How is this different from connecting Fathom 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 Fathom MCP API changes?

We track the Fathom 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 Fathom 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 Fathom?

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 Fathom MCP server myself?

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

Connect Fathom MCP to your AI agents, securely.

Q: Is Fathom MCP secure?

The server itself exposes 12 tools, and some of them can write to your Fathom 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 Fathom.

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

Get started for free

Get a demo

Try Fathom MCP now

What your agents can ask once Fathom MCP is connected.

Select the tools your AI agents can call

12 tools from the Fathom MCP schema.

Showing 12 tools

list_meetingsreadLists meetings with filters for date range, participants, team and external-only calls.
search_meetingsreadSearches meetings by keyword across titles and summaries, not full transcripts.
find_relevant_meetingsreadTargeted ranked retrieval for specific facts, decisions, quotes, named projects, companies, products, people-plus-topic questions, or locating the best matching meetings.
get_relevant_meetings_resultreadReturns the find_relevant_meetings result for a search_id.
scan_meeting_summariesreadBroad chronological scan for themes, patterns, frequency, change over time, comparisons, or synthesis across many meetings.
find_personreadFinds a person by name across meeting speakers and returns their meetings with short summaries.
list_teamsreadLists all accessible teams.
get_identityreadReturns the authenticated user's name and email address.
get_meeting_summaryreadReturns the AI summary of a specific Fathom meeting.
get_meeting_transcriptreadReturns the full transcript of a specific Fathom meeting.
get_recording_by_call_idreadResolve a Fathom call ID to a recording_id plus title, date, and url.
get_recording_by_urlreadResolve a Fathom URL to a recording_id plus title, date, and url.

What Fathom MCP exposes

Fathom MCP groups its 12 tools into 3 categories, each with a suggested starting policy.

All 12 tools as JSON, ready to paste.

Category	Covers	Access	Suggested policy
Meetings	Meeting listing with filters and search across titles and summaries	Read	Treat meeting content as sensitive customer data
Content	AI summaries, full speaker-labelled transcripts and action items	Read	Transcripts can contain anything said on a call; restrict access
People & Teams	Finding a person across meeting speakers, teams and team members	Read	Limit organization access

Connect Fathom 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 Fathom
Find Fathom 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 Fathom MCP or block it. You allow the exact tools each agent can call, one by one.

Fathom MCP	12 TOOLS AVAILABLE
Code review agent	4 tools, read only
Issue triage bot	9 tools
Platform team assistant	all 12 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 Fathom 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.	Fathom MCP12 documented tools.
Coding assistants	Connection & credentialsper user	Meetings5 tools
Internal copilots	Tool access policiesdeny by default	Content4 tools
Workflow automations	Request & response inspectioninline	People & Teams3 tools
Compatible MCP clients	Activity monitoringalerts and logs