How is this different from connecting Intercom MCP directly?

Connected directly, an agent sees every tool the server exposes and holds the credential itself. Through TrustGate you choose which tools each agent gets, and every call is logged against the agent that made it.

What if the Intercom MCP API changes?

We track the Intercom MCP schema, so the tool catalogue stays current. Tools you have already allowed keep working, and anything new stays denied until you enable it.

Can I give different agents different Intercom tools?

Yes. Access is set per agent: one can get a handful of read tools, another the full set. You grant the whole MCP or single tools within it.

Where can I see what my agents did in Intercom?

Every call is logged against the agent that made it, with the tool it used. Activity can be sent on to your own monitoring.

Do I need to run the Intercom MCP server myself?

No. TrustGate connects to the Intercom MCP server and sits in front of it. Your agent only talks to your TrustGate URL, never to Intercom directly.

Connect Intercom MCP to your AI agents, securely.

Q: Is Intercom MCP secure?

The server itself exposes 19 tools, and some of them can write to your Intercom account. Behind TrustGate an agent only sees the tools you allow, requests and responses are inspected, and every call is logged. Anything outside the allowlist is denied before it reaches Intercom.

One secured endpoint for every Intercom call your AI agents make, scoped per user, inspected, and logged.

Get started for free

Get a demo

Try Intercom MCP now

What your agents can ask once Intercom MCP is connected.

Select the tools your AI agents can call

19 tools from the Intercom MCP schema.

Showing 19 tools

searchreadUniversal search for Intercom resources using a query DSL. Requires object_type conversations or contacts.
search_conversationsreadSearches conversations with filters on state, source, author and timing.
search_contactsreadSearches contacts by ID, name, email, phone, custom attributes or email domain.
fetchreadFetches the full details of a conversation or contact by the prefixed ID returned from search.
get_conversationreadGets a conversation with its full message history.
add_internal_notewriteAdds an internal note to a conversation, visible to teammates only.
get_contactreadGets a contact record with its attributes and recent activity.
list_companiesreadLists the companies in the workspace.
get_companyreadGets a company record and the contacts associated with it.
search_articlesreadSearches Help Center articles by phrase.
get_articlereadGets the content of a Help Center article.
create_articlewriteCreates or updates a Help Center article, when the token permits it.
list_articlesreadLists all articles in the Intercom Help Center.
update_articlewriteUpdates an existing Help Center article.
send_operator_messagewriteSends a message to Fin Operator; the answer is collected later.
get_operator_responsereadReads the latest response from a Fin Operator chat.
get_proposal_detailsreadShows what each pending Fin Operator proposal would change.
apply_proposalshigh riskApplies Fin Operator proposals to the workspace's live configuration.
reject_proposalswriteDiscards Fin Operator proposals.

What Intercom MCP exposes

Intercom MCP groups its 19 tools into 5 categories, each with a suggested starting policy.

All 19 tools as JSON, ready to paste.

Category	Covers	Access	Suggested policy
Search	Unified query DSL across conversations and contacts, plus dedicated search tools	Read	Grant read-only scopes; the server reaches customer data
Conversations	Conversation details and internal notes	Read / Write	Review the internal notes agents add
Contacts & Companies	Contact and company lookup and details	Read	Treat contact records as personal data
Help Center	Article search, reading, creation and updates	Read / Write	Review article content before publishing
Fin Operator	Fin Operator chats and configuration proposals, for workspaces with Fin Operator	Read / Write	Allow reading; require approval before applying proposals to live configuration

Connect Intercom MCP to your AI agent

Four steps, under ten minutes.

01
Sign in to NeuralTrust
Open the NeuralTrust platform, sign in and go to Getting started, then Connect your tools.
02
Choose your agent
When asked which agent you use, pick Claude Code, Codex, Cursor, Windsurf, Copilot or your own code.
03
Connect Intercom
Find Intercom in the tool list and connect it.
04
Connect your agent
Follow the steps on screen to add the config to your agent, then send the test prompt.

Permissions down to the single tool

You do not allow Intercom MCP or block it. You allow the exact tools each agent can call, one by one.

Intercom MCP	19 TOOLS AVAILABLE
Code review agent	4 tools, read only
Issue triage bot	9 tools
Platform team assistant	all 19 tools

Tool by toolConnecting the server is not the unit of access. Each tool is granted on its own.
Default denyA tool you have not enabled is never exposed to the agent.
Approval on writesTools that change or delete things can require a human to confirm.

Is Intercom MCP secure?

One endpoint instead of raw credentials. Every call is checked against policy and logged.

AI agentsConnect through your MCP client configuration.	NeuralTrustApply controls based on your configuration.	Intercom MCP19 documented tools.
Coding assistants	Connection & credentialsper user	Help Center5 tools
Internal copilots	Tool access policiesdeny by default	Fin Operator5 tools
Workflow automations	Request & response inspectioninline	Search4 tools
Compatible MCP clients	Activity monitoringalerts and logs	All other tools5 tools