-time.

Where this comes from

Weight 24 of 100 in HR & employee operations: 4 of 13 accounts (AI memory and assistant connectors for BambooHR and Rippling, a scoped directory plugin, a custom report returning nulls); counts are low, weight set by hand as the commonest agent request in vendor MCP docs

The same as data: /api/v1/use-cases/hr.directory-lookup.json, or the MCP tool get_use_case with id hr.directory-lookup. Other jobs in this category: /api/v1/niches?category=hr.

Draft, read 2026-11-15 from public docs and first-hand accounts, not yet reviewed by a person. A mark says what the docs show, not what a run measured.

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.