# Namely MCP connector

Connecting Namely to Elaichi lets Claude, ChatGPT, Cursor, Microsoft Copilot and the Elaichi Agent look up and update employee profiles, teams, groups, folders and company events, with each person signed in as themselves and every call logged.

Source: https://elaichi.ai/connectors/namely/

## Facts

| | |
| --- | --- |
| Application | Namely |
| Category | HRIS |
| AI tools | 54 |
| Authentication | OAuth or API key |
| Bring your own OAuth app | Yes |
| MCP endpoint | https://api.elaichi.ai/mcp |
| Works with | Claude, ChatGPT, Cursor, Microsoft Copilot, any MCP client, and the Elaichi Agent |
| Tools advertised by name | No. Connected tools are never listed one by one, however few there are. The endpoint advertises `search_tools` and `execute_tool` instead |

## What you can ask once Namely is connected

- List everyone on the Engineering team with their start dates
- Create a profile for Priya Shah starting Monday in Marketing
- Add a company event for the all-hands next Thursday at 10

## Connect Namely in Elaichi

This happens once for the organization, before any client is involved.

1. Open Connections, choose Add connection, and pick Namely.
2. Optionally set Share with, then press Connect.
3. Supply your own Namely app, then approve. Namely needs an OAuth app you register yourself, so bring its client ID and secret. One person does this once for the organization.

Credentials are vaulted and nobody, including the AI, reads them back. The connection becomes a toolbox immediately, so you can curate which Namely tools are exposed, rename them, or freeze arguments before anyone points a client at it.

## Namely MCP connector for Claude

Endpoint: https://api.elaichi.ai/mcp

1. Open Customize, then Connectors.
2. Press Add.
3. Name it, paste the MCP server URL, then Continue.
4. Sign in and approve.

On Team and Enterprise, an Owner adds it once. Everyone else turns it on for themselves.

## Namely MCP connector for Claude Code

Endpoint: https://api.elaichi.ai/mcp

1. In a terminal, run `claude mcp add` with the endpoint.
2. Start Claude Code and run `/mcp`.
3. Pick elaichi, then sign in and approve in the browser.

```bash
claude mcp add --transport http elaichi --scope user https://api.elaichi.ai/mcp
```

Use `--scope project` instead to share it with the repository through `.mcp.json`.

## Namely MCP connector for ChatGPT

Endpoint: https://api.elaichi.ai/mcp

1. Open Plugins, then press the + button.
2. Name it and paste the endpoint into Server URL.
3. Leave Authentication on OAuth, then tick the risk acknowledgement.
4. Press Create, then sign in and approve.

Works on the web. The plugin directory lives at chatgpt.com/plugins.

## Namely MCP connector for Cursor

Endpoint: https://api.elaichi.ai/mcp

1. Open `~/.cursor/mcp.json`.
2. Add the endpoint under `mcpServers`.
3. Reload Cursor, then sign in and approve.

Set up per machine, so repeat it on each computer you work from.

## Namely MCP connector for Microsoft Copilot

Endpoint: https://api.elaichi.ai/mcp

1. In Copilot Studio, open your agent, then Tools, Add a tool, New tool and Model Context Protocol.
2. Paste the endpoint into Server URL, choose OAuth 2.0, then Dynamic discovery, and press Create.
3. Create a new connection, sign in and approve, then press Add to agent.
4. Under Channels, open Teams and Microsoft Copilot and make the agent available in Microsoft Copilot.

Microsoft Copilot was called Microsoft 365 Copilot. Keep the tool on end-user credentials, so each person signs in as themselves.

## Connect Namely to any MCP client

Endpoint: https://api.elaichi.ai/mcp

1. Add the endpoint as a remote MCP server.
2. Sign in and approve.

The Elaichi Agent already has these tools, with nothing to set up.

## What the consent screen decides

Every scope the client asks for starts ticked except "Delete things", which you tick yourself. Calling a Namely tool needs "Use your connected apps". Over MCP there is no trusted place to confirm a write in the moment, so the consent screen is the standing approval rather than a formality. Think hard before granting Use your connected apps, which can also delete in connected apps and cannot be undone.

## What teams do with Namely through Elaichi

### Find who sits on which team today

HR. Ask for everyone on a team or in a group and get the current roster from Namely, with the profile details you need before a review or a reorg.

### Set up a new hire's profile

People Ops. Create the Namely profile for a new starter from the offer details you already have, then confirm it looks right before their first day.

### Catch a profile up after a change

Managers. After a promotion, a title change or a move to a new manager, update the person's Namely profile in one ask instead of clicking through the form.

### Pull a roster for an access review

IT. List every active profile in Namely, grouped by team or department, so you can check it against the systems people still have access to.

### Put the all-hands on the company calendar

Office. Create a Namely event for the all-hands, the holiday party or the fire drill, and pull up what is already scheduled before picking a date.

### Keep the policy folder tidy

Internal comms. See which documents live in each Namely folder, add a folder for a new policy set, and remove resources that are out of date.

## Elaichi vs Zapier MCP vs Composio for Namely

All three can connect Namely to an AI assistant, and all three have admin controls. They differ in where access lives and how you pay.

| What to check | Elaichi | Zapier MCP | Composio |
| --- | --- | --- | --- |
| Where the AI connects | One address for the whole organization. Endpoint: https://api.elaichi.ai/mcp | A server per member, created at sign-in. | An MCP endpoint per team, or an SDK. |
| Control over Namely tools | Allow or restrict single Namely tools, per role or user. | App and action restrictions on the account. | Role permissions, down to the action. |
| Record of calls | One audit entry per Namely call. | A History tab of tool calls. | A log of every tool call. |
| Single sign-on | SAML or OIDC, plus SCIM, on Gold. | SAML on Enterprise. | SAML and OIDC on Enterprise. |
| Price | Free for one person; $15 per user per month on Gold. | 2 tasks per successful call. | Billed per tool call. |

Sources: Zapier MCP [docs](https://docs.zapier.com/mcp/get-started/quickstart), [security](https://docs.zapier.com/mcp/manage/security), [usage](https://docs.zapier.com/mcp/features/usage); Composio [docs](https://docs.composio.dev/docs/composio-connect), [gateway](https://composio.dev/mcp-gateway), [enterprise](https://composio.dev/enterprise), [pricing](https://composio.dev/pricing). Checked September 2026.

Longer take: [Zapier MCP alternative](/blog/zapier-mcp-alternative/) and [when you don't need an MCP gateway](/blog/when-you-dont-need-an-mcp-gateway/).

## Frequently asked questions

### How do I connect Namely to Claude?

Connect Namely in Elaichi first, then in Claude go to Customize, then Connectors, then Add, and paste https://api.elaichi.ai/mcp. Namely asks for an OAuth application registered inside your own Namely account, so an admin brings a client ID and secret once, or you can connect with a Namely API key instead. After that, each person signs in to Namely as themselves and nobody else handles a credential.

### Does Namely work with ChatGPT and Cursor as well as Claude?

Yes. Once Namely is connected in Elaichi, the same endpoint, https://api.elaichi.ai/mcp, works in Claude, ChatGPT, Cursor, Microsoft Copilot, any other MCP client and the Elaichi Agent. You connect Namely once and every client picks it up.

### What can an AI agent actually do with my Namely data?

With Namely connected, an agent can look up an employee's profile, list who is on a team or in a group, create or update a profile, browse folders and the documents in them, and add or remove company events. Short, concrete asks such as "list everyone on the Support team" work better than long paragraphs.

### Does connecting Namely give the AI access to everyone's records?

No. Every call to Namely runs as the person who signed in, so an agent sees only the profiles, groups, folders and events that person can already see in Namely. Elaichi can narrow that access further with roles and restrictions, and it can never widen it beyond what Namely already allows.

### Can my team share one Namely connection?

Yes. One person connects Namely in Elaichi and shares it with a team, and nobody else ever handles the client ID, secret or API key. Each teammate still signs in as themselves, so the audit log names the actual person behind every Namely lookup or change.

### Can I stop an agent from deleting or changing things in Namely?

Yes. Restrictions in Elaichi work per action, so you can restrict deleting folders or events, or updating profiles, for a role or for one person while leaving lookups open. A restricted Namely action still appears in Elaichi's tool search, flagged as restricted, but no client can run it, whatever the prompt says.

### What happens to a Namely connection when someone leaves?

Offboarding a person in Elaichi ends their access to Namely through every client at once. A Namely connection shared with a team keeps working for everyone else. If you want it gone entirely, disconnecting Namely once in Elaichi removes it from Claude, ChatGPT, Cursor, Microsoft Copilot and every other client.

### Does the Namely MCP connector work with Gemini, Codex, Claude Code or other MCP clients?

Yes. Namely is reached over the same MCP endpoint every client uses, so anything that speaks MCP can call it — Gemini, Codex, Claude Code, Windsurf, Cline, Zed and OpenCode among them — alongside Claude, ChatGPT, Cursor, Microsoft Copilot, and the Elaichi Agent. The tools on offer and the access behind them are identical whichever client asks. Only the setup screen differs.

### Is Elaichi an alternative to Zapier MCP for Namely?

Yes. Both let Claude, ChatGPT or Cursor use Namely. Zapier MCP fits a team that already automates in Zapier, since each person signs in and acts as themselves in that account. Elaichi fits when IT wants one address for the whole company, per-tool rules by role, and a record of every Namely call.

### How is Elaichi different from Composio for Namely?

Composio gives AI agents tools and sign-in handling across 1,000+ apps, for developers building agents or people using an assistant, billed per tool call. Elaichi gives a company's own people governed access to Namely: one address, restrictions per role or user, and $15 per user per month. Both have role permissions and a log of every call.

## All 54 Namely tools

Every tool below is callable through https://api.elaichi.ai/mcp once Namely is connected, subject to the toolbox it is in and the restrictions on the caller.

- **List all Namely companies info** (List). Get information about the company in Namely. Returns the company record including its id and company-specific attribute fields.
- **List all Namely profiles** (List). List Namely profiles. Returns each profile's id, created_at, and updated_at. Supports page and per_page (max 50), sort, profile_format, and filters passed as filter[first_name], filter[last_name], filter[email], filter[personal_email], filter[job_title], filter[reports_to] or filter[user_status]. Rate limited to 100 requests per minute.
- **Get single Namely profile by ID** (Get). Get a single Namely profile by id. Returns the profile's id, created_at, and updated_at. Required: id.
- **Create a Namely profile** (Create). Create a profile (employee record) in Namely. Send the profile fields inside the profiles array in the body; first_name, last_name, email and user_status are the minimum. Set a start_date and job_title where known. To create the profile as a draft Onboarding session instead, the Onboarding feature must be enabled for the company and the request must include the onboarding session fields documented on the Create a Profile page. Returns the created profile under profiles with its id, created_at and updated_at. Returns: id, created_at, updated_at, first_name, last_name, email, user_status, start_date, job_title, links.
- **Update a Namely profile by ID** (Update). Update a profile in Namely by id. Only include the fields that should change inside the profiles array in the body; omitted fields are left as they are. Salary, job title, reports_to and other effective-dated fields are set the same way as on create. Returns the updated profile under profiles. Returns: id, created_at, updated_at, first_name, last_name, email, user_status, start_date, job_title, links. Required: id.
- **List all Namely groups** (List). List the groups that belong to a group type in Namely. Returns: id, created_at, updated_at. Required: group_id.
- **Namely groups list all** (List). Returns an array of all groups. Every group must belong to one and only one group type. Each group type can have zero to many associated groups. Although not present in this endpoint, each group can also have zero to many associated profiles (i.e. people within groups). Office Locations and Departments are groups. Lists every group across all group types; use groups.list to list the groups of one group type. Returns: id, title, type, is_team, address, count, links.
- **Get single Namely group by ID** (Get). Returns same information about the group as in the corresponding list endpoint, as well as linked any profiles associated with that group (zero to many). Returns: id, title, type, address, links, linked. Required: id.
- **List all Namely folders** (List). This endpoint returns a list of folders and their information. Returns: id, title, type, items_count, position.
- **Create a Namely folder** (Create). To create a folder, a title is required. An array of folders will be returned upon success, similar to folders index endpoint. Returns: id, title, type, items_count, position.
- **Update a Namely folder by ID** (Update). Updates the name of a folder. Returns: id, title, type, items_count, position. Required: id.
- **Delete a Namely folder by ID** (Delete). You must pass in the folder id to delete a specific folder. Required: id.
- **Get single Namely resource by ID** (Get). Specify the id of the resource to get a complete description. Please see "Download Resource" documentation to actually download a specific resource. Returns the resource record (Namely nests it under "groups" in the raw response). Returns: id, title, link, file_name, file_format, file_size, file_url, last_edited, folder_id. Required: id.
- **List all Namely resources** (List). Get Resources not in a Folder Lists resources that are not in any folder. Returns: id, title, link, file_name, file_format, file_size, file_url, last_edited, folder_id.
- **List all Namely folder resources** (List). This method returns an array of resources, whose format and content will be the same as the show resource endpoint. Returns: id, title, link, file_name, file_format, file_size, file_url, last_edited, folder_id. Required: folder_id.
- **Delete a Namely folder resource by ID** (Delete). This endpoint deletes a specified resource. Pass the resource id as id. Required: id.
- **List all Namely group types** (List). Returns an array of all group types. Although not present in this endpoint, every group must belong to one and only one group type. Each group type can have zero to many associated groups. Each group type can also have zero to many associated profiles (i.e. people within groups that belong to those group types). Returns: id, field_name, title, deletable, type, x_groups_as_teams.
- **Get single Namely group type by ID** (Get). Returns same information about the group as in the corresponding list endpoint, as well as linked any profiles associated with that group type (zero to many). Returns: id, field_name, title, deletable, type, x_groups_as_teams. Required: id.
- **List all Namely teams** (List). Returns an array of all teams as well as linked, a list of team categories. Every team can belong to zero to many team categories. Each team category can have zero to many associated teams. Although not present in this endpoint, each team can also have zero to many associated profiles (i.e. people within teams). Returns: id, name, email, updated_at, created_at, links.
- **Get single Namely team by ID** (Get). Get a Team Returns: id, name, email, updated_at, created_at, links. Required: id.
- **List all Namely events** (List). Returns all events, paginated. Linked to the event is an array of any profiles that commented on the event. Only events associated with the profiles of active employees are eligible to appear. To filter by type (birthday, announcement, recent_arrival, anniversary) pass the query parameter filter[type]. Paginate manually with limit and after. Returns: id, href, type, time, ufc_offset, content, html_content, years_at_company, use_comments, can_comment.
- **Create a Namely event** (Create). Creates an announcement. Other event types are auto-generated and cannot be manually created. The file parameters allow you to include a file which is located in the announcement. As with uploading a file to a profile, the file must be previously uploaded via the `file create` endpoint. Creates an announcement on the home feed. Returns: id, href, type, time, ufc_offset, content, html_content, years_at_company, use_comments, can_comment.
- **Get single Namely event by ID** (Get). Returns information about a single event. Returns: id, href, type, time, ufc_offset, content, html_content, years_at_company, use_comments, can_comment. Required: id.
- **Delete a Namely event by ID** (Delete). Delete a particular event. Deletes an announcement. Returns: message. Required: id.
- **List all Namely event comments** (List). Returns all comments associated with a particular event. Returns: id, content, html_content, created_at, can_destroy, links, utc_offset, likes_count, liked_by_current_profile. Required: event_id.
- **Create a Namely event comment** (Create). Creates a comment on a particular event. Returns: id, content, html_content, created_at, can_destroy, links, utc_offset, likes_count, liked_by_current_profile. Required: event_id.
- **Delete a Namely event comment by ID** (Delete). Delete a particular comment on an event. Pass the comment id as id. Returns: message. Required: id, event_id.
- **List all Namely event likes** (List). Returns a list of profiles that liked a particular event. Returns: id, href, full_name, job_title, links. Required: event_id.
- **Create a Namely event like** (Create). Like a particular event simply by `POST`ing to the endpoint with its id in the path parameters. No request body. Returns: likes_count, liked_by_current_profile. Required: event_id.
- **Delete a Namely event like by ID** (Delete). Delete a particular like from an event. Pass the event id as id; removes the token bearer's like. Returns: message. Required: id.
- **List all Namely comment likes** (List). Returns a list of profiles that liked a particular comment on a particular event. Returns: id, href, full_name, job_title, links. Required: comment_id.
- **Create a Namely comment like** (Create). Like a comment on a home feed event as the token bearer. Pass the comment id as comment_id. No request body, and Namely does not document a response body for this call; a 2xx status means the like was recorded. Required: comment_id.
- **Delete a Namely comment like by ID** (Delete). Delete your like from a particular comment. You can only delete your own like (from the profile related to the token). Pass the comment id as id; removes the token bearer's like. Returns: message. Required: id.
- **List all Namely job tiers** (List). Returns an array of all job tiers. Each job tier can have zero to many linked job titles (while each job title must have one and only one linked job tier). Returns: id, numerical_id, title, links.
- **Create a Namely job tier** (Create). Creates a job tier. Returns: id, numerical_id, title, links.
- **Get single Namely job tier by ID** (Get). Returns information about a single job tier. Returns: id, numerical_id, title, links. Required: id.
- **Update a Namely job tier by ID** (Update). Updates the label of a job tier. Use the corresponding list endpoint to get a list of job tiers, whose id is used in the path parameters. Returns: id, numerical_id, title, links. Required: id.
- **List all Namely job titles** (List). Returns all job titles. Each job title must have one and only one linked job tier (and each job tier can have zero to many linked job titles). When using the corresponding list endpoint, the API user must either use the title or id of a job_title . Returns: id, parent_id, title, links.
- **Create a Namely job title** (Create). Creates a job title. Use the corresponding list endpoint to get a list of job tiers, whose id is used to populate the value for the parent (job tier) key in the request body. Returns: id, parent_id, title, links.
- **Get single Namely job title by ID** (Get). Returns information about a single Job Title.. When using the corresponding list endpoint, the API user must either use the title or id of a job_title . Returns: id, parent_id, title, links. Required: id.
- **Update a Namely job title by ID** (Update). Updates the label and/or parent (job tier) of a job title. Use the corresponding list endpoint to get a list of job tiers, whose id is used to populate the value for the parent (job tier) key in the request body. If not updating the parent , use the id of the current parent value; if not updating the title , use the current job title title . Returns: id, parent_id, title, links. Required: id.
- **List all Namely countries** (List). Returns all valid countries in Namely. A country is universal and may not be modified. Returns: id, name, subdivision_type.
- **Get single Namely country by ID** (Get). Returns one country, as well as a list of a country’s subdivisions (e.g. a list of its states or provinces). Returns: id, name, subdivision_type, links. Required: id.
- **List all Namely notifications** (List). Returns all notifications for the current API user/token bearer. There are three main types of notifications: 1. Time Off 2. Mentioned/Appreciated 3. Generic (All Other) Notifications for the token bearer. Returns: id, text, type, timestamp, seen, read, links.
- **List all Namely profile notifications** (List). Returns notifications for a profile in a paginated form. By default, there will be 30 notifications per page. At most, you can request 50 notifications per page. There are three main types of notifications: 1. Time Off 2. Mentioned/Appreciated 3. Generic (All Other) Paginated with page and per_page (default 30, max 50). Returns: id, text, type, timestamp, seen, read, links. Required: profile_id.
- **List all Namely profile fields** (List). Returns all profiles fields as configured at your company with instructions on valid format for passing through the API. This includes custom fields, but exceptions can be found on the the related endpoint page. Returns: id, name, label, type, default, deletable, valid_format_info, block_index, links.
- **Create a Namely profile field** (Create). Creates a profile field within a profile field section. Returns: id, name, label, type, default, deletable, valid_format_info, block_index, links.
- **Get single Namely profile field by ID** (Get). Returns information about a single Profile Field. Returns: id, name, label, type, default, deletable, valid_format_info, block_index, links. Required: id.
- **Update a Namely profile field by ID** (Update). Updates a profile field within a profile field section. Supports changing the label and the profile field section in which it sits. Returns: id, name, label, type, default, deletable, valid_format_info, block_index, links. Required: id.
- **List all Namely profile field sections** (List). Returns all profiles field sections as configured at your company. Linked to this endpoint is a list of profile fields, including additional fields not necessarily included in the corresponding list endpoint, as not all are API transferrable. Returns: id, title, block_titles, links.
- ...and 4 more tools. Call `tools/list` via the MCP endpoint, or see the full catalog via the API, for the complete set.
