search_conversationsLABSCO SUMMARY
The cache is the feature, not an optimisation.
Asking an assistant to analyse support conversations means many queries over the same window, and doing that through the API is slow enough that you stop asking. Holding the corpus locally changes what kinds of question are worth asking — you can iterate on a search instead of budgeting for it. The trade is a copy of your customer conversations sitting on the machine that runs it, and a first sync you have to wait through before anything is answerable.
What it is
An Intercom analytics server that keeps conversations locally rather than calling the API on every question. A background sync keeps the cache fresh, requests are served from SQLite, and stale timeframes trigger an update for next time. Storage is around 2KB per conversation, and search accepts natural-language timeframes like "last 7 days".
What you get
search_conversationssearches message text with a natural-languagetimeframe, acustomer_emailfilter and alimitget_conversationreturns the full detail of one conversation by IDsync_conversationstriggers a sync manually, withforcefor a full passget_server_statusreports server state and statistics- A local SQLite store with an optimised schema, so repeat questions do not re-hit the API
Requirements
An Intercom access token, set as INTERCOM_ACCESS_TOKEN. Python and a checkout: create a virtualenv and pip install -e . (package fast-intercom-mcp, version 0.3.0), then fast-intercom-mcp init, fast-intercom-mcp sync --force --days 7 to seed the cache, and point your client at fast-intercom-mcp start. Sync freshness and the background interval are set through FASTINTERCOM_MAX_SYNC_AGE_MINUTES and FASTINTERCOM_BACKGROUND_SYNC_INTERVAL, or the config file at ~/.fast-intercom-mcp/config.json.
Setup effort
One command plus a key — fast-intercom-mcp start, then supply credentials
USE CASES
01
Finding out what customers complained about this week
Search the message text with a plain-language timeframe.
02
Pulling up a customer's history before you reply
Filter by their email, then open the conversation in full.
03
Spotting a theme across many tickets
Run repeated searches over the local cache and let the model group what it finds.
04
Making sure you are looking at current data
Check the sync state, and force a fresh pass if it has drifted.
4 tools
Listed in project docs. Your client may show a different list.
get_conversationget_server_statussync_conversationsBEFORE YOU INSTALL
What to know first
Tools you get
4 tools named in the project's documentation.
Requires
- fast-intercom-mcp on PATH
- INTERCOM_ACCESS_TOKEN in your environment
Where it runs
Both documented setups run the server on your machine.
INSTALLATION
Connect your client
Server setup
TERMINAL
fast-intercom-mcp startMCP Clients
Claude Desktop
CLAUDE DESKTOP · JSON
{
"mcpServers": {
"fast-intercom-mcp": {
"command": "fast-intercom-mcp",
"args": [
"start"
],
"env": {
"INTERCOM_ACCESS_TOKEN": "<YOUR_INTERCOM_ACCESS_TOKEN>"
}
}
}
}Claude Desktop — Docker
CLAUDE DESKTOP — DOCKER · JSON
{
"mcpServers": {
"fast-intercom-mcp": {
"command": "docker",
"args": [
"exec",
"-i",
"fastintercom-mcp",
"python",
"-m",
"fast_intercom_mcp.cli",
"start"
],
"env": {
"INTERCOM_ACCESS_TOKEN": "<YOUR_INTERCOM_ACCESS_TOKEN>"
}
}
}
}
