Connect the Fireflies MCP server to Unblocked to give AI agents live meeting context
Unblocked connects to Fireflies’ MCP server so AI coding agents can search your meeting transcripts, summaries, and action items live — then its Context Engine reconciles what they find with the code, pull requests, and conversations behind it.
Fireflies integration details
What the Fireflies integration adds
Many engineering decisions are made out loud — in a design review, a sprint planning call, or a customer escalation — and Fireflies records and transcribes them. Those decisions rarely make it into the ticket or the pull request, so an agent working on the code never hears why the team chose one approach over another. Fireflies’ MCP server exposes meeting transcripts and summaries to AI agents, and Unblocked connects to it once so every agent can ask about a meeting without its own Fireflies setup.
This is a third-party MCP server: Fireflies hosts and maintains it, and Unblocked connects to it as a verified MCP server. Nothing is ingested or indexed — Unblocked calls the read-only tools you select at the moment a question needs them, so answers reflect your meetings as Fireflies holds them now, including calls transcribed since the last time anyone asked.
Wiring Fireflies’ MCP server straight into an agent gives it raw transcripts. Unblocked’s Context Engine reasons across those results and your other sources — following an action item from a design review to the ticket that captured it, the pull request that delivered it, and the Slack thread where the plan later changed — and returns one cited answer.
Once connected, any MCP-compatible coding agent — Claude Code, Cursor, Devin, GitHub Copilot, Codex — reaches Fireflies context through a single Unblocked MCP server connection.
What you get
- Live transcripts and summaries — Agents search meetings and read transcripts, summaries, and action items as Fireflies holds them right now, through Fireflies’ own MCP server.
- One connection for every agent — Connect Fireflies to Unblocked once. Claude Code, Cursor, Codex, and GitHub Copilot reach it through the Unblocked MCP server, with no per-agent Fireflies configuration.
- Read-only, meeting-safe control — Only read-only tools are offered, so agents can’t share meetings, revoke access, rename transcripts, or move them between channels. Choose which tools Unblocked may call from Settings → Data Sources.
- Context Engine reasoning — Fireflies results are reconciled with your code, pull requests, tickets, and conversations, so a decision made on a call leads to the change it produced — with citations.
How to connect Fireflies to Unblocked
Prerequisites
- An Unblocked account (free to start).
- A Fireflies account with access to the meetings you want to query, and permission to authorize Unblocked to connect to it.
- An MCP-compatible coding agent (Claude Code, Cursor, Devin, etc.) to use the context in your editor.
Step 1: Connect Fireflies to Unblocked
- In Unblocked, go to Settings → Data Sources → Connect another data source, and under Documentation select Fireflies.
- The Fireflies MCP server URL is filled in for you. Choose OAuth, click Connect, and sign in to Fireflies to authorize Unblocked.
- Once Unblocked discovers the server’s tools, select the read-only tools it may use and click Save Settings.
Step 2: Install the Unblocked MCP server
On macOS or Linux, one command auto-detects and configures the supported agents on your machine:
curl -fsSL https://getunblocked.com/install-mcp.sh | bash On Windows, or when you prefer remote MCP, add the server manually using the configuration below, or follow the manual install guide .
Claude Code
Add the remote server, then run /mcp in Claude Code, select unblocked, and log in via OAuth:
claude mcp add -s user --transport http unblocked https://getunblocked.com/api/mcpsseCursor
Open View: Open MCP Settings → Add Custom MCP, add the server, then click Connect to authenticate via OAuth:
{
"mcpServers": {
"unblocked": {
"url": "https://getunblocked.com/api/mcpsse"
}
}
}Other MCP clients
Any MCP-compatible client (Devin, Codex, VS Code, Claude Desktop, and others) can connect to the remote server with OAuth:
https://getunblocked.com/api/mcpsseFireflies MCP server tools
Fireflies hosts and maintains this MCP server. Unblocked calls only the read-only tools you select, at the moment a question needs them:
fireflies_searchSearches meeting transcripts using Fireflies’ query grammar. Fireflies marks this tool as experimental.fireflies_get_transcriptsQueries multiple meetings with structured filters and returns their metadata and summaries.fireflies_get_transcriptReturns the detailed transcript of a meeting by its ID, with speakers and timestamps.fireflies_get_summaryReturns a meeting’s summary, including its overview, keywords, and action items.fireflies_list_channelsLists the channels and folders available to the connected user.
Connect Fireflies to Claude Code, Cursor, and other AI agents
To give Claude Code, Cursor, GitHub Copilot, Codex, or another MCP-compatible AI coding agent access to Fireflies context, connect Fireflies to Unblocked and add the single Unblocked MCP server to your agent.
Unblocked acts as the MCP context layer for your Fireflies data, searching meeting transcripts and meeting summaries alongside your other connected sources and returning cited results through these tools:
context_researchResearches a question across your connected sources and calls the Fireflies tools you selected when meeting transcripts or summaries are relevant, returning a synthesized answer with citations.context_get_urlsFetches the full content behind URLs your agent encounters across connected sources — Jira, Linear, Notion, Confluence, Slack, GitHub, and more.
Questions to ask an AI agent about Fireflies
Questions you (or your agent) can ask Unblocked about your Fireflies data:
What did we decide about the caching strategy in last week’s architecture review, and has a pull request implemented it yet?
Which action items from the incident postmortem call still have no ticket?
Did the customer on yesterday’s escalation call describe the same bug as the open Jira issue, and who is working on it?
Summarize the sprint planning meeting and link each commitment to its ticket or pull request.