Supported Tools

What this page covers

This page answers a simple question: what can an AI assistant realistically help with in Enginy today? Enginy MCP does not ship a separate hand-written tool catalog. Instead, the MCP server reads Enginy’s public API document and turns supported API operations into MCP tools. That means the MCP surface stays aligned with the public API. The current MCP server also exposes a few native tools:

mcp_whoami, which returns the authenticated user, client, and granted scopes
mcp_get_profile, which returns the connected Enginy account (a stable, opaque profile id plus name, email, and workspace) so clients such as ChatGPT can tell several connected Enginy accounts apart (available on ChatGPT connections, and elsewhere only in the Sales Workspace early access; never on the reduced toolset)

Interactive workspace in ChatGPT and Claude

Clients that render MCP Apps — ChatGPT and Claude — can also open the Enginy Sales Workspace (in early access: ask your Enginy contact to enable it for your workspace), an interactive view that runs inside the conversation. The assistant opens it with the native open_enginy_workspace tool (in ChatGPT you can also launch it from the sidebar), and it covers:

Prospects — preview an AI Finder search, refine it, and import it into a new or existing list; browse a list, select contacts or companies (the assistant sees your selection), and run enrichment such as finding or verifying emails.
Outreach — draft an email sequence for a contact list and create it as a draft campaign.
Campaigns — review campaign performance: contacts reached, reply rates, per-channel stats, and daily activity.

The workspace uses the same tools and permissions as the rest of Enginy MCP, and it never sends messages or launches campaigns: it creates drafts that you review and launch in Enginy. Imports and enrichment spend credits, and the view shows the estimated cost before you start them. Clients without MCP Apps support just get a short text reply from open_enginy_workspace.

What an assistant can help with today

The current surface is broad enough for real operator workflows. Representative capability families include:

Capability family	Representative things you can do
Workspace	Read workspace metadata, credits, saved views, and validation helpers; create, read, and delete saved filters; read and update the AI Playbook
Identities	Inspect sender identities and identity performance
Owners	Look up CRM owners for routing and assignment flows
Campaigns	Read campaigns and folders, create campaigns, clone campaigns, and change campaign state
Contacts	Search contacts, read contact fields, create contacts, and update contacts
Companies	Search companies, read company fields, create companies, and update companies
Lists	Read lists and folders, create, update, or delete lists, and move members
AI variables	Read AI variables and their folders (contact, company, AI message, AI snippet, message template), create or update them, and delete them
Analytics	Read analytics exports and campaign analytics
AI Finder	Preview, refine, and import new prospect lists; use `identityId` only for explicit identity-specific LinkedIn searches
Actions	Inspect action-run state and trigger action-style workflows such as imports
Messaging	Read inbox threads, tags, and conversation messages; send replies; mutate thread state
Webhooks	Read webhook subscriptions and logs, and create, update, delete, or test webhooks
Workflows	Build, validate, publish, run, and monitor advanced (graph) workflows — see the agent guide
Social Selling	Read post analytics and engagers, export engagers to a list, comment, react, and schedule posts (tools)

In practice, what the assistant can successfully do depends on two things: whether the action exists in the public API, and whether the approved permissions allow it. If a tool exists but your permissions are too narrow, the call will be blocked when the assistant tries to use it.

Social Selling has its own tools, all gated by the Social Selling feature. MCP clients only list them for users who have it, and the REST endpoints answer 403 to anyone else. The read tools need SOCIAL_SELLING_READ and the write tools need SOCIAL_SELLING_WRITE. Over MCP they only reach the identities the connected user may use. The Social Selling guide explains the two post ids, credits and approvals.

Area	Tools
Analytics	`get_social_selling_overview`, `list_social_selling_identity_performance`, `get_social_selling_best_publishing_times`
Audience	`list_social_selling_posts`, `get_a_social_selling_post`, `list_social_selling_engagers`, `list_social_selling_post_engagers`, `preview_social_selling_engager_export`, `export_social_selling_engagers_to_a_list`
Engagement	`track_a_social_selling_post`, `add_a_comment_to_a_social_selling_post`, `generate_social_selling_comment_suggestions`, `add_reactions_to_a_social_selling_post`
Publishing	`schedule_a_social_selling_post`, `list_scheduled_social_selling_posts`, `cancel_a_scheduled_social_selling_post`

The write tools are export_social_selling_engagers_to_a_list, track_a_social_selling_post, add_a_comment_to_a_social_selling_post, add_reactions_to_a_social_selling_post, schedule_a_social_selling_post and cancel_a_scheduled_social_selling_post. preview_social_selling_engager_export and generate_social_selling_comment_suggestions only read: they create, post and store nothing.

Advanced: how tool inputs are shaped

OpenAPI-derived tools follow a simple input pattern:

{
  "pathParams": {
    "id": "123"
  },
  "query": {
    "limit": 25,
    "includeArchived": false
  },
  "body": {
    "name": "Example"
  }
}

In practice:

pathParams holds route parameters; numeric values are accepted for string-typed ID parameters and are serialized into the path as strings
query holds query-string arguments
body holds JSON request bodies

The tool name usually comes from the OpenAPI summary. If names would collide, Enginy falls back to a method-plus-path style name. Tool names are always 64 characters or fewer.

Tool annotations

Every tool advertised in tools/list carries MCP annotations so clients can reason about safety before calling:

title: a human-readable label.
readOnlyHint: true for tools that only read data, false for tools that create, update, or delete data.
destructiveHint: true on write tools that modify or remove data.
idempotentHint: true when repeating the call with the same arguments has no additional effect.

Read versus write is derived from the operation’s required scope (for example, a *_write scope marks a tool as a write), so the hints stay aligned with what the public API actually does.

What is not guaranteed yet

Tool names can change if the OpenAPI summary changes.
Coverage changes whenever Enginy’s public API surface changes.
Some operations may not be available if they are not part of the public contract.
Most tools are generated from OpenAPI; a few native tools such as mcp_whoami, mcp_get_profile, and open_enginy_workspace are built into the server.
The MCP server is remote Streamable HTTP only. It is not a local stdio server.

What to try first

If you are deciding whether MCP is useful for your workflow, start with:

mcp_whoami to confirm the connection and granted scopes.
The overview page to understand the transport and policy model.
The scopes page to see which permission families unlock which tools.
The client support matrix for the dedicated setup page for your client.

Overview

Review the hosted server model, OpenAPI-derived tool generation, and runtime policy enforcement.

Client support matrix

Find the setup page for Claude, Codex, Cursor, VS Code, Gemini CLI, Microsoft 365 Copilot, ChatGPT, and more.

Scopes

Match the tool families above to the scope groups that unlock them.

Security & troubleshooting

Debug auth, scope, and compatibility problems before assuming the server is broken.

Getting started

Clients

Guides

Reference

What this page covers

Interactive workspace in ChatGPT and Claude

What an assistant can help with today

Advanced: how tool inputs are shaped

Tool annotations

What is not guaranteed yet

What to try first

Overview

Client support matrix

Scopes

Security & troubleshooting

​What this page covers

​Interactive workspace in ChatGPT and Claude

​What an assistant can help with today

​Social Selling tools

​Advanced: how tool inputs are shaped

​Tool annotations

​What is not guaranteed yet

​What to try first

Overview

Client support matrix

Scopes

Security & troubleshooting

What this page covers

Interactive workspace in ChatGPT and Claude

What an assistant can help with today

Social Selling tools

Advanced: how tool inputs are shaped

Tool annotations

What is not guaranteed yet

What to try first