Enterprise Search Aggregator
Search across all connected sources with a single unified query
The answer is somewhere in Slack, or maybe the Google Doc from Q3, or that Notion page someone linked in an email. You search five tools and find nothing because enterprise knowledge is scattered across a dozen disconnected silos.
Who it's for: knowledge workers searching across too many tools, operations teams needing unified information access, managers who can't find decisions made in Slack three months ago, IT teams building internal search solutions, anyone who spends 30 minutes finding a document they know exists
Example
"Find everything we discussed about the pricing change last quarter" → Single query searches Slack, email, Google Drive, Notion, and Jira in parallel — returns deduplicated results ranked by relevance with source links and a synthesized summary
CLAUDE.md Template
New here? 3-minute setup guide → | Already set up? Copy the template below.
npx ccplaybooks add enterprise-search-aggregator# Enterprise Search Aggregator
Search across all connected sources in a single query. Decompose the user's question, run parallel searches, and synthesize results.
## Instructions
### 1. Check Available Sources
Before searching, determine which MCP sources are available. Attempt to identify connected tools from the available tool list. Common sources:
- **Chat** — chat platform tools
- **Email** — email toolsGet new playbooks like this one
One email a week with new Claude Code workflows. Free, like everything here.
No spam. Unsubscribe anytime.
What This Does
This playbook turns Claude into a unified search assistant that queries across all your connected MCP sources -- chat, email, cloud storage, project trackers, CRMs, and knowledge bases -- in a single request. It decomposes your question into targeted sub-queries, runs them in parallel, deduplicates and ranks results, and synthesizes a single coherent answer with source attribution.
Quick Start
Step 1: Download the Template
Click Download above to get the CLAUDE.md file.
Step 2: Set Up Your Project
Create a project folder and place the template inside:
mkdir -p ~/Documents/EnterpriseSearch
mv ~/Downloads/enterprise-search-aggregator.md ~/Documents/EnterpriseSearch/CLAUDE.md
Step 3: Connect Your Sources
Ensure you have at least one MCP source connected (chat, email, cloud storage, project tracker, CRM, or knowledge base) in your Claude Code MCP settings.
Step 4: Start Working
cd ~/Documents/EnterpriseSearch
claude
Say: "Find that doc about the Q4 budget proposal"
Supported Filter Syntax
You can use inline filters in your queries to narrow results:
from:-- Filter by sender or authorin:-- Filter by channel, folder, or locationafter:-- Only results after a specific datebefore:-- Only results before a specific datetype:-- Filter by content type (message, email, doc, thread, file)
Example: "from:sarah in:#engineering after:2026-01-01 API migration"
Tips
- Be specific about what you need -- "what did we decide about pricing" works better than "pricing"
- Mention people or channels when you remember where a conversation happened
- Use time constraints like "this week" or "last month" for recent items
- One source is fine -- the assistant still works well even with just one connected source
- Results are synthesized into answers, not raw lists, so you get context immediately
Example Prompts
"Find that doc about the Q4 budget proposal"
"What did we decide on the API redesign last week?"
"Where was the conversation about the new vendor contract?"
"from:alex in:#product-launches type:doc feature roadmap"
"What do we know about Project Aurora?"