Slunk (Slack Conversation Search)
This MCP server provides intelligent Slack message search and monitoring capabilities through a Swift/SwiftUI macOS application that captures Slack conversations in real-time using accessibility APIs and stores them locally with SQLite and vector embeddings. Built with Apple's NLEmbedding framework for semantic search, GRDB for database operations, and SQLiteVec for vector storage, it offers 8 specialized search tools including natural language conversation search, precise message filtering with channel/user/date constraints, thread context retrieval, cryptic message interpretation, query parsing with entity extraction, multi-turn conversational search, pattern discovery, and semantic similarity suggestions. The implementation features content-based deduplication to prevent storing duplicate messages during polling intervals, hybrid search combining semantic and keyword matching, automatic embedding generation for new messages, and configurable monitoring intervals (5s active, 10s background, 30s inactive), making it valuable for Slack workspace analysis, conversation discovery, and building AI assistants that need deep access to team communication history without manual Slack search limitations.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-02.
Scan details: Circle-IR · 2026-09-02 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- database
- Source
- PulseMCP
- Repository
- github.com/kimjune01/slunk-mcp
- Author type
- human
- Last scanned
- 2026-09-02
- Updated
- 2026-09-02
Use via MCP
Resolve Slunk (Slack Conversation Search) from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.